AI Strategy - Tygart Media

Tygart Media

Category: AI Strategy

  • OpenAI’s Everything App: Why Behavior Is a Better Moat Than Infrastructure

    OpenAI’s Everything App: Why Behavior Is a Better Moat Than Infrastructure

    Microsoft has LinkedIn and enterprise distribution. Google has the native stack. Notion has the database architecture. OpenAI has something none of them have: 500 million people who already open ChatGPT when they want to get something done. That’s not a product advantage. That’s a behavior advantage. And behavior is the hardest moat to breach.

    Where OpenAI Sits in This Series This is the fifth piece examining who builds the everything app. We’ve covered Microsoft, Google, Notion, and the everything database frame. OpenAI’s path is the most unusual: they’re not building from infrastructure up. They’re building from user behavior down.

    The Model Reality First — Get This Right

    Before the strategy discussion, the model facts — because the landscape shifted significantly in early 2026 and the marketing doesn’t always match what’s actually deployed.

    As of mid-2026, OpenAI’s current flagship is GPT-5.5, which powers ChatGPT Enterprise (unlimited messages) and is the reasoning backbone of the unified super-assistant experience. The o-series — o3 and o4-mini — are the thinking models, trained to reason longer before responding. o3 is the deep-reasoning flagship; o4-mini is the high-throughput option that outperforms o3-mini on non-STEM tasks and data science, with higher usage limits.

    Notably, GPT-4o, GPT-4.1, and GPT-4.1 mini were retired from ChatGPT as of February 13, 2026. Enterprise customers retained GPT-4o access until April 3, 2026. If you’re referencing these models in your stack — in tutorials, in documentation, in integrations — those references are now stale. The current tier is GPT-5.5 Instant / Thinking and the o3/o4-mini reasoning models.

    One more significant infrastructure move: the Assistants API is being deprecated, with sunset on August 26, 2026. OpenAI is replacing it with the Responses API — a new primitive that combines Chat Completions simplicity with Assistants-style tool use, supporting web search, file search, and computer use natively. If you built on the Assistants API, migration planning should already be underway.

    OpenAI’s Everything App Bet: Behavior Over Infrastructure

    Microsoft’s everything app bet is infrastructure — they own the OS, the enterprise software stack, and a professional network. Google’s bet is native stack — they own search, email, calendar, and mobile. Both are building from the platform up.

    OpenAI is doing the opposite. They’re starting from where people already go to get things done, and expanding outward from that behavioral beachhead. ChatGPT’s 500 million monthly users don’t use it because it owns their email. They use it because it’s the fastest path from question to answer, from idea to draft, from problem to solution.

    The everything app doesn’t have to own your data. It just has to be the place you go first. OpenAI is betting that if they can make ChatGPT good enough at enough things — and fast enough at integrating with the tools you already use — the behavioral habit becomes the moat. You stop going to Google first. You stop opening a new app. You open ChatGPT.

    The Pieces OpenAI Has Assembled

    The consolidation has been quieter than Microsoft’s marketing machine or Google’s Cloud Next announcements, but the pieces are substantial.

    Operator — the computer-using agent — launched as a research preview in early 2025 and integrated fully into ChatGPT by mid-year. It browses, clicks, fills forms, and manages logins autonomously. GPT-5.5’s score on OSWorld-Verified — the standard benchmark for computer-use agents — is 78.7%. The human baseline on the same benchmark is 72.4%. That’s not a lab result. That’s production-grade desktop and browser automation beating human performance on standardized tasks.

    Projects and Memory — launched through 2025 — give ChatGPT persistent context across sessions. Projects (November 2025) let you organize work by context. Project Memory (August 2025) lets ChatGPT learn your preferences, communication style, and working patterns over time. This is the foundational layer for the everything app: an AI that knows you, not just your current prompt.

    Workspace Agents for Enterprise — launched April 22, 2026 — let enterprise teams create, share, and manage AI agents for workflow automation. Powered by Codex, these agents handle reporting, coding, and messaging tasks autonomously. This is OpenAI’s direct enterprise play, competing with Microsoft’s Agent 365 and Google’s Workspace Studio on their home turf.

    Sora 2 — released September 2025 — moved AI video from novelty to production-grade. It’s available both as a standalone app and deeply integrated within ChatGPT. Video generation, image creation, voice, code execution, deep research, file analysis — all inside one interface. The surface area of what ChatGPT can do has expanded faster than most people have tracked.

    The Apps SDK and MCP support — announced in 2025 — let developers build UIs alongside MCP servers, defining both logic and interactive interface of applications that run inside ChatGPT. OpenAI is building a developer ecosystem where third-party tools surface inside ChatGPT natively, not as links out to other apps.

    The Honest Strategic Weakness: OpenAI Doesn’t Own the Data Layer

    Here’s the structural problem with OpenAI’s everything-app path that doesn’t get enough attention.

    Microsoft owns the calendar data, the email data, the document data, the professional network data. Google owns the same stack natively. Notion owns the database architecture where your operational data lives. OpenAI owns a conversation history and whatever files you’ve uploaded to Projects.

    That’s a meaningful gap. When you ask Microsoft Copilot “what happened in last week’s client meeting?” it can actually answer — because it has the calendar event, the Teams recording transcript, and the follow-up email thread. When you ask ChatGPT the same question, the answer is only as good as what you’ve explicitly provided.

    OpenAI’s answer to this is Operator and the connector ecosystem — let ChatGPT reach into your existing tools and pull the data it needs. That works, but it creates a dependency chain that Microsoft and Google don’t have. Every integration is a point of failure. Every API change is a breakage risk. Every permission prompt is friction that erodes the behavioral habit.

    The Responses API — replacing the Assistants API in August 2026 — is designed to close some of this gap with native web search, file search, and computer use built in. But native search is not the same as owning the inbox. And computer use, for all its benchmark performance, is still slower and less reliable than a dedicated integration.

    Where OpenAI Wins: The Consumer and Creator Layer

    The enterprise everything-app race may go to Microsoft or Google by default — too much infrastructure, too many IT relationships, too much compliance architecture for a newcomer to overcome in 18 months.

    But the consumer and creator layer is wide open. And that’s where OpenAI’s behavioral moat matters most.

    For freelancers, solopreneurs, content creators, small agencies, and knowledge workers who aren’t tied to an enterprise IT environment, ChatGPT is already the everything app. It drafts your emails, edits your copy, analyzes your data, generates your images, browses for research, and runs your automations. The question isn’t whether they’ll adopt it — they already have. The question is whether OpenAI deepens that relationship fast enough to make switching costly before Microsoft and Google catch up on the consumer side.

    Memory is the weapon here. The longer a user runs their work through ChatGPT Projects with memory enabled, the more context OpenAI accumulates about how that person thinks, works, and communicates. That context is genuinely hard to transfer to a competing platform. It’s not data in a database — it’s learned behavioral preference. The switching cost compounds with every session.

    The Operator Economy: OpenAI’s Wildcard

    The most underrated piece of OpenAI’s everything-app strategy isn’t ChatGPT itself — it’s the operator ecosystem.

    An “operator” in OpenAI’s framework is any business that deploys ChatGPT capabilities inside their own product. Every company building on the OpenAI API — embedding ChatGPT into their CRM, their help desk, their e-commerce platform, their internal tools — is an operator. Every one of those deployments is a surface where OpenAI’s models become the intelligence layer of someone else’s everything app.

    Microsoft has Copilot. Google has Gemini. But neither of them has the sheer number of third-party applications already running on their models that OpenAI has accumulated. The operator ecosystem means OpenAI doesn’t have to build every surface themselves. They just have to remain the model that operators trust most — and as long as GPT-5.5 and the o-series stay at the frontier of capability, that trust is relatively durable.

    The Workspace Agents launch, combined with the Apps SDK and MCP support, is OpenAI formalizing this operator model for enterprise. They’re saying: we won’t replace your enterprise software stack. We’ll become the reasoning layer that sits across all of it.

    What This Means for Your Stack Right Now

    If you’re building on OpenAI’s API or running workflows through ChatGPT, three immediate action items:

    • Audit your Assistants API usage now. August 26, 2026 sunset is closer than it looks. The Responses API migration path is documented — start the evaluation before you’re forced into a rushed migration.
    • Enable Projects and Memory for your team’s ChatGPT accounts. The compounding advantage of memory only builds if you start using it. Teams that have six months of Project memory by Q4 2026 will have a materially different AI experience than teams starting fresh.
    • Think about where ChatGPT sits relative to your Notion database. OpenAI’s operator model and MCP support mean ChatGPT can connect to your Notion everything database via the Notion Public API. The everything database frame doesn’t require you to choose between Notion and ChatGPT — it lets you use both, with Notion as the structured data layer and ChatGPT as the reasoning and action surface on top of it.

