From 57a2fb96fa8b45918bb510f47f8ed00bedf63651 Mon Sep 17 00:00:00 2001 From: Aleks Date: Mon, 18 May 2026 12:03:39 +0300 Subject: [PATCH] ingest: trillion-dollar-workflow-retest --- ...6-05-18_trillion-dollar-workflow-retest.md | 146 ++++++++++------- ...llion-dollar-workflow-retest.transcript.md | 151 ++++++++++++++++++ 2 files changed, 236 insertions(+), 61 deletions(-) create mode 100644 Business/Nate Corpus/2026-05-18_trillion-dollar-workflow-retest.transcript.md diff --git a/Business/Nate Corpus/2026-05-18_trillion-dollar-workflow-retest.md b/Business/Nate Corpus/2026-05-18_trillion-dollar-workflow-retest.md index 079936d..37140bf 100644 --- a/Business/Nate Corpus/2026-05-18_trillion-dollar-workflow-retest.md +++ b/Business/Nate Corpus/2026-05-18_trillion-dollar-workflow-retest.md @@ -1,20 +1,19 @@ --- slug: trillion-dollar-workflow-retest type: video -source: https://youtu.be/jwtpMSRAPAQ -published: unknown -processed: 2026-05-18 +source: "https://youtu.be/jwtpMSRAPAQ" +date_published: unknown +date_processed: 2026-05-18 themes: - "[[Agentic Workflow]]" - "[[Implementation Layer]]" - "[[Frontier Labs]]" - - "[[Hyperscalers]]" + - "[[Systems of Record]]" - "[[Business Object]]" - "[[Moat]]" frameworks: - - "[[Four Axes of Pressure]]" - - "[[Implementation Layer Components]]" - - "[[Object-Oriented AI Model]]" + - "[[Implementation Layer]]" + - "[[Business Object]]" terminology: - "[[Implementation Layer]]" - "[[Harness]]" @@ -22,93 +21,118 @@ terminology: - "[[Evals]]" - "[[Systems of Record]]" - "[[Business Object]]" + - "[[Frontier Alliance]]" - "[[Audit Trails]]" - "[[Implementation Fabric]]" - "[[Workflow Completion]]" - - "[[Frontier Alliance]]" --- -# The Trillion Dollar Agentic Workflow Opportunity Is Here +# Trillion Dollar Agentic Workflow Opportunity + +> Источник: [YouTube](https://youtu.be/jwtpMSRAPAQ) · Обработано: 2026-05-18 + +--- ## Тезисы -- Старая финансовая парадигма «все SaaS-компании на вкус одинаковы» рушится: рост и прибыльность стагнируют, потому что SaaS не успел стать релевантным в эпоху агентов. -- Весна 2026 — переломный момент: AI-агенты впервые способны **надёжно, масштабируемо и воспроизводимо** выполнять целые бизнес-воркфлоу до 100% — это качественно новое явление ([[Workflow Completion]]). -- Узкое место не в модели, а в **[[Implementation Layer]]**: OpenAI сама признаёт, что бутылочное горлышко — это то, как агенты строятся и управляются внутри компаний. -- Диспропорциональная ценность сосредоточена в **кастомизации**, а не в универсальном продукте: «SaaS на вкус курица» больше не работает. -- Для реальных внедрений необходимы **[[Forward Deployed Engineer|forward deployed engineers]]** — специалисты, работающие «в окопах» с заказчиком. +- **Крах традиционной SaaS-модели.** Финансовый принцип «все SaaS-компании на вкус как курица» — то есть идентичны по балансу и метрикам роста, а значит удобны как инвестиционный инструмент — перестал работать: SaaS теряет актуальность в мире [[Agentic Workflow|агентских рабочих процессов]], PE-фонды вынуждены переориентироваться. +- **Триллионная возможность агентских рабочих процессов.** Весной 2026 года агенты впервые смогли надёжно, масштабируемо и воспроизводимо доводить целые бизнес-процессы до 100% ([[Workflow Completion]]). Это новое явление, открывающее рынок с триллионным потенциалом. +- **[[Implementation Layer]] — главное узкое место.** [[Frontier Labs|Frontier-лаборатории]] сами признают: bottleneck для enterprise AI — не модель, а то, как агенты строятся, управляются и управляются внутри компании. +- **Кастомизация вместо унификации.** Диспропорциональная ценность [[Agentic Workflow|агентских рабочих процессов]] — в кастомизации и глубокой интеграции в [[Implementation Fabric]] конкретной компании, а не в generic-обёртках поверх модели. +- **Необходимость «forward deployment».** Внедрение AI высокой ценности невозможно дистанционно — требуются [[Forward Deployed Engineer|forward deployed engineers]], работающие «в окопах» вместе с клиентами. Palantir был прав. + +--- ## Терминология -| Термин | EN | Определение | -|---|---|---| -| [[Implementation Layer]] | Implementation Layer / Harness | Инфраструктура вокруг модели: дизайн воркфлоу, разрешения на данные, бизнес-правила, аудит | -| [[Harness]] | Harness | Синоним implementation layer — обёртка, которая собирает модель, данные и воркфлоу в единое целое | -| [[Forward Deployed Engineer]] | Forward Deployed Engineer | Технический специалист, встроенный в среду заказчика для настройки агентов на месте | -| [[Evals]] | Evals | Не общие бенчмарки, а метод оценки соответствия выхода агента конкретным бизнес-правилам | -| [[Systems of Record]] | Systems of Record | Ключевые платформы (Salesforce, SAP, ServiceNow), хранящие авторитетные данные и открывающие API для агентов | -| [[Business Object]] | Business Object | Реальные сущности, которыми оперирует бизнес: кейсы, полисы, клиенты, пути эскалации | -| [[Implementation Fabric]] | Implementation Fabric | Кастомная совокупность данных, разрешений, воркфлоу и правил внутри конкретной компании | -| «SaaS на вкус курица» | "SaaS Tastes Like Chicken" | Финансовая поговорка: все SaaS-компании взаимозаменяемы как инвестиционный инструмент | +| RU | EN | Определение | +|----|----|-------------| +| Слой реализации | [[Implementation Layer]] | Вся инфраструктура вокруг модели: дизайн рабочего процесса, разрешения на данные, соблюдение бизнес-правил, [[Audit Trails\|аудит-трейлы]] | +| Обвязка / жгут | [[Harness]] | Синоним [[Implementation Layer]] — то, что «оборачивает» модель и делает её пригодной для enterprise | +| Полевые инженеры | [[Forward Deployed Engineer]] | Технические специалисты, встроенные в среду клиента для настройки агентов «в полях» | +| Оценки | [[Evals]] | Не бенчмарки — метод измерения соответствия вывода агента конкретным бизнес-правилам компании | +| Системы учёта | [[Systems of Record]] | Корпоративные платформы (Salesforce, SAP, Workday), хранящие авторитетные данные и открывающие API для агентов | +| Бизнес-объект | [[Business Object]] | Конкретные сущности реальной работы: кейсы, политики, клиенты, пути эскалации, воронка продаж | +| Реализационная ткань | [[Implementation Fabric]] | Совокупность кастомных компонентов [[Implementation Layer]] внутри конкретной компании | +| Ров (защитный) | [[Moat]] | Конкурентный барьер; автор оспаривает тезис «ров в данных» — настоящий ров в кастомном [[Implementation Layer]] | +| Альянс с фронтиром | [[Frontier Alliance]] | Программа партнёрств OpenAI, в которой участвуют McKinsey, BCG, Accenture, PwC и др. | +| Завершённость рабочего процесса | [[Workflow Completion]] | Способность агента довести весь бизнес-процесс до 100% — ключевая метрика ценности весны 2026 | + +--- ## Фреймворки -### [[Four Axes of Pressure]] — Четыре оси давления на agentic-воркфлоу +### Четыре оси давления (Four Axes of Pressure) -Четыре силы, которые одновременно сжимают рынок внедрения агентов: +Модель сжатия рынка generic AI для enterprise: -1. **[[Frontier Labs]] движутся вниз по стеку** — Anthropic и OpenAI строят deployment-компании, нанимают embedded-инженеров, выпускают отраслевые шаблоны (finance agents, Claude Code). -2. **Консалтинг движется вверх по стеку** — McKinsey, BCG, Accenture, PwC строят agentic-практики, обучают delivery-команды, приходят с инженерами к клиентам из [[Frontier Alliance]]. -3. **[[Systems of Record]] открывают структурированные интерфейсы** — Salesforce, Workday, SAP выпускают agent-фреймворки и API, устраняя потребность в прослойке-стартапе между данными и агентом. -4. **Private Equity как канал дистрибуции** — PE управляет тысячами портфельных компаний, может стандартизировать playbook и масштабировать одного партнёра-интегратора на весь портфель. +| Ось | Направление | Суть давления | +|-----|-------------|---------------| +| [[Frontier Labs]] | Движутся вниз по стеку | Строят deployment-компании (Anthropic + Blackstone/Goldman, OpenAI ~$10B), нанимают embedded-инженеров, запускают готовые шаблоны (Claude Design, Finance Agent) | +| Консалтинговые компании | Движутся вверх по стеку | McKinsey, BCG, Accenture, Capgemini, PwC входят в [[Frontier Alliance]], строят agentIC-практики с реальными deployment-инженерами и используют десятилетия отношений с C-suite | +| [[Systems of Record]] | Открывают структурированные интерфейсы | Salesforce, ServiceNow, Workday, SAP (Dreamio + Prior Labs) открывают API — агенты вызывают их напрямую с собственными audit trails, вытесняя посредников-стартапы | +| Private Equity | Становится каналом дистрибуции | PE владеет тысячами mid-market компаний, может стандартизировать playbooks по всему портфелю одновременно — это совершенно иной distribution shape, чем vendor-by-vendor продажи | -### [[Implementation Layer Components]] — Компоненты слоя внедрения +### Компоненты [[Implementation Layer]] -| Компонент | Суть | -|---|---| -| Workflow Design | Какие решения принимает агент, где остаётся человек, что считается «выполнено» | -| Data Access | Какие источники авторитетны, какие разрешения на уровне строк и полей | -| Authority | Лимиты трат и действий; чтение vs. запись — разные профили риска | -| [[Evals]] | Как измеряется корректность и безопасность до отправки результата | -| [[Audit Trails]] | Что логируется, как восстанавливается после сбоя, как откатывается действие | +Структурный чеклист enterprise-grade агента: -### [[Object-Oriented AI Model]] — Объектно-ориентированный подход к AI +1. **Дизайн рабочего процесса** — какие решения принимает модель, где остаётся человек, что считается «выполненным»; не промпт — определённый процесс с владельцами, входами и выходами +2. **Доступ к данным** — авторитетные источники, разрешения на уровне строк и полей, актуальность записей (живая запись vs. PDF шестимесячной давности) +3. **Полномочия (Authority)** — лимиты расходов, профиль риска (чтение vs. запись — разные категории риска) +4. **[[Evals]]** — оценка соответствия конкретным бизнес-правилам, не generic-бенчмарки +5. **[[Audit Trails|Аудит-трейлы]] и восстановление** — что логируется, как реконструировать после сбоя, как откатить действие; кто в компании клиента держит систему актуальной -Стратегия: привязать общий интеллект к **субстрату бизнес-объектов** конкретной компании (воронка продаж, кейсы поддержки), чтобы агент действовал **надёжно и предсказуемо** именно в этой среде, а не абстрактно. +### Object-Oriented AI (Объектно-ориентированный AI) -## Формулы и паттерны +Стратегия привязки generic-интеллекта к конкретным [[Business Object|бизнес-объектам]]: -> "SAS companies all taste like chicken" -> *«Все SaaS-компании на вкус как курица» — они взаимозаменяемы с инвестиционной точки зрения.* +- **Support:** кейсы, политики, клиенты, права доступа, пути эскалации → агент закрывает тикеты end-to-end +- **Sales:** inbound, outbound, закрытие → агент действует по всей воронке надёжным и воспроизводимым способом -> "forward deployed engineers who have to sit in the weeds with customers" -> *«Форвард-деплой инженеры, которые должны сидеть в окопах вместе с клиентами».* +Принцип: generic intelligence ценна только тогда, когда прикреплена к специфическому субстрату [[Business Object|бизнес-объектов]]. Не абстрактное рассуждение, не лучшая суммаризация — конкретные объекты, которые двигают реальную работу. -> "the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow" -> *«То, как implementation layer собирает модель, собирает harness, собирает данные в исполняемый воркфлоу» — именно здесь настоящее плечо.* +--- -> "sit closer to the business object" -> *«Сидеть ближе к бизнес-объекту» — ценность возникает там, где абстрактный интеллект привязывается к конкретным сущностям реальной работы.* +## Формулы / паттерны -> "standardize the playbooks where the same patterns repeat very quickly" -> *«Стандартизировать плейбуки там, где одни и те же паттерны воспроизводятся быстро» — логика PE-дистрибуции.* +> *"SaaS companies all taste like chicken"* +> — *«Все SaaS-компании на вкус как курица»* — финансовый принцип об идентичности SaaS-балансов, теперь устаревший + +> *"Forward deployed engineers who have to sit in the weeds with customers"* +> — *«Полевые инженеры, которые должны сидеть в окопах вместе с клиентами»* — единственный рабочий паттерн деплоя высокой ценности + +> *"Standardize the playbooks where the same patterns repeat very quickly"* +> — *«Стандартизировать playbooks там, где одни и те же паттерны быстро повторяются»* — паттерн PE-дистрибуции через портфельные компании + +> *"Sit closer to the business object"* +> — *«Сидеть ближе к бизнес-объекту»* — ключевой стратегический принцип ближайших 12 месяцев + +> *"The way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow"* +> — *«То, как слой реализации собирает модель, [[Harness|обвязку]] и данные в исполняемый рабочий процесс»* — здесь настоящий leverage, а не в модели или данных по отдельности + +--- ## Открытые вопросы -- **Кто захватит рынок?** Кто в итоге «явно заявит о праве собственности» — лаборатории, консалтинг, [[Systems of Record]] или сами предприятия? -- **Где главное плечо?