    The everything app race isn’t over. OpenAI has the behavior moat, the operator ecosystem, and the fastest-moving model roadmap of any company in this field. What they don’t have is the data infrastructure that Microsoft and Google own by default. How they close that gap — through connectors, through Operator’s computer-use capabilities, through the Responses API — will determine whether ChatGPT becomes the everything app or the everything layer sitting on top of someone else’s everything app.

    Both outcomes are valuable. Only one of them wins the race.

    Frequently Asked Questions

    What is OpenAI’s current flagship model in 2026?

    As of mid-2026, GPT-5.5 is OpenAI’s primary model powering ChatGPT Enterprise. The o3 and o4-mini models handle deep reasoning tasks. GPT-4o, GPT-4.1, and GPT-4.1 mini were retired from ChatGPT on February 13, 2026. The Assistants API sunsets August 26, 2026, being replaced by the Responses API.

    What is the OpenAI Responses API?

    The Responses API is OpenAI’s replacement for the Assistants API (sunset August 26, 2026). It combines Chat Completions simplicity with Assistants-style tool use, supporting built-in web search, file search, and computer use. It’s the new primitive for building agents on OpenAI’s platform.

    What are OpenAI Workspace Agents?

    Launched April 22, 2026, Workspace Agents let enterprise teams create, share, and manage AI agents for workflow automation inside ChatGPT. Powered by Codex, they handle reporting, coding, and messaging tasks autonomously — OpenAI’s direct enterprise play against Microsoft Agent 365 and Google Workspace Studio.

    How does ChatGPT Operator work?

    Operator is OpenAI’s computer-using agent — it browses, clicks, fills forms, and manages logins autonomously. GPT-5.5 scores 78.7% on the OSWorld-Verified benchmark for computer-use tasks, above the 72.4% human baseline. It’s integrated directly into the ChatGPT interface for eligible plans.

    Can ChatGPT connect to a Notion database?

    Yes. Via the Notion Public API and OpenAI’s MCP support and connector ecosystem, ChatGPT can read from and interact with Notion databases. This makes the “everything database” architecture viable with OpenAI as the reasoning surface — Notion holds the structured data, ChatGPT reasons and acts on it.

  • Notion Isn’t the Everything App. It’s the Everything Database — and That’s a Better Bet.

    Notion Isn’t the Everything App. It’s the Everything Database — and That’s a Better Bet.

    Last refreshed: May 15, 2026

    Update — May 15, 2026: On May 13, 2026, Notion shipped the Notion Developer Platform (version 3.5), with Claude as a launch partner. The platform adds Workers, database sync, an External Agents API, and a Notion CLI. For the full breakdown of what changed and what it means for the Notion + Claude stack, see Notion Developer Platform Launch (May 13, 2026). For the underlying operating philosophy, see The Three-Legged Stack: Notion + Claude + Google Cloud.

    Everyone is building the everything app. Microsoft wants to be yours. Google wants to be yours. Notion wants to be yours. But there’s a fourth path nobody is talking about — and it might be the smartest play for brands, agencies, and multi-system operators: don’t pick one everything app. Build one everything database, and let it feed all of them.

    The Core Idea Notion isn’t competing to be your everything app. It’s competing to be your everything database — the structured, queryable, agent-ready source of truth that sits underneath whatever surface you use. The everything app becomes interchangeable. The database is the moat.

    The Series So Far — and Why This Frame Changes Everything

    This is the fourth piece in a series examining who wins the everything-app race. We looked at Microsoft stitching together an everything app through acquisitions, Google trying to unify a native stack it keeps fragmenting, and Notion building from the database up. Each piece treated the everything app as the destination.

    But there’s a reframe worth making. What if the everything app isn’t the destination? What if the destination is the data layer underneath it — and the everything app is just whichever surface happens to be most useful at a given moment?

    That’s the angle that emerged from actually building inside Notion Workers alpha. And it changes the strategic calculus significantly for anyone running a brand, an agency, or a multi-system operation.

    Your Brand Doesn’t Need One Everything App. It Needs One Everything Database.

    Think about what an everything app actually requires to work. It needs to know your tasks. Your projects. Your contacts. Your content calendar. Your pipeline. Your team’s status. Your historical decisions. Your brand voice. Your client relationships. Your automation outputs.

    That’s not an app problem. That’s a data structure problem. And the company that solves the data structure problem — that gives you a clean, typed, queryable, agent-ready home for all of that — wins, regardless of which surface you use to view it.

    Notion’s database architecture is purpose-built for exactly this. Every property is typed. Every row is queryable. Every database can be filtered, sorted, related, and rolled up. When you build your brand’s operational data inside Notion — tasks with statuses, projects with owners, content with metadata, contacts with relationship history — you’re not just organizing. You’re building a structured intelligence layer that agents can read, write, and reason over reliably.

    That database doesn’t care which “everything app” sits on top of it. Microsoft Copilot can query it. Google Workspace agents can sync from it. Your own custom dashboard can read it via the Public API. Claude can operate on it directly. The surface is interchangeable. The database is the thing that compounds in value over time.

    The 30-Second Trigger: Where the Architecture Gets Interesting

    Here’s the piece that came out of our own Workers alpha experience — and it reframes the “30-second sandbox limitation” from a constraint into a feature.

    Notion Workers runs in a 30-second execution window. We hit that wall hard when we tried to move heavy automations — multi-site WordPress optimization passes, content pipelines, image generation — into Workers. Those are multi-minute jobs. They don’t fit.

    But 30 seconds is more than enough to do one specific thing: fire a signed HTTP POST to an external endpoint and return.

    That’s the architectural insight. You don’t use Notion Workers to execute heavy work. You use Notion Workers to trigger it. The Worker wakes up — on a schedule, on a database change, on a webhook — reads the relevant Notion database row, constructs a signed payload, fires a POST to a Google Cloud Run job, and exits. The whole thing takes under five seconds. Well within the 30-second window.

    Cloud Run picks up the job, runs for as long as it needs — minutes, not seconds — and when it’s done, it writes the results back to the Notion database via the Public API. The Notion database is now the job queue, the status tracker, the results store, and the orchestration log. All in one place. All queryable by agents.

    The pattern in practice:

    Notion Worker (cron / DB change / webhook)
      → reads Notion database row for job config
      → signs POST to Cloud Run endpoint
      → returns immediately (3–8 seconds, well under 30s)

    Cloud Run (no time limit)
      → runs heavy job (WP optimization, pipeline, image gen)
      → writes status + results back to Notion DB via Public API

    Notion Database
      → job queue / status tracker / results store / audit log
      → queryable by agents, visible to team, triggerable again

    This is the hybrid architecture we’re running. Our Tuesday 18-site WordPress SEO optimization pass runs on Cloud Run — not because Notion can’t orchestrate it, but because Notion does orchestrate it, as the database layer, while Cloud Run handles the execution. The Worker is the tickle. Cloud Run is the muscle. Notion is the brain that remembers everything.

    What “Brand Everything Database” Actually Means in Practice

    If you’re an agency, a media operation, or a multi-brand operator, here’s the concrete version of this architecture:

    • One Notion workspace as the brand OS. Every client, project, task, content piece, automation job, and decision lives as structured database rows. Not documents. Not folders. Typed, relational data.
    • Agents inside Notion prep the data. Custom agents compile status updates, flag stale work, surface blockers, build briefings — all operating on the Notion database directly. The “everything” data is always clean and current because agents are maintaining it continuously.
    • Workers trigger external execution. When a job needs more than 30 seconds — content pipelines, SEO runs, bulk operations — a Worker fires the trigger. Cloud Run executes. Results come back into Notion. The database stays the source of truth.
    • Any surface can consume it. A Copilot user can query the project database through Microsoft Graph connectors. A Google Workspace user can sync from Notion via the connector ecosystem. A custom dashboard can read the Notion API. The front end doesn’t matter. The database is always current.
    • External agents get full context. Through the External Agents API, Claude, Codex, or any agent you build can operate against your Notion databases with complete organizational context — not a generic AI, but one that knows your specific data, your specific projects, your specific brand.

    Why This Beats Betting on One Everything App

    The everything-app race has a winner-take-all framing that may be wrong. Here’s what we’ve observed from operating across Microsoft, Google, and Notion simultaneously:

    Different team members live in different surfaces. Your developer lives in GitHub and a terminal. Your account manager lives in Gmail. Your ops lead lives in a spreadsheet. Your creative lead lives in Figma. Forcing everyone onto one everything app means fighting human behavior, not working with it.