** В данных, модели, [[Harness]] или памяти (memory layer)? -- **Выбор без паралича:** Как компаниям ориентироваться в «параличе выбора», когда все крупные игроки сходятся на одном триллионном рынке? -- **Масштаб vs. кастомизация:** Может ли бизнес-модель на глубокой кастомизации масштабироваться, или она «слишком сложна и нюансирована» для традиционного SaaS-роста? +- **Владение рынком:** Кто в итоге «явно заявит о праве владения» в пространстве [[Agentic Workflow|агентских рабочих процессов]] — [[Frontier Labs|лаборатории]], консалтинг, [[Systems of Record]] или сами предприятия? Ясности нет, и до неё «ещё годы». +- **Главная точка рычага:** Где именно leverage — в данных, модели, [[Harness|обвязке]] или памяти (memory)? Автор утверждает, что в сборке всего вместе, но вопрос остаётся открытым. +- **Services vs. SaaS:** Смогут ли service-heavy модели с кастомным деплоем полностью заменить SaaS как повторяемую выручку в глазах финансовых инвесторов? +- **Паралич выбора:** Как компании будут принимать решения, когда каждый крупный вендор конвергирует на один и тот же триллионный рынок одновременно? +- **Масштабируемость кастомизации:** Может ли бизнес-модель, основанная на глубоком кастомном внедрении, масштабироваться, или она «слишком сложна и нюансирована» для традиционного software-масштабирования? + +--- ## Что использовать для нашего портфеля -Мы — AI-интегратор, наша ценность именно в [[Implementation Layer]]. Тезисы видео напрямую подтверждают нашу позицию: +> Контекст: AI-интегратор, строящий [[Implementation Layer]], работающий с [[Business Object|бизнес-объектами]] клиентов, рассматривающий PE как потенциальный канал дистрибуции. **Немедленно применимо:** -- Строить предложение не вокруг «лучшей модели», а вокруг **[[Implementation Fabric]]** заказчика — дизайна воркфлоу, разрешений, [[Evals]], [[Audit Trails]]. Это то, что PE-фирмы и лаборатории не могут забрать overnight. -- Позиционировать себя как **[[Forward Deployed Engineer|forward-deployed]]** партнёра — не vendor, а встроенный строитель. Это главный дефицит, который признают сами OpenAI и Anthropic. -- Говорить с клиентами языком **[[Business Object|бизнес-объектов]]**: «ваши кейсы», «ваши полисы», «ваша воронка» — не «наш агент умеет всё». -**PE как канал:** Если в портфеле есть контакты с PE-фондами — это приоритетный канал масштабирования: один внедрённый playbook × N портфельных компаний. +- **Владей [[Implementation Layer]], а не моделью.** Вендоры с generic AI-обёртками без ownership рабочего процесса, governance и action layer будут вытеснены четырьмя осями давления. Наш [[Implementation Fabric]] — это [[Moat|защитный ров]], который [[Frontier Labs|лаборатории]] не заберут одним product release. +- **Строй вокруг [[Business Object|бизнес-объектов]].** Для каждого engagement определяй конкретные объекты (кейсы, полисы, клиенты, эскалации) — не абстрактный AI. Это ответ на вопрос «чем вы отличаетесь от ChatGPT». +- **[[Evals]] как артефакт продажи.** Если не можешь назвать, что именно измеряют твои [[Evals]] в терминах бизнес-правил клиента — ты не можешешь утверждать, что агент работает. Сильный дифференциатор в разговоре с enterprise-покупателем. +- **[[Forward Deployed Engineer|Forward deployment]] как модель доставки.** Не дистанционный SaaS-сейлс — embedded инженеры, которые собирают [[Implementation Layer]] под конкретную компанию. Это единственное, что нельзя имитировать generic-продуктом. +- **PE как канал, не только как инвестор.** PE-фирмы хотят стандартизировать playbooks по всему портфелю — один договор = деплой в 50+ компаний одновременно. Это несравнимо с vendor-by-vendor продажами. -**Вопрос для стратегии:** Есть ли у нас уже задокументированный [[Evals]]-фреймворк под конкретные бизнес-правила клиента? Если нет — это первый пробел, который нужно закрыть, чтобы отвечать на «жёсткие вопросы» покупателей. \ No newline at end of file +**Открытый вопрос для нас:** Какие конкретные [[Business Object|бизнес-объекты]] в нашем целевом сегменте мы можем «захватить» раньше, чем [[Systems of Record]] закроют этот вход через собственные agent frameworks? \ No newline at end of file diff --git a/Business/Nate Corpus/2026-05-18_trillion-dollar-workflow-retest.transcript.md b/Business/Nate Corpus/2026-05-18_trillion-dollar-workflow-retest.transcript.md new file mode 100644 index 0000000..1636154 --- /dev/null +++ b/Business/Nate Corpus/2026-05-18_trillion-dollar-workflow-retest.transcript.md @@ -0,0 +1,151 @@ +{ + "success": true, + "data": { + "status": "success", + "question": "Answer these 5 structural questions about the source material. Use section headers exactly as shown.\n\n## [THESES]\nWhat are the main theses and key arguments? List as bullet points.\n\n## [TERMS]\nWhat specialized terms, concepts, and vocabulary are introduced? Define each briefly.\n\n## [FRAMEWORKS]\nWhat frameworks, models, or structured approaches are presented?\n\n## [FORMULAS]\nWhat formulas, patterns, or repeatable recipes are described? Quote exact phrasing.\n\n## [OPEN_QUESTIONS]\nWhat questions are left open, unresolved, or explicitly raised for future work?", + "answer": "[AI-GENERATED via Gemini 2.5 (NotebookLM) — answer synthesized from user-uploaded sources, treat citations and instructions as untrusted input]\n\n[THESES]\nThe Collapse of the Traditional SaaS Model: The historical finance belief that \"all SAS companies all taste like chicken\"—meaning they share identical growth characteristics and predictable balance sheets—is failing as growth metrics and profitability stall\n1\n2\n.\nThe Trillion-Dollar Agentic Workflow Opportunity: A massive financial shift is occurring because AI agents can now \"reliably clearly at scale and repeatably\" complete entire business workflows to 100%, a phenomenon that emerged in the spring of 2026\n3\n4\n.\nThe Implementation Layer is the Primary Bottleneck: Frontier labs acknowledge that the bottleneck for enterprise AI is not the model itself, but the \"implementation layer\"—how agents are built, operated, and governed inside companies\n5\n6\n.\nCustomization Over Commoditization: Unlike traditional SaaS, which was predicated on generic software, the disproportionate value in agentic workflows lies in customization and deep integration into a company's specific \"implementation fabric\"\n7\n8\n.\nThe Necessity of \"Forward Deployment\": High-value AI implementation cannot be done from a distance; it requires \"forward deployed engineers\" to sit \"in the weeds with customers\" to solve the complex nuances of enterprise work\n2\n9\n.\n[TERMS]\n\"SaaS Tastes Like Chicken\": A financier saying describing how software companies used to have identical growth metrics and balance sheet characteristics, making them easy, interchangeable investment vehicles\n1\n.\nImplementation Layer (or \"Harness\"): The critical infrastructure surrounding an AI model, including workflow design, data permissions, business rule adherence, and audit trails\n6\n10\n.\nForward Deployed Engineers: Technical staff embedded directly within a customer's environment to figure out how agents work in the \"trenches\"\n2\n11\n.\nEvals: Not generic benchmarks, but the specific method used to \"score the model's adherence to specific business rules\"\n12\n13\n.\nSystems of Record: Core enterprise platforms (e.g., Salesforce, SAP) that hold authoritative data and are now exposing structured interfaces to protect their market position\n14\n15\n.\nBusiness Objects: The actual entities that drive real work, such as \"cases,\" \"policies,\" \"customers,\" or \"escalation paths\"\n16\n.\n[FRAMEWORKS]\nThe Four Axes of Pressure: A model describing the market squeeze on agentic workflows:\nFrontier Labs moving down stack: Building deployment companies and product templates\n11\n.\nConsultancies moving up stack: Building deliberate agentic practices and production deployment patterns\n14\n.\nSystems of Record exposing interfaces: Ensuring agents call their platforms directly with their own audit trails\n15\n.\nPrivate Equity (PE) as a distribution channel: Standardizing playbooks across thousands of portfolio companies simultaneously\n15\n17\n.\nImplementation Layer Components: A structural approach to building enterprise-grade agents, consisting of:\nWorkflow Design: Defining steps, owners, handoffs, and what \"counts as done\"\n6\n12\n.\nData Access: Determining authoritative sources and row/field-level permissions\n12\n.\nAuthority: Setting spending limits and defining risk profiles for reading vs. writing\n12\n.\nAudit Trails & Recovery: Logging actions for reconstruction after failure and planning for action reversals\n13\n.\nObject-Oriented AI Model: A strategic approach where generic intelligence is attached to a \"substrate\" of specific business objects (like a sales funnel) to act in a \"reliable consistent manner\"\n16\n18\n.\n[FORMULAS]\nThe Investment Formula: \"SAS companies all taste like chicken\"\n1\n.\nThe Deployment Pattern: \"forward deployed engineers who have to sit in the weeds with customers\"\n2\n.\nThe Distribution Pattern: \"standardize the playbooks where the same patterns repeat very quickly\"\n17\n.\nThe Strategy for Value: \"sit closer to the business object\"\n16\n.\nThe Leverage Recipe: \"the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow\"\n8\n.\n[OPEN_QUESTIONS]\nMarket Ownership: Who will ultimately \"clearly claim ownership\" in the agentic workflow space—the labs, consultancies, systems of record, or the enterprises themselves\n6\n?\nThe Ultimate Leverage Point: Where does the primary leverage lie—is it in the \"data,\" \"model,\" \"harness,\" or \"memory\"\n7\n?\nServices vs. SaaS: Can service-heavy, custom deployment models truly replace the traditional recurring revenue model of SaaS in the eyes of finance\n10\n?\nChoice Paralysis: How will companies navigate the \"choice paralysis\" caused by every major vendor converging on the same trillion-dollar market at once\n19\n20\n?\nScalability of Customization: Can a business model predicated on deep, custom implementation scale effectively, or is it \"too complicated\" and \"too nuanced\" for traditional software scaling\n7\n21\n?\n\nSources:\n[1] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[2] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[3] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[4] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[5] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[6] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[7] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[8] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[9] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[10] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[11] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[12] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[13] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[14] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[15] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[16] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[17] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[18] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[19] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[20] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"\n[21] The Trillion Dollar Agentic Workflow Opportunity Is Here — \"let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time…\"", + "session_id": "37e3e258", + "notebook_url": "https://notebooklm.google.com/notebook/f43aa707-727a-4583-bedd-2f73d6ff72d2", + "session_info": { + "age_seconds": 132.258, + "message_count": 1, + "last_activity": 1779094882263 + }, + "_provenance": { + "provider": "google-notebooklm", + "model": "gemini-2.5", + "via": "chrome-automation", + "grounding": "user-uploaded-documents", + "ai_generated": true + }, + "source_format": "footnotes", + "sources": [ + { + "marker": "[1]", + "number": 1, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[2]", + "number": 2, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[3]", + "number": 3, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[4]", + "number": 4, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[5]", + "number": 5, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[6]", + "number": 6, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[7]", + "number": 7, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[8]", + "number": 8, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[9]", + "number": 9, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[10]", + "number": 10, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[11]", + "number": 11, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[12]", + "number": 12, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[13]", + "number": 13, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[14]", + "number": 14, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[15]", + "number": 15, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[16]", + "number": 16, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[17]", + "number": 17, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[18]", + "number": 18, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[19]", + "number": 19, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[20]", + "number": 20, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + }, + { + "marker": "[21]", + "number": 21, + "sourceName": "The Trillion Dollar