    But if everyone’s work — regardless of where they do it — writes back into a shared Notion database? The everything app problem disappears. You don’t need everyone in the same surface. You need everyone’s data in the same structure.

    That’s what Notion’s connector ecosystem is actually building toward. GitHub syncs into Notion. Jira syncs into Notion. Salesforce syncs into Notion. Slack syncs into Notion. The surface stays wherever it is. The intelligence layer centralizes.

    The Compounding Advantage

    Here’s the strategic reason this matters beyond the technical architecture: databases compound. Documents don’t.

    A Google Doc from two years ago is mostly dead weight — hard to search, hard to query, impossible for an agent to reason over reliably. A Notion database from two years ago is a living asset. Every row is still queryable. Every relationship still works. The history of every project, every decision, every outcome is structured data that an agent can analyze, pattern-match against, and use to inform current work.

    The longer you run your brand’s operations through a Notion database, the smarter your agents get — because they have more structured history to work with. That’s not true of any document-first system. And it’s not something you can easily replicate once a competitor has two years of structured operational data and you’re starting from scratch.

    The everything app you pick in 2026 matters less than the data structure you commit to in 2026. Pick the wrong everything app and you switch in 18 months. Pick the wrong data structure and you’re rebuilding from zero.

    The Practical Starting Point

    If this architecture makes sense for your operation, here’s how to think about the starting point:

    • Audit what data your business actually runs on. Tasks, projects, clients, content, pipelines, automations — map out what you’re currently tracking and where. How much of it is in documents? How much is in structured databases?
    • Pick the three databases that matter most and build them right in Notion. Don’t try to migrate everything at once. Start with your project tracker, your content calendar, and your client/contact database. Get those typed, relational, and agent-ready.
    • Connect one external source via Workers or the connector ecosystem. Slack, GitHub, Jira — pick the one that generates the most signal for your operation and get it syncing into Notion.
    • Build one Custom Agent that works on those databases. A status compiler, a blocker detector, a briefing builder — something that demonstrates the database-first advantage concretely to your team.
    • Then consider the trigger pattern. What jobs in your operation take longer than 30 seconds but could be triggered from a database change? Those are your first Cloud Run candidates, with Notion as the orchestration layer.

    The everything app race is real. But the more durable competitive advantage is the data structure underneath it. Build the database right, and the everything app becomes a detail.

    Frequently Asked Questions

    What is a “brand everything database” in Notion?

    A brand everything database is a Notion workspace architected as the structured, queryable source of truth for all of a brand’s operational data — tasks, projects, content, clients, automations, decisions. Unlike document-based systems, every piece of information is typed, relational, and agent-readable. External tools sync into it; agents operate on it; any surface can consume it via the Public API.

    How do Notion Workers act as triggers for Google Cloud Run?

    Notion Workers run in a 30-second sandbox — enough time to read a Notion database row, construct a signed payload, and fire an HTTP POST to a Cloud Run endpoint. The Worker returns immediately; Cloud Run handles the long-running execution (minutes, not seconds) and writes results back to the Notion database via the Public API. This makes Notion the orchestration and visibility layer without hitting the sandbox time limit.

    Why is a database-first architecture better than document-first for AI agents?

    Documents require AI to infer structure from prose — an error-prone process that degrades at scale. Database rows are typed, structured, and directly queryable. An agent asking “which projects are blocked this week?” gets an exact filter result from a Notion database in milliseconds; the same question against a folder of Google Docs produces a best-effort summary. Reliability and precision are the key differences.

    Can Notion databases feed Microsoft Copilot or Google Workspace agents?

    Yes, via connectors and the Notion Public API. Microsoft Graph connectors and Google Workspace connectors can sync from Notion databases. Custom agents built on the External Agents API can also read and write Notion data from any external platform. The Notion database becomes the shared source of truth regardless of which AI surface your team prefers.

    What’s the best first step to building a brand everything database in Notion?

    Start with three core databases: a project tracker, a content calendar, and a client/contact database. Get them typed with proper properties, linked relationally, and cleaned up. Then build one Custom Agent that operates on those databases — a status compiler or briefing builder. Once you’ve seen the database-first advantage in action, the architecture for connecting external tools and Cloud Run triggers becomes obvious.

  • Notion’s Database-First Bet: Why the Everything App Might Be Built on a Spreadsheet, Not a Document

    Notion’s Database-First Bet: Why the Everything App Might Be Built on a Spreadsheet, Not a Document

    Last refreshed: May 15, 2026

    See also: Our full breakdown of the May 13, 2026 platform launch is here — Notion Developer Platform Launch (May 13, 2026). And for the operating doctrine the launch reinforces, see The Three-Legged Stack.

    Microsoft is stitching together an everything app from acquisitions. Google is trying to unify a native stack it keeps fragmenting. Notion is doing something different — and arguably more interesting. It’s building the everything app from the database up, and it just made its most important move yet.

    Definition: The Database-First Everything App An AI-powered workspace where every piece of information — tasks, projects, docs, contacts, data — lives in a structured, queryable database, and agents can read, write, reason over, and act on that data autonomously. The database isn’t the backend. It’s the interface.

    Yesterday Changed Everything for Notion

    On May 13, 2026 — yesterday — Notion shipped version 3.5 and announced their full Developer Platform in a livestreamed product event. The tech press covered it as an AI agent story. They weren’t wrong, but they missed the bigger frame.

    Notion didn’t just add agents. They introduced a new primitive called Workers — a hosted runtime for custom code that lets teams extend Notion without running their own servers. Database sync, agent tools, and webhook triggers all run through Workers. They launched the External Agents API, allowing any agent — ones you built, or ones from Claude, Codex, Decagon, and other partners — to work natively inside your Notion workspace. And they opened a developer platform that lets teams connect AI agents, external data sources, and custom code directly into their workspace.

    Taken individually, these are nice product updates. Taken together, they’re an orchestration play. Notion is positioning itself not as a note-taker with AI features bolted on, but as the hub where people, agents, and data collaborate across every tool a team uses.

    The Database Advantage Nobody Else Has

    Here’s the thing that separates Notion from every other everything-app candidate — including Microsoft and Google.

    Both Microsoft 365 and Google Workspace are document-first platforms. Their fundamental unit of work is a file: a Word document, a Google Doc, a PowerPoint, a Sheet. Files are great for humans to read. They’re terrible for AI to reason over at scale. You can’t ask an AI agent to “find every project where the status is blocked and the deadline is this week” across a folder of Word documents and get a reliable answer.

    Notion’s fundamental unit is a database. Every page can be a database row. Every property is structured, queryable, filterable data. When Notion AI looks at your workspace, it doesn’t see a pile of documents — it sees a relational knowledge graph. Tasks have statuses. Projects have owners and deadlines. Contacts have properties. Everything is connected, typed, and queryable.

    That’s not a feature difference. That’s an architectural difference. And it’s why Notion’s agents can do things that Copilot and Gemini agents fundamentally struggle with: operate reliably on your actual organizational data, not summaries of your documents.

    The Agent Timeline: Faster Than Anyone Expected

    Notion’s agent rollout has moved at a pace that’s easy to underestimate if you haven’t been watching closely. Here’s the actual timeline:

    • September 18, 2025 — Notion 3.0: Agents. First AI agents launch. Autonomous data analysis and task automation. The starting gun.
    • January 20, 2026 — Notion 3.2. Mobile AI, new model support, people directory. Agents go everywhere, not just desktop.
    • February 24, 2026 — Notion 3.3: Custom Agents. Users can build their own agents from scratch. Over 21,000 custom agents built in the first free trial period alone. Notion reported 2,800 agents running 24/7 internally at Notion itself.
    • March 2026. Workers introduced in alpha — a TypeScript-based framework for agents to talk to any service with an API. The coding layer for power users.
    • April 14, 2026 — Notion 3.4. Calendar and inbox connectors. Notion AI can now schedule meetings and draft emails from inside your workspace.
    • May 5, 2026. Custom Agent admin controls for enterprise — workspace-level credit limits, governance tools, compliance features.
    • May 13, 2026 — Notion 3.5: Developer Platform. External Agents API, Workers out of alpha, database sync with no servers, full developer ecosystem launched.

    That’s eight months from first agent launch to full developer platform. For context, Microsoft spent years building Azure OpenAI integration before Copilot reached feature parity with what Notion shipped in less than a year.