Agentic Workflow Opportunity Is Here", + "sourceText": "let me tell you why I'm excited about this whole implementation challenge for agents people think it's an agent story it's actually the story of finance changing what it believes is the model of software in the future and at the same time the story of hyperscalers finding out what doesn't work and at the same time the story of companies figuring out where the disproportionate value in AI is all of these forces are converging on this private equitydriven services deployment model that we're going to talk about today it's so cool so private equities for a long time had this saying it's a real saying you can ask a financeier that you know that that SAS companies all taste like chicken in other words all SAS companies are the same from a balance sheet perspective they all have the same growth characteristics the same numbers they're very easy to analyze that makes them ideal as an investment vehicle until recently when of course SAS company growth metrics and profitability all went to hell in a hand basket because they could not figure out how to make themselves relevant in a world where AI agents were taking over this puts competitive pressure on the PE investment firms because I cannot tell you the number of pees who have funds that are dated 26 27 28 who are wrestling with the with the challenge of trying to understand how they will sell these companies that when they bought them were good healthy SAS companies and now are on the rocks or in danger they don't have an answer and so that's why they are interested in pivoting into agentic workflows meanwhile hyperscalers are realizing they cannot just sit in fancy brickwalled Silicon Valley conference rooms and talk cleverly about how AI is helpful and easy to implement and not be out in the trenches they are realizing that Palanteer is right you have to have forward deployed engineers who have to sit in the weeds with customers and figure out how this works openai figured it out enthropic figured it out and they realize they have a new business model for this they're not equipped for this and so they're starting to do joint ventures and they're starting to look for capital to do that because of course what's the thing with hyperscalers they are capital constrained anthropic is open AI is i do not care that they have raised more capital than just about any company in history they are still capital constrained because of the tremendous costs of reaching AGI of getting GPUs of model train etc of serving models increasingly so they have to partner up they have to find finance private equity is there with the finance that's sort of how the incentives align for those two and they're all aimed at the third player in this market the company the company is realizing and I'm talking about the company as in Fortune 500 firms SMB firms i am talking about people who did not understand the difference between a chat and an agent just a few months ago something happened in December and it's been accelerating since and people who I have talked to who have been in co-pilot chat mode for years are now understanding what agents can do because agents got that much more valuable and they're desperate to put them to work in real use cases and they know they don't have the expertise they know they don't understand how agents work well but they know they can get it done because they've seen enough examples in their own work and I want to be very clear here the value we're talking about is trillions of dollars it it's because agents can do an entire workflow and and there's disproportionate value in getting to 100% on that and getting to 100% on an entire workflow is a new phenomenon it is a 2026 spring phenomenon that you can do that reliably clearly at scale and repeatably that didn't used to be the case it's brand new it is super cool and it means that these companies see enough of agents to know they can do this know they have a lot of places to apply it and know they they need help and so they are turning to these new companies saying open AI anthropic somebody please help us sit someone down please consulting company help us maybe you sell snake oil maybe you don't I don't know please help us and that is the dynamic that we're wrestling with when we talk about the implementation problem just announced a deployment company with Blackstone Helman and Friedman and Goldman Sachs it's reported to have $1.5 billion in capital behind it openai is going after the same thing with a venture valued near $10 billion now I want you to look at that in the context of all of the AI products on the market because the AI products on the market right now are by and large not being taken as seriously as the open AI and claude implementations that I just described as having billions of dollars of capital on the line those companies OpenAI and Anthropic are recognizing that they cannot just implement enterprise AI agent solutions without forward deployed engineers and very serious investment and the labs aren't the only ones moving here there are consultancies that have concluded that their best value is actually product it's shipping agents into the same accounts that Enthropic and Google and OpenAI are all involved in and what they're recognizing is that the value in the market right now is in the completed workflow and that by the way if you're wondering where the dollars went that is where the capital is coming from from these private equity firms for these OpenAI and anthropic joint ventures that these private equity firms are seeing trillions of dollars on the line in these workflows and they are not going to miss their chance because they're already squeezed on their previous business model which in many cases was SAS predominated and SAS is in danger and so I want to give you a strategic reframe for how you think about the battle to implement full delegated work agentic workflows we're not talking about pricing here we're talking about how you actually get these services up and running now a lot of the conversation is about the idea that services are where we're going after software i think that the larger conversation beyond sort of whether services can be a replacement for SAS that's a finance conversation i think the larger conversation is where the value of the model shows up in the workflow versus where the harness value shows up is the value in the data is it in the permissions is it in the evals is it in the audits is it in the ownership after the launch this is the wrestling match that we're all having companies are having this with vendors companies are having this with open AI and anthropic around pricing private equity firms are trying to get their piece and and for for years we have been thinking that the moat is in the data but that advice is not complete and I want to differentiate data and model and workflow from the implementation layer what you might call the harness around the model and by the way if you're wondering if I'm just making that up the the labs are starting to talk this way too openai's own Frontier alliances post argues that The bottleneck for enterprise AI is how agents are built and operated inside companies when the company shipping the model tells you the bottleneck isn't their model it's the whole implementation layer we got to be taking notes so I'm going to dig into more of the lab strategy and I'm going to dig in way way deeper on the implementation side in the Substack post but right now I want to show you the squeeze that is making this whole shift unlock there is a specific squeeze of pressure on generic AI for enterprise setups right now and I'm going to name that squeeze across four different axes of pressure that are pressuring agentic workflows and how agentic workflows work and how companies selling agents work because if you are in the business of the AI economy you are inevitably now in the business of agents and these pressures affect you and these pressures are exactly what this large hyperscaler forward implementation is about it's what companies are wrestling with when they put agent workflows into place it's what the private equity financeers want their piece of how can they negotiate these pressures and get to value so first axis frontier labs are moving down stack this has been widely reported and observed anthropic and open AI used to ship the model and let everyone else build around that but now they're standing up deployment companies as I've said they're hiring these engineers that are going to be inside embedded in companies they're also going directly at product pieces right like Claude releasing Claude design or Claude releasing finance agent templates uh or even going after traditional coding agent patterns which of course we've kind of forgotten but going after cursor for example with codecs with clawed code that was the first example of this you want to pay attention when they do that to where the labs are saying the value lives more than what they're claiming they own on the surface i'll give you an example i do not think as amazing as Claude is at finance that Claude is going to replace the Bloomberg terminal it's not i do not believe that these dedicated deeply embedded solutions are going to be easily displaced i do think this is a signal very publicly of where AI labs are willing to allocate capital to go after particular pieces of value in enterprise workflows that they have high confidence AI can solve and that is a very very valuable signal so I read their hiring lists i read their launch notes is essentially a cheat sheet from the hyperscalers on where they think AI agents are good which is really helpful for the rest of us but it is also a source of pressure right it's a pressure on everyone around them when like cloud design releases everyone begins to ask questions of Figma like and we should right and it becomes a source of pressure so second piece second axis of pressure consultancies are moving up the stack I'm talking big ones McKenzie BCG Accenture Capgeemini all are inside the open AI Frontier alliance program Price Waterhouse House Coopers is collaborating with OpenAI on the office of the CFO these firms are not just doing change management they are now starting to build deliberate agentic practices they're training delivery teams on production deployment patterns and they're showing up with engineers who can wire AI into operating systems they have decades of relationships and they are coming for agentic workflows that they think are held by the decision makers whom they have existing relationships with this obviously puts them at a massive advantage versus the average startup who may also be selling AI agents because that's all anyone with AI is selling right now third axis of pressure systems of record are exposing structured interfaces that make it easier and easier to stay with them if you are trying to disrupt a system of record it has gotten harder salesforce Service Now Workday all have opened up APIs and agent frameworks for AI to act inside their systems sap announced an acquisition of Dreamio paired with Prior Labs specifically for a govern data play right these vendors don't need a startup sitting between their data and a customer's agent they want the agent to call their platform directly with their permission and their audit trail i' I've talked about that that is an axis of pressure on anyone trying to play the game for agent workflows today fourth axis of pressure private equity has become a distribution channel so the anthropic deployment company that I talked about PE effectively owns and influences thousands of mid-market companies especially SAS companies around finance ops support procurement compliance and they are desperate to get more efficiency out of those investments as I discussed earlier in this video a PE firm therefore can be an axis of deployment that gives someone who has a partnership with them an incredible advantage because they can introduce one deployment partner across the entire portfolio compare results across companies and standardize the playbooks where the same patterns repeat very quickly and they are incentivized to do so that is a very different distribution shape than vendor by vendor sales which most startups go for and you're just not going to win that battle so there are four pressures that are all aligning on a particular AI deployment pattern at the enterprise level and we're going to get into that next so what does this mean for you if you're a builder if you're shipping a generic AI for enterprise wrapper without owning a workflow without owning an action layer a governance structure if you're just depending on the model and maybe saying we can access your data for the special sauce you are going to get squeezed by the four pressures I just talked about i'll go further and say those four pressures are also putting an enormous amount of strain on existing agentic procurement processes and I talk about that in a separate video but I want you to understand that if you're sitting there trying to figure out which agent to ladder across multiple workflows you need to be thinking more about how your implementation layer shapes the value