    What the Notion Everything App Actually Looks Like Today

    This isn’t theoretical. Here’s what a team running on Notion can configure right now:

    • Your project data, always current. Databases synced from Slack, Google Drive, GitHub, Jira, Microsoft Teams, Salesforce, and Box — all flowing into Notion databases in real time, powered by Workers. No manual updates. No stale spreadsheets.
    • Agents watching your work. Custom agents triggered by database changes, schedules, or webhooks — compiling status updates, flagging blocked tasks, escalating overdue items, answering team FAQs.
    • Your inbox and calendar inside your workspace. Connect Gmail or Outlook and your calendar; Notion AI can schedule meetings and draft emails without leaving the tool your work already lives in.
    • External agents working in your context. Claude, Codex, Decagon — agents you’ve built yourself via the External Agents API — all operating against your Notion databases with full context. Not generic AI. AI that knows your specific data.
    • Plan Mode for complex operations. Before an agent makes large changes to your databases or pages, it stops, asks clarifying questions, and builds a plan for your approval. This is the governance layer that makes AI trustworthy in a business context.
    • Your institutional knowledge, always accessible. Every decision, every project history, every team document — structured and queryable by agents that can synthesize across your entire knowledge base on demand.

    The Model Behind It: Claude Opus 4.7

    Unlike Microsoft (Copilot runs on GPT-4o and Azure OpenAI) and Google (Gemini family), Notion is built on Anthropic’s Claude. As of the January 2026 update, Notion runs Claude Opus 4.7 — Anthropic’s most capable model at the time of release — for its AI features and agent reasoning.

    This is a strategic choice worth examining. Claude is specifically designed with a focus on reliability, honesty, and safe behavior in agentic contexts — qualities that matter enormously when an AI agent has write access to your company’s databases. Anthropic’s Constitutional AI training approach was built for exactly the kind of autonomous, long-running agent work that Notion is deploying.

    The Notion + Claude combination isn’t just a vendor relationship. It’s an architectural alignment: a database-first workspace built on a model specifically designed for trustworthy agentic behavior. That’s a more coherent stack than either Microsoft or Google has assembled, where the AI model and the productivity platform were developed independently and integrated later.

    Why “Database First” Beats “Document First” for the Everything App

    Let’s make this concrete with a comparison most teams will recognize.

    Ask Microsoft Copilot: “Which of our client projects are behind schedule this quarter?” Copilot will search your emails, scan your SharePoint documents, and produce a reasonable summary — but it’s reading prose, inferring structure, and hoping the documents are up to date. The answer is a best-effort synthesis, not a query result.

    Ask a Notion agent the same question: it runs a database filter. Status = Behind. Quarter = Q2 2026. It returns an exact list in under a second, with links to every project, the responsible person, and the last update — because that data is structured. The agent didn’t infer anything. It read typed data.

    That’s the difference between AI that helps you find things and AI that actually knows things. Notion’s database architecture is what makes the second kind possible at scale, without hallucination, without retrieval errors, without the AI making up a project that doesn’t exist.

    The Honest Weakness: The 30-Second Wall

    Here’s what you only learn by actually building inside the alpha — and we did.

    Notion Workers runs in a 30-second sandbox with 128MB of memory. Each Worker is created through the Notion control panel, taking 3–5 minutes to spin up. The network is limited to an approved domain allowlist. Storage is ephemeral — nothing persists between runs. These aren’t theoretical constraints. They’re the real walls you hit when you try to move serious automation workloads into Notion.

    We were in the Workers alpha. We built Workers. We set up custom agents. And we stress-tested the sandbox deliberately — forcing failures to find the exact break points, then running production workloads at 60% of the known ceiling as a stability rule. That’s the only honest way to operate inside a system this constrained: know where it breaks before you depend on it.

    What we found changed our architecture. Heavy automations — multi-site WordPress SEO optimization passes across 18 sites, content pipelines, image generation, WP-CLI batch operations — couldn’t live inside Notion Workers. They’re multi-minute jobs, not 30-second jobs. Moving them to Notion would have meant engineering workarounds that added complexity without adding reliability.

    So instead of moving Cowork automations into Notion as we originally planned, we moved them to Google Cloud Run. The notion-deep-extractor (crawls the workspace, extracts structured knowledge, logs to the Second Brain database — runs 3x daily) and the notion-maintenance bundle (archive sweeper, stale work detector, content guardian — runs daily at 6am UTC) all live on Cloud Run now, with Cowork scheduled tasks paused. The 18-site WordPress optimizer running Tuesday? Cloud Run. Not Notion.

    This isn’t a knock on Notion. It’s an architectural reality that every builder needs to understand before they commit workloads. The right pattern — the one we’re now using and that Notion’s own documentation points toward — is Notion Workers as the trigger layer, Cloud Run as the execution layer. A Worker fires a signed POST to a Cloud Run endpoint, returns immediately (well under 30 seconds), Cloud Run runs the heavy job, then writes results back to a Notion database via the Public API. You get Notion as the orchestration and visibility layer without hitting the sandbox wall.

    That hybrid is genuinely powerful. But it requires infrastructure that most small teams don’t have. If you don’t have a Cloud Run setup, a service account, and the deployment knowledge to wire this together, the 30-second limit will stop you cold on anything more complex than a lightweight API call or a database update.

    Notion doesn’t own email. It connects to Gmail and Outlook. It doesn’t own a calendar — it integrates with yours. It doesn’t have a mobile OS or browser. Those gaps matter less than the sandbox constraint does for real production workloads. The everything app story is real — but the execution layer has hard limits that require a hybrid architecture to work around, at least until Workers matures beyond its current beta constraints.

    Who Should Be Paying Attention Right Now

    If you’re an agency, a service business, a content operation, or any knowledge-work team that already uses Notion — or has been considering it — the May 13 Developer Platform announcement changes your calculus significantly.

    Custom Agents are available as an add-on for Business and Enterprise plans. Workers are free during the current beta period (billing starts August 11, 2026). The External Agents API is open now. This is the window to build before your competitors do.

    The teams that spend the next 90 days wiring up their Notion databases, building their first custom agents, and connecting their external data sources will have a compounding advantage that’s very hard to replicate in 2027. The institutional knowledge that feeds these agents — the project histories, the SOPs, the client databases — takes time to build. Starting now is the only strategy that works.

    The Bigger Picture: A Series on Who Wins the Everything App

    This is the third article in an emerging pattern I’ve been thinking through: who actually builds the everything app, and what does their path look like?

    Microsoft is building it through acquisitions and Copilot, stitching together LinkedIn, Azure, and the M365 suite. Google already owns the native stack — Gmail, Drive, Search, Android — and is trying to unify it through Gemini Enterprise and Workspace Studio after years of product fragmentation. Notion is building it from the database up, betting that structured data plus open agents beats document-first platforms with AI bolted on.

    None of them has won yet. All three bets are live. The winner won’t be the company with the most features — it’ll be the one that earns enough trust to become the single place where your work actually lives.

    Notion’s database-first architecture is the most interesting bet of the three. It’s also the most fragile — dependent on integrations, constrained by not owning the OS or the inbox, limited by whatever Anthropic does with Claude pricing and capabilities. But if it works, it works in a way the others can’t easily copy. You can’t retrofit a database architecture onto a document platform. You have to start over.

    Microsoft and Google aren’t starting over. Notion never had to.

    Frequently Asked Questions

    What are Notion Custom Agents?

    Notion Custom Agents are AI teammates that handle repetitive tasks autonomously — answering FAQs, compiling status updates, automating workflows — triggered by schedules, database changes, or webhooks. They launched in February 2026 (Notion 3.3) and are available as an add-on for Business and Enterprise plans. Over 21,000 were built during the free trial period alone.

    What is Notion Workers?

    Notion Workers is a hosted cloud runtime for custom TypeScript code, introduced in alpha in March 2026 and fully launched with the Developer Platform on May 13, 2026. It powers database sync, agent tools, and webhook triggers — letting teams extend Notion to connect any service with an API, without running their own servers. Workers are free during the beta period through August 10, 2026.

    What AI model does Notion use?

    Notion runs on Anthropic’s Claude — specifically Claude Opus 4.7 as of the January 2026 update. This is different from Microsoft Copilot (which uses OpenAI’s GPT models) and Google Workspace (which uses the Gemini family). Notion’s choice of Claude reflects an emphasis on reliable, safe agentic behavior for workflows that have write access to business databases.

    What is the Notion External Agents API?

    The External Agents API, launched with Notion 3.5 on May 13, 2026, lets teams bring any AI agent — including ones built internally or from partners like Claude, Codex, and Decagon — directly into their Notion workspace. These external agents can read and write to Notion databases with full context about the team’s data.

    How is Notion different from Microsoft Copilot and Google Workspace AI?