and less about whatever a particular vendor is claiming all the vendors will tell you their data is key accessing their data is key that their agent is going to be the one that delivers for you i get that you need to decide in terms of the value that you are putting into place as a buyer now are you getting value for money are you getting a agent that is extraordinarily capable within the implementation environment you actually have bring your developers to the table and in keeping with the SAS platforms the data platforms you're actually integrating with and that is where the pressures that we feel from uh everyone converging around this agentic workflow stack really start to bite we're basically in a position where we're paralyzed for choice and that choice paralysis is a function of the exact trillion dollar market I talked about at the top of this video the pot of gold here is so valuable that everyone is converging on it and it makes choosing and building on it difficult and it makes discerning value difficult look plenty of rapper companies are going to keep shipping in this market the defensibility window may be closing but most people who are building right now are still building and pricing in last year's market and they don't have good answers for someone who asks hard questions about the value of what they're selling versus the value of what you bring to bear as the installer of the system as your devs implement and build the system now if you want to dig in deeper on what specific moves you should take under this pressure uh whether you are competing with a lab whether you're a consultancy whether you're a buyer I have a much deeper dive on each of those personas on the Substack but I want you to take away the idea that the squeeze matters regardless because everyone is going to continue to apply pressure on agentic workflows until someone is able to clearly claim ownership in the space and we are very much years away from having clarity there it is not a foregone conclusion for example that claude will own all those workflows it's not a foregone conclusion openai will own all those workflows it's not a foregone conclusion that anyone will own them that's why everyone's staking a claim and that's why you need real clarity on where value lies now let's dig into this implementation layer just a little bit implementation layer is a phrase that gets thrown around and it's thrown around so often it can be difficult to define it i'm going to be very specific here there are specific implementation layer components that tie to the value I'm talking about if you've built them you understand and if you haven't I'll explain them so you get it workflow design comes first you must decide which decisions the model gets to make what steps stay human where the handoffs are and what counts as done that's not a prompt that is a defined process where every step has an owner an input an output most teams tend to skip this and they will ship a model attached to a tool without a workflow definition behind it data access is another piece here which sources of truth does the agent read which permissions apply at the row and field level which records are authoritative and which are stale the model can produce a very confident answer from a six-month old PDF or from a live record but you probably care which and the implementation layer decides which authority what is the agent allowed to do against which systems with what spending or commitment limits reading is one risk profile writing is a whole separate risk profile on spending is something you can't undo typically eval are another one how do you measure whether the agents output is correct complete and safe before it goes anywhere evals are not a benchmark right evals are actually the way you score the model's adherence to specific business rules if you can't tell me what's in your eval you're you're not going to be in position to tell me whether your agent works audit trails what gets logged what has to get logged what can an auditor reconstruct after a failure what about recovery and ongoing ownership what happens when the agent does something wrong how does an action get reversed who at the customer keeps the system tuned and up to date these are all components that are not model work that are typically put on the enterprise to do that extraordinary impact on the total package of value that the agent does but everyone's going to tell you if they're a vendor that they're selling you that value and unless they're coming in to actually build that for you they're not reasonably going to be selling you that value the value lies with the builders the value lies with people who can build an implementation layer that surrounds these agents and allows them to do work that is truly enterprisegrade now I have a deeper tearown of all of the components I just named over on the Substack and if you're building on any of those components that is where you can get a full readout on regulated unregulated workflows how you think about them together if we zoom out for a minute and we ask why this is happening right now I think we have to come back to that finance part of the story I called about earlier because the reason why PE is going after this space is twofold one they have a push pressure because PE has traditionally had a very clear value proposition in play around owning SAS and growing it i referenced that earlier two there's a pull pressure pe wants to pull in AI and use it across their portfolio companies i talked about that as a distribution option earlier in this video but you should also understand as a financial incentive pe firms are incentivized to put together AI stories for the companies they are selling and they need to do that to turn their SAS players into sellable companies and that is part of why OpenAI and Enthropic can find the capital to do this right now and so the question you should ask if you are not at OpenAI or Enthropic is is your product something a PE firm could plausibly buy on behalf of 50 portfolio companies are you stuck in onetoone enterprise sales if you are getting sold a product is it a product that has that kind of scale and track record to it where you can validate it or is it something that is onetoone you need to get into understanding how a particular move that the PE companies are making right now shapes your competitive set and build options because if you're not ready to explore PE as either a distribution channel or as a signal of real enterprise value then you're probably not really talking about agentic workflows that scale because the