    Notion is database-first. Every piece of information in Notion is structured, typed, and queryable data — not documents. This means Notion agents can run precise database queries against your actual organizational data rather than inferring structure from prose documents. For teams that need AI to reliably operate on business data (not just search and summarize), this architectural difference is significant.

    What are the real limitations of Notion Workers in the alpha?

    Notion Workers runs in a 30-second sandbox with 128MB of memory and ephemeral storage. Network access is limited to an approved domain allowlist. Workers are created via the Notion control panel (3–5 minutes each). Long-running jobs — content pipelines, multi-site operations, image generation — won’t fit. The recommended pattern for serious workloads is Notion Workers as the trigger layer firing a signed POST to an external execution environment (like Google Cloud Run), with results written back to Notion databases via the Public API.

  • Google Already Has the Everything App. The Question Is Whether They’ll Actually Build It.

    Google Already Has the Everything App. The Question Is Whether They’ll Actually Build It.

    Microsoft gets credit for the “everything app” conversation because of Copilot’s marketing reach. But Google has quietly assembled something more complete, more native, and arguably more dangerous to every other productivity platform on earth — and most people haven’t connected the dots yet.

    Definition: Google’s “Everything Stack” The convergence of Google Workspace, Agentspace, Workspace Studio, NotebookLM, Google Search, Gmail, Calendar, Drive, Maps, Android, and the Gemini model family into a single AI-unified operating environment — where agents connect your data, automate your work, and surface what matters, without switching apps.

    Google Didn’t Need to Acquire Its Way Here

    Microsoft’s path to the everything app runs through acquisitions: LinkedIn ($26.2B), GitHub ($7.5B), Activision ($68.7B), and years of stitching Azure, Teams, and Bing into a coherent story. It’s impressive. It’s also fundamentally a construction project — building a unified platform out of parts that weren’t designed to work together.

    Google already owns the pieces natively. Gmail. Google Calendar. Google Drive. Google Docs, Sheets, and Slides. Google Search. Google Maps. Android. Chrome. YouTube. These aren’t acquisitions bolted onto a platform — they’re the platform. Over three billion people use Google Workspace tools. That install base isn’t a future bet; it’s the present reality.

    The question was never whether Google had the ingredients. The question was whether they’d ever actually bake the cake. In 2026, they finally are.

    What Google Just Shipped: The Pieces Coming Together

    At Google Cloud Next 2026, Google made moves that deserve more attention than they got.

    Workspace Studio launched to all Google Workspace domains on March 19, 2026. It’s the place to create, manage, and share AI agents that automate work across Workspace — no coding required. An end user can describe what they want in plain language (“every Friday, ping me to update my tracker”) and Gemini builds the agent. That’s not a developer feature. That’s a feature for your office manager, your sales coordinator, your operations lead.

    Workspace Intelligence is the connective tissue underneath. It’s a secure, dynamic system that understands the semantic relationships between your Docs, Slides, Gmail threads, active projects, collaborators, and your organization’s institutional knowledge — all in real time. Not indexed. Not cached. Live.

    Google Agentspace (now absorbed into the unified Gemini Enterprise Agent Platform as of Cloud Next 2026) brings together Gemini’s reasoning, Google-quality search, and enterprise data regardless of where it lives. Agents can connect to Google Drive, NotebookLM, and Google Group Chats and become an expert on a specific topic — delivering daily briefings, status updates, and research synthesis without anyone digging through months of documents.

    NotebookLM — Google’s AI research and synthesis tool — is now available as an out-of-the-box agent in Agentspace for enterprise users, with podcast-style audio summaries, enhanced privacy controls, and direct integration into the agent ecosystem. It’s the knowledge layer sitting on top of everything else.

    The AI Control Center, announced in May 2026 in the Admin console, gives IT and enterprise organizations visibility and governance over every agent and AI interaction touching Workspace data. For regulated industries, this is the feature that unlocks the whole stack.

    The Model Reality: Get This Right Before You Strategize

    Any honest conversation about Google’s AI strategy has to be anchored in what the models actually are — because the capabilities are moving fast and the marketing often lags the reality.

    As of mid-2026, Google’s current model family looks like this:

    • Gemini 3.1 Pro — Released February 19, 2026. The most capable model in the family. Scores 77.1% on ARC-AGI-2. Optimized for complex multi-step agentic workflows. This is the model powering the high-stakes enterprise use cases.
    • Gemini 2.5 Pro — The previous flagship, announced at Google I/O 2025. Still widely deployed in Vertex AI for enterprise. Excellent reasoning, very long context window.
    • Gemini 2.5 Flash — The speed/cost-efficiency model. Default model in the Gemini app. Generally available in Google AI Studio and Vertex AI. This is what most Workspace automation runs on day-to-day.
    • Gemini 2.5 Flash-Lite — The lightest, cheapest tier. For high-volume, low-complexity tasks like classification, routing, and summarization at scale.

    The architecture matters for strategy: Gemini 3.1 Pro handles reasoning-heavy agent tasks (complex research, multi-step decisions, agentic workflows), while Flash handles the volume work (daily digests, routine automation, quick lookups). The tiered model family is what makes an everything-app architecture economically viable — you don’t run your email summarizer on your most expensive model.

    What Google’s Everything Page Actually Looks Like Today

    Here’s what’s possible right now — not as a concept, but as actual configured Workspace behavior:

    • Your Gmail digest — Gemini in Gmail surfaces key threads, drafts replies, and flags action items before you open your inbox
    • Your Calendar intelligence — Meeting briefs pulled from your Drive documents, recent email threads with attendees, and relevant Docs — surfaced automatically before each event
    • Your Drive knowledge — NotebookLM agents synthesizing your team’s documents, project histories, and institutional knowledge into on-demand briefings
    • Your automation outputs — Workspace Studio agents running on schedule, pinging updates, moving data between Sheets and Docs, reporting on triggers
    • Your search layer — Google Search and Workspace Intelligence working together to answer business questions against both your internal data and the public web
    • Your news and signals — Gemini Enterprise surfacing industry news, competitor moves, and relevant content as part of a unified daily briefing

    The difference between this and the Microsoft vision is subtle but important: Google’s version requires almost no new infrastructure for most organizations. If you’re already on Google Workspace — and three billion people are — the agent layer sits on top of what you already use. The friction is configuration, not adoption.

    The Tension: Google’s Biggest Competitor Is Google’s Own Fragmentation

    Here’s where the opinion part comes in, because the facts alone don’t tell the whole story.

    Google has a well-documented history of building extraordinary tools and then failing to unify them. Google+. Google Wave. Google Inbox. Allo. Hangouts. The graveyard of Google products that almost became the everything app is long and sobering. The pattern is consistent: build something brilliant, run it in parallel with five other things, confuse the market, and eventually kill it.

    The 2026 rebranding — consolidating Vertex AI and Agentspace into the Gemini Enterprise Agent Platform — is either the sign that Google has finally learned its lesson about fragmentation, or it’s another reorganization that will look different again in 18 months. The cynical read is that Google Cloud Next announcements have promised unification before.

    The optimistic read — and I lean toward this one — is that the Gemini model family gives Google something it never had before: a single coherent AI backbone that every product can be rebuilt around. When your search, your email, your documents, your agents, and your developer platform all run on the same model family with the same context and the same API surface, unification becomes an engineering problem rather than a product vision problem. Engineering problems get solved.

    The A2A Protocol: The Move Nobody Talked About Enough

    One of the quieter announcements at Cloud Next 2026 was the Agent-to-Agent (A2A) protocol — Google’s open standard for allowing AI agents to communicate with each other across platforms and vendors. This is strategically significant in a way that’s easy to miss.

    If A2A gains adoption, the everything page doesn’t have to be Google’s proprietary walled garden. Your Workspace agents could communicate with agents from other platforms — your CRM, your project management tool, your industry-specific software. Google becomes the orchestration layer rather than the only layer. That’s a smarter long-term play than trying to own everything, and it sidesteps the antitrust concern that the Microsoft everything-app vision runs into head-on.

    What This Means for SMBs and Content Creators Right Now

    If you’re a small business running on Google Workspace — and most are — the everything-app infrastructure is closer than you think, and cheaper than you assume.

    Workspace Studio is included in Business Standard and above. Gemini in Gmail and Docs is rolling out across plans. NotebookLM Business is available as an add-on. The agent layer is not a future enterprise-only feature — it’s arriving in the same tools you’re already paying for.

    The businesses that will win the next three years are the ones that start treating their Google Workspace as an agent platform right now — connecting their data, building their automations, and training their teams to work alongside AI rather than around it.

    The everything page isn’t a product launch you wait for. It’s a configuration decision you make today.

    Google vs. Microsoft: Who Wins the Everything App Race?

    Honest answer: it’s not a race with one winner. The enterprise world will bifurcate along existing tool allegiances. Microsoft 365 shops will get their everything page through Copilot and Agent 365. Google Workspace shops will get theirs through Gemini Enterprise and Workspace Studio. The cold-start problem — who do you trust with all your connected data — will be solved by whoever already has your accounts.

    What’s different about Google’s position is the consumer crossover. Microsoft dominates enterprise desktops but has marginal consumer presence. Google lives on both sides — the same Gemini that runs your enterprise agent also runs in your personal Gmail, your Android phone, your Google search bar. The everything page, for Google users, won’t feel like a new product. It’ll feel like the thing you already use, finally doing what you always wished it would.

    That’s a powerful distribution advantage. And it’s one Microsoft, for all its enterprise strength, can’t easily replicate.

    Frequently Asked Questions

    What is Google Workspace Studio?

    Google Workspace Studio is Google’s no-code AI agent builder, launched to all Workspace domains on March 19, 2026. It lets any user create, manage, and share AI agents that automate work across Gmail, Docs, Sheets, Drive, and other Workspace apps — without writing code. Users describe what they want in plain language and Gemini builds the agent.

    What is Google Agentspace?

    Google Agentspace (now unified into the Gemini Enterprise Agent Platform as of Cloud Next 2026) is Google’s enterprise AI agent environment. It combines Gemini’s reasoning, Google-quality search, and enterprise data across Drive, NotebookLM, and Group Chats to give employees AI agents that understand their organization’s specific knowledge.

    What is the latest Google Gemini model in 2026?

    As of mid-2026, Gemini 3.1 Pro (released February 19, 2026) is Google’s most capable model, scoring 77.1% on ARC-AGI-2 and optimized for complex agentic workflows. Gemini 2.5 Flash is the default model for most consumer and business Workspace use cases, balancing speed and cost efficiency.

    What is Google’s A2A protocol?

    Agent-to-Agent (A2A) is Google’s open standard for AI agents to communicate across platforms and vendors, announced at Cloud Next 2026. It allows Workspace agents to interoperate with agents from other tools and platforms, positioning Google as an orchestration layer rather than a closed ecosystem.

    Do small businesses have access to Google’s AI agent features?

    Yes. Workspace Studio and Gemini features are included in Business Standard and higher tiers. NotebookLM Business is available as an add-on. Most of the agent infrastructure is arriving in existing Workspace plans, not as separate enterprise-only products.

  • Microsoft’s Everything App: Is Copilot Building the Unified AI Dashboard Nobody Asked For (But Everyone Needs)?

    Microsoft’s Everything App: Is Copilot Building the Unified AI Dashboard Nobody Asked For (But Everyone Needs)?

    What if every email, calendar event, LinkedIn notification, health metric, automation log, and business dashboard you care about lived on one page — organized by AI, updated in real time, and actually useful? That’s not a fever dream. It may already be Microsoft’s plan. And if it isn’t, someone needs to build it fast.

    Definition: The “Everything App” A unified AI-powered platform that aggregates professional data, communications, scheduling, automation outputs, and personal metrics into a single intelligent interface — personalized per user and powered by connected APIs.

    The Observation That Started This

    A few days ago I noticed something odd: LinkedIn posts I was publishing were reformatting into blocks of plain text instead of keeping their intended structure. My own agents couldn’t scrape LinkedIn the way I wanted them to. Anti-AI friction was everywhere on the platform.

    Then it hit me: Microsoft owns LinkedIn. Microsoft owns Bing. Microsoft is betting billions on Copilot. What if the formatting weirdness, the scraping blocks, the structured data changes — what if those aren’t bugs? What if they’re features in a Beta program for AI information ingestion?

    Think about it differently. Imagine a Bing page — or a Copilot interface — that pulls in curated LinkedIn posts, your email threads, your calendar, your business process updates, your health watch data, your cloud automations, and your news feed. All of it, organized the way you think about your day. That’s not a stretch. That might be exactly where this is heading.

    Microsoft Is Already Building the Pieces

    Let’s be clear about what Microsoft has actually shipped and announced, because the pieces of this puzzle are already on the table.

    Microsoft 365 Copilot Wave 3 launched in early 2026 alongside Microsoft 365 E7: The Frontier Suite (generally available May 1, 2026). It combines productivity, identity, Copilot AI, and Agent 365 — a control plane for governing and scaling AI agents across an organization. The Agent 365 dashboard shows connections between agents, people, and data in real time. That’s not a search box. That’s an operational view of your entire professional world.

    Microsoft Graph is the connective tissue. It links LinkedIn professional data — profiles, company updates, job changes, content signals — directly into Copilot’s intelligence layer. When enterprise users ask Copilot about industry experts or companies, LinkedIn data feeds the answer. The integration is deeper than most people realize, and it’s been quietly expanding since Microsoft acquired LinkedIn for $26.2 billion in 2016.

    Bing web cards in Copilot Chat now deliver rich, expandable information cards for weather, stocks, sports, news, and more. It’s a small feature on paper. But it signals the visual direction: Copilot as a personalized front page, not a search box.

    The new Agenda view in Windows — announced at Ignite 2025 — shows a chronological list of upcoming events unified with Calendar, surfaced directly in the Notification Center. Microsoft is literally building a unified daily view into the operating system itself.

    Why the Western Super App Never Happened — Until Now

    WeChat has over 1.3 billion monthly active users and handles messaging, payments, e-commerce, government services, and mini-programs all in one place. Western companies have been trying and failing to replicate that for a decade.

    The reasons for failure are real: U.S. data privacy law, antitrust scrutiny, platform fragmentation, and deeply entrenched single-purpose apps (Slack for chat, Stripe for payments, Google Calendar for scheduling) made the super app strategy a dead end in the West.

    But AI changes the calculus. The old super app required you to rebuild every vertical inside one app. The new super app just needs one AI brain that can use everything outside it. You don’t need to own payments — you need Copilot to understand your Stripe data. You don’t need to own scheduling — you need Copilot to read your Google Calendar and act on it.

    As one analysis of the U.S. super app window put it: “The old super app was ‘one app with everything inside.’ The next super app might be ‘one AI brain that can use everything outside.’” Between 2025 and 2027, the U.S. enters what some analysts call its Super App window — a convergence of AI interfaces, behavioral compression, and digital sovereignty that’s distinctly Western in character.

    Microsoft is the only Western company with the asset stack to pull this off: an OS (Windows), a browser (Edge), a search engine (Bing), a professional network (LinkedIn), a productivity suite (Microsoft 365), a developer platform (GitHub + Azure), and now a unified AI layer (Copilot) stitching it all together.

    What the “Everything Page” Actually Looks Like

    Here’s the vision, stated plainly:

    • Your news — curated by AI based on your industry, interests, and saved searches
    • Your LinkedIn feed — surfaced selectively, not chronologically, based on what actually matters to your business goals
    • Your email digest — key threads, action items, follow-ups, flagged by AI before you even open your inbox
    • Your calendar — not just events, but prep briefs for each meeting pulled from your email, CRM, and LinkedIn history
    • Your automation outputs — Cloud Run jobs, Zapier logs, agent reports, anything your background systems are doing
    • Your health signals — fitness watch data, sleep scores, recovery metrics — not in a separate app, but contextualizing your day
    • Your business metrics — revenue, leads, content performance, wherever your data lives

    All of it on one page. All of it updated in real time. All of it organized by an AI that knows what you consider signal versus noise.

    That’s not sci-fi. The APIs for all of that exist today. The AI to synthesize it exists today. The missing piece is the will to build the page — and a platform with enough trust and install base to make it stick.

    The LinkedIn Angle Nobody Is Talking About

    Here’s where my original observation gets more interesting. Microsoft has spent years sitting on one of the richest professional datasets on earth and doing relatively little with it compared to what’s possible. LinkedIn has 1 billion+ members, decades of career graph data, company relationship maps, content engagement signals — and it feeds directly into Microsoft Graph.

    Now that Copilot is deeply embedded in enterprise environments, LinkedIn data isn’t just a social feature — it’s a professional intelligence layer. When your Copilot brief for a sales call surfaces that your prospect just changed jobs, posted about a pain point, or follows a competitor — that’s LinkedIn data flowing through Microsoft Graph into your daily workflow.

    The scraping friction I noticed? It makes more sense when you consider that Microsoft may be actively working to make LinkedIn data more valuable inside its own ecosystem rather than letting third-party agents extract it freely. They’re not blocking AI — they’re channeling it through Copilot.