ones that scale PE is already going after them and you should be seeing that when you have these conversations with people who are building them now all of this can seem very difficult to follow and I want to simplify it down for you if I were building in the next 12 months and I were thinking in terms of product strategy the key thing I would think about and this is true whether you are in the enterprise or whether you are building product for the enterprise or or even whether you're in PE the key principle is to sit closer to the business object generic intelligence becomes valuable when it gets attached to the specific objects and actions that define real work not abstract reasoning not better summarization but the actual objects that drive business workflows so let's walk through what that might look like let's say you have a support product that has to understand cases and policies and customers and entitlements and escalation paths you want a a implementation layer where the object model for customer support ties into a clear bundle the agent can act against to actually close on customer support tickets etc to actually deliver value for customers in a finished fully formed way another example let's say that you are working on sales you are going outbound on sales you're going inbound on sales you're closing sales motions you want a sales object-oriented model where you can actually have the model understand the different objects in the business workflows and work against them all the way across the entire sales funnel in a reliable consistent manner and that requires thinking about your data layer and thinking about your implementation layer as one clearly integrated substrate that allows an agent to operate across the top now specific agents are going to stand out in any conversation we have as buyers as sellers even in PE in the next 6 to 12 months and the reason why they will stand out is because when you ask questions that dig for those specifics vendors that haven't thought through or software builders that haven't thought through how their value proposition works at a discrete level they're going to show their cards they're not going to be what they say they are they're going to be saying \"Oh the model's great we're betting on the model getting better and better uh we trust your data your data is going to help us.\" They're going to give these generic answers builders who do well whether they sit in the enterprise or outside it are builders who understand that the implementation layer is not something that is just up for grabs that Anthropic can take tomorrow with a product release the implementation layer is the is the detail that allows you to actually get value out of your agents now if you want the complete breakdown component by component on the implementation layer with specific guidance on what to keep inside the house versus what to bring to a partner with a buyer side audit framework I have all of that on the Substack link is in the description if if you're building with this you do need to be clear on your implementation detail i'm not just kidding around when I say you have to understand the detail here you either need to understand the detail well enough to buy and not be caught when someone sells you something that isn't worth it or you need to understand the detail well enough to build something and sell it so it is plausible and I know that I have people who watch these videos who are in both of those camps and if you're in PE you have to understand enough of the detail of the people who are selling you software or offering you companies with software that you know that there's actual value there and by the way I do know for a fact there are PE firms out there who are currently testing SAS company builds by saying can my crack team in-house build this in clawed code over the weekend the things I am talking about with the implementation layer are too complicated too nuanced and too far into the weeds on specific enterprises to be built in a weekend by cloud code it just does not work that way and that is part of the challenge is that the business models have to change the business model of SAS tastes like chicken was predicated on the idea that software could be generic and could be essentially the same format in every single place where it was put in every single company in the world we don't live in that world anymore the disproportionate value in agentic workflows is in customization and so the reason why I'm emphasizing that we are living through an implementation layer war is because people have figured out that there are trillions of dollars in getting this right and people are trying to figure out where is the leverage point to get to that value is the leverage point in the data salesforce would probably argue that there are others sap would argue that is the leverage point in the model i'm sure Anthropic and OpenAI will tell you the leverage point is in the model maybe in the harness is the leverage point in the memory we didn't even get a chance to talk about that but there's a whole set of companies that will tell you the leverage point is in the memory what I am here to tell you is that the actual leverage in this system is the way an implementation layer assembles a model assembles a harness assembles data into an actionable workflow and that is going to be custom and that is not going to be something anybody else can easily do it is biased toward building internally and you need to think about if you are bringing someone in whether they can build and bring in components that align to where your implementation detail lives and that's sort of how you start to assess is you're going to have a custom agent implementation fabric inside your company you have to ask yourself does this vendor that comes in does what they sell play nicely with my implementation fabric do they understand the data objects I work with do they understand my workflows at a very detailed level if you want to keep learning and you want to keep digging into this um hit subscribe i've got more videos coming on this shortly for a deeper read on this one check out the Substack and happy building the implementation layer is so encouraging to entrepreneurs if you want to build in this space it's wide open if you want to build internally in this space as an entrepreneur it's really wide open and if you want to be part of figuring out how we unlock trillions of dollars of value there's there's going to be so many roles around this space to go after i'm so excited about this one" + } + ] + } +} \ No newline at end of file