    The Risk: Nobody Wants One Company Holding All of This

    It would be dishonest not to acknowledge the obvious counterargument: this is a massive concentration of data and influence in one company’s hands.

    The reason WeChat works in China is partly cultural and partly because the regulatory environment permits it. U.S. antitrust law, GDPR-aligned state privacy rules, and growing public skepticism about big tech data practices all push against a single unified everything app.

    Microsoft’s bet is that enterprise trust — built through compliance features, security architecture, and the corporate IT relationship — gives them the permission that consumer platforms like Meta or X never earned. It’s a reasonable bet. It’s also one that regulators will watch closely.

    If Microsoft Doesn’t Build It, Someone Will

    The technology is not the bottleneck. Any serious developer with access to the right APIs could build a personal everything page today. Connect your Gmail, your LinkedIn (to the extent the API allows), your calendar, your fitness data, your cloud automation logs, and your analytics tools. Build a UI that surfaces what matters. Add an AI layer to summarize and prioritize.

    The bottleneck is distribution, trust, and the cold-start problem — nobody wants to connect all their accounts to something they’ve never heard of. That’s why Microsoft wins this race if they choose to run it. They already have the accounts. They already have the trust relationships. Copilot is already installed in hundreds of millions of enterprise seats.

    But if they don’t move fast enough, or if they build it only for enterprise and ignore the small business and creator class — that’s an opening. A focused, privacy-first, SMB-oriented everything page, built on open APIs, with no data lock-in? That’s a product worth building.

    What This Means for Your Content and AI Strategy Right Now

    Whether or not Microsoft delivers the everything app in the next 18 months, the direction of travel is clear. Professional information is consolidating around AI interfaces. LinkedIn content is increasingly flowing into Copilot’s intelligence layer. Bing-based AI answers are pulling from structured, authoritative content.

    For businesses and content creators, that means:

    • Your LinkedIn presence is now AI training data. What you post, how you structure it, and what entities you’re associated with affects how Copilot describes you to enterprise users asking about your industry.
    • Your website content needs to be AI-readable. Structured data, clear entity signals, authoritative citations — these are no longer optional for AI search visibility.
    • Your automation stack is a competitive advantage. The businesses that have already connected their tools via APIs will be first in line when the everything page actually ships.

    The everything app isn’t coming. It’s arriving in pieces, quietly, through products you already use. The question is whether you’re positioned when the pieces snap together.

    Frequently Asked Questions

    Is Microsoft building an “everything app” like WeChat?

    Microsoft hasn’t announced a single “everything app” product, but the pieces — Copilot, Microsoft Graph, LinkedIn data integration, Agent 365, and Bing web cards — suggest a unified AI-powered dashboard is the strategic direction. Whether it arrives as one product or an ecosystem of connected tools remains to be seen.

    Why did Western super apps fail where WeChat succeeded?

    U.S. data privacy regulations, antitrust scrutiny, platform fragmentation, and deeply entrenched single-purpose apps all prevented a WeChat-style super app from emerging in the West. AI changes the equation by enabling one system to connect and synthesize data across many separate apps without needing to own them.

    How does LinkedIn data connect to Microsoft Copilot?

    Microsoft Graph links LinkedIn’s professional data — profiles, company updates, career changes, content signals — directly into Copilot’s intelligence layer. Enterprise Copilot users receive LinkedIn-informed context in sales briefings, meeting prep, and professional research queries.

    What is Microsoft 365 E7 and what does it include?

    Microsoft 365 E7 (The Frontier Suite, GA May 1, 2026) combines Microsoft 365 E5 for secure productivity, Entra Suite for identity and access, Microsoft 365 Copilot for AI-in-workflow, and Agent 365 as the control plane to govern and scale AI agents across an organization.

    What can small businesses do today to prepare for AI-unified platforms?

    Connect your tools via APIs now, optimize your LinkedIn presence for AI entity recognition, publish structured authoritative content for AI search visibility, and build automation stacks that produce clean data outputs — these investments compound in value as AI platforms consolidate professional information.

  • From A-Z to AI: The Great Compression of Human Knowledge

    From A-Z to AI: The Great Compression of Human Knowledge

    The world of 1974 was defined by physical weight. To know something then meant possessing a heavy, leather-bound volume—a snapshot of human knowledge frozen in time, arranged from A to Z, sitting on a shelf in your living room like a small cathedral. My father kept a set. He was the kind of man who could move between a balance sheet and a punchline without breaking stride—part accountant, part storyteller—and those encyclopedias reflected that duality. The data was in the volumes. The meaning was in the man who knew how to use them.

    Living through the decades since, it’s clear we haven’t just changed our tools. We’ve changed our orientation to the universe.

    The Encyclopedia Era: The Weight of the Macro

    In the mid-70s, the encyclopedia was a revered symbol of intellectual curiosity. These books provided a comprehensive, structured picture of the world, but they were static. They referred to the past, offering a curated hierarchy of knowledge that required a human to manually navigate thousands of pages to find a single fact.

    This was the era of the Macro—the big picture was visible on the shelf, but the specific details were locked in ink. You could see the whole forest. Finding a single tree took time, patience, and a willingness to get lost.

    The genius of that format wasn’t the information. It was the journey. You went looking for one thing and came out knowing three others. The serendipity was built into the medium.

    The Search Era: The Language of the Micro

    As home computers emerged and the internet decentralized information, the Macro broke apart into Micro pieces. We moved into the era of the Keyword.

    For the first time, we used rigid queries to describe our world. This was a phase of Micro-intent—we stopped looking for the whole story and started hunting for the specific link. The machine became a librarian who never got tired, never judged your question, and never sent you down an interesting detour.

    Revolutionary. And a little flat. The serendipity was gone. So was the storyteller.

    The AI Era: The Return of the Storyteller

    Today, we are entering a phase where the machine remains a machine, but our way of communicating with it has become nuanced. We have moved from keyword-matching to conversational interaction. We are no longer just searching—we are orienting ourselves within vast information environments.

    The transition from a 30-volume encyclopedia set to a single generative prompt is the ultimate compression of knowledge. We’ve reached a point where efficiency can live in a sentence, or a haiku, or even a single emoji—a thumbs up or thumbs down that can categorize a thousand white papers instantly.

    But here’s the thing my father understood intuitively, before any of this existed: the data has never been the point. The point is knowing which story to tell with it.

    The Human-in-the-Loop: The Final Sweet Spot

    The arc from the encyclopedia to AI is not a story of machines replacing humans. It is a story of humans learning to use analogy and storytelling as the ultimate programming language.

    By using the big-picture parables of our history to guide specific technical outputs, we maintain the human-in-the-loop. Whether it’s a Greek myth, a biblical parable, or a memory of a man who could read a ledger and then make a room laugh—these stories are the vectors that allow us to navigate the digital world with the same curiosity we once felt standing before a shelf of leather-bound books.

    The compression is real. The intelligence is still ours.

    The best prompt engineers aren’t coders. They’re storytellers who learned to speak machine.

    Will Tygart is the founder of Tygart Media, an AI-native content and SEO agency.

  • Cowork Routines and Windows Computer Use: What’s New and How We’re Using Both

    Cowork Routines and Windows Computer Use: What’s New and How We’re Using Both

    Last refreshed: May 15, 2026

    Two Cowork capabilities that haven’t been written about here yet, despite being live since late April: Cowork Routines (always-on scheduled tasks that run when your laptop is closed) and Windows computer use (Claude operating your Windows desktop directly from within Cowork). Both shipped in the April 28–30 window alongside the Claude GA release. Both materially change what Cowork is.

    Cowork Routines: The Laptop Can Be Closed

    The original Cowork model required your laptop to be open and the Cowork desktop app to be running. Useful — but bounded by your hardware being available and powered on. Cowork Routines changes that.

    Routines are cloud-hosted scheduled tasks that execute on Anthropic’s infrastructure regardless of your local hardware state. They run on a schedule you define. They execute when your laptop is off, sleeping, or in your bag on a plane. The task runs, the output lands where you configured it to land, and when you open the laptop you find the work done.

    The practical scope of what runs well as a Routine:

    • Daily briefings: Pull sources, synthesize, write to Notion or email — delivered before you open your laptop each morning
    • Monitoring tasks: Check a source on a schedule, flag anomalies, log findings
    • Content pipeline steps: Recurring publication tasks, social scheduling prep, site audit runs
    • Report generation: Weekly status documents assembled from live data sources
    • Notification triggers: Watch a condition, fire an action when it’s met

    We run our own Claude Newspaper Desk — a daily briefing that checks Anthropic’s news, release notes, GitHub releases, and external coverage, then writes a structured briefing to Notion before we start the day. That’s a Routine. The briefing that generated this article was produced by a Routine running on a schedule, not by someone manually triggering a task.

    The architectural decision that makes Routines significant: the task reads its instructions from a Notion desk spec page at runtime, not from a baked-in prompt. Change the Notion spec, change what the Routine does — without touching the scheduled task itself. The shim file that triggers the Routine is thin by design; the intelligence lives in Notion.

    Windows Computer Use: Claude Operates Your Desktop

    Computer use in Claude — the ability for Claude to navigate desktop interfaces, click through UI, fill forms, and verify results — was previously available primarily in research preview and on macOS. The April 2026 Cowork release brought computer use to Windows as a generally available capability within the Cowork desktop app.

    What this means in practice: Claude can open a native Windows application, navigate its interface, perform a sequence of actions, and hand the result back — without you needing to automate it through code or build an API integration. If there’s a tool that only has a Windows UI and no API, Claude can use the Windows UI directly.

    The current state of computer use is honest about its scope. It’s good at:

    • Navigating well-structured desktop applications with clear UI hierarchies
    • Form completion across multiple-step workflows
    • Data extraction from desktop tools that don’t export well
    • Verification steps that require visual confirmation

    It’s slower than direct API integrations when those exist. For tools with APIs, use the API. Computer use is the path when no API exists or when the integration cost exceeds the value of doing it properly.

    The combination of Routines + Windows computer use means a scheduled task can now include a step that operates a Windows desktop application — unattended, while your laptop is running in the background. That’s a meaningfully different capability than what Cowork shipped with originally.

    How We’re Using Both

    Our Cowork architecture as of May 2026:

    • Cowork as execution layer — always-on laptop running scheduled tasks
    • Notion as control plane — desk specs, task queues, logs, and credential storage
    • GCP Cloud Run as action layer — WordPress publishing, API calls, content pipeline steps
    • Claude Code Routines as cloud fallback — tasks that need to run independent of local hardware

    Routines handle the tasks where continuous availability matters more than local context: briefings, monitoring, scheduled publishing. Cowork handles the tasks where rich local context matters: multi-step sessions with file access, browser navigation, and tools that live on the local machine.

    The practical division: if the task needs to run at 3am when the laptop is sleeping, it’s a Routine. If the task needs to interact with local files, a browser session, or a Windows app, it’s Cowork.

    The Non-Developer Angle

    Neither of these capabilities requires you to be a developer to use. Routines are configured through the Cowork interface with natural language task descriptions and a schedule. Computer use activates through the same conversational interface you’re already using.

    The architecture underneath is sophisticated. The interface isn’t. You describe what you want done and when, and the system figures out the implementation. This is the progression that makes these capabilities meaningful for operations teams, executive assistants, knowledge workers, and small business owners — not just engineers building agent pipelines.

    Singapore’s Foreign Minister Balakrishnan built his own version of this on a Raspberry Pi. The point isn’t to build your own — it’s that the underlying architecture (persistent memory, scheduled tasks, multi-channel input) is now accessible at multiple layers of sophistication, from DIY open source to fully managed product.

    Frequently Asked Questions

    What are Cowork Routines?

    Cowork Routines are cloud-hosted scheduled tasks that run on Anthropic’s infrastructure regardless of whether your local Cowork laptop is on or available. They execute on a schedule you define — daily, weekly, or at specific times — and can perform any task Cowork handles: briefings, monitoring, content pipeline steps, report generation, and notification triggers. Each Routine reads its instructions from a Notion desk spec at runtime.

    Does Windows computer use require coding to set up?

    No. Computer use in Cowork activates through the standard conversational interface. You describe what you want Claude to do in the application, and Claude navigates the Windows desktop UI directly. No scripting, automation code, or API integration is required — though API integrations are faster when they exist. Computer use is the path for tools with no accessible API.

    What’s the difference between Cowork and Cowork Routines?

    Cowork runs on your local machine and requires the desktop app to be open and active. Routines run on cloud infrastructure and execute regardless of local hardware state. The practical division: tasks that need to run unattended on a schedule go to Routines; tasks that need local context, file access, or desktop UI interaction go to Cowork. Both read task instructions from Notion desk spec pages at runtime.

    Is Cowork available on both Mac and Windows?

    Yes. Cowork and computer use are available on both macOS and Windows as of the April 2026 general availability release. The Windows release also established PowerShell as the default shell (previously Git Bash was required), reducing a friction point for enterprise Windows shops.

  • Singapore’s Foreign Minister Built His Own Claude AI Second Brain — And Published the Blueprint

    Singapore’s Foreign Minister Built His Own Claude AI Second Brain — And Published the Blueprint

    Last refreshed: May 15, 2026

    On April 21, 2026, Singapore’s Foreign Minister Dr Vivian Balakrishnan published the architecture of his personal AI assistant on GitHub. He called it NanoClaw — “a second brain for a diplomat.” It runs on a Raspberry Pi 5. It costs roughly $80 in hardware and $5–20 a month in API fees. It connects to his WhatsApp, Gmail, and voice notes. It drafts speeches, runs scheduled briefings, and — unlike every standard chatbot — gets smarter over time because it maintains a structured knowledge graph that persists across sessions.

    His summary: “It answers every question, researches topics, provides daily updates, drafts speeches and condenses information. It has become invaluable — I don’t dare switch it off.”

    A sitting cabinet minister of a G20-adjacent nation just open-sourced his personal AI second brain on GitHub. That’s worth slowing down to look at.

    What NanoClaw Actually Is

    NanoClaw is built on four open-source components running on a Raspberry Pi 5:

    • NanoClaw (agent framework, built by developer Gavriel Cohen, 28k+ GitHub stars) — orchestrates Claude agents in isolated Docker containers. Each chat group gets its own sandboxed container.
    • Mnemon — the knowledge graph layer. Extracts discrete facts, insights, and style preferences from raw documents and conversations into a structured, retrievable graph database. Each entry is a self-contained statement, not a raw text chunk.
    • OneCLI — credential proxy.
    • Karpathy’s LLM Wiki pattern — the memory architecture that lets the system synthesize knowledge rather than just retrieve it.

    WhatsApp integration runs through Baileys, an open-source implementation of the WhatsApp Web protocol — no commercial API required. Voice notes are transcribed locally via Whisper.

    The full architecture is published at: gist.github.com/VivianBalakrishnan/a7d4eec3833baee4971a0ee54b08f322

    The Architecture Detail That Matters Most

    Standard chatbots are stateless. Each session starts from zero. The standard workaround is RAG — retrieval-augmented generation, which pulls chunks of raw text from a document store when they seem relevant. Balakrishnan’s system does something different. Mnemon’s Extract function pulls discrete facts and insights from raw documents into a graph database. Each entry is a self-contained, retrievable statement — not a text chunk.

    This is the same distinction that Anthropic’s Dreaming feature (announced May 6 for Managed Agents) is built on: the difference between storing raw experience and synthesizing it into structured knowledge. A system that synthesizes what it learns compounds in usefulness over time. One that just accumulates raw text doesn’t.

    Balakrishnan acknowledged this in a reply on his GitHub gist: “Local models will not give you the big context needed for digesting the memory graph, but will be good enough for querying it. You may want to use a bigger model that works well with a 128K token context at the very least.” He chose Claude specifically for the reasoning capability on the memory graph.

    He Built It With Claude Code, Not Traditional Coding

    This detail matters. Balakrishnan confirmed on X that he never used an IDE. Claude Code made all edits. His description of his own process: “No ‘vibe coding’. All I did was ‘tool assembly’ to create a utility that worked in my domain.”

    Tool assembly. That’s an important distinction. He didn’t write code — he assembled existing open-source tools using Claude as the implementation layer. A trained ophthalmologist and career diplomat, with no traditional software development background, built and deployed a production AI system running on commodity hardware by composing tools through Claude Code.

    His framing at the 17th Asia-Pacific Programme for Senior National Security Officers, the day he published NanoClaw: “AI agents have crossed a threshold I did not expect so soon. Not just impressive demos — but practical tools for daily use.” The audience was senior national security officials from across the Asia-Pacific region.

    Why This Is the Cowork Story in Miniature

    We run our own version of this — Claude operating scheduled tasks, content pipelines, and research workflows on our behalf through Cowork. The architecture Balakrishnan published is recognizably the same value proposition: persistent memory, multi-channel input, scheduled tasks, a system that improves over time.

    His total cost: ~$80 hardware, $5–20/month API. That’s a DIY Cowork running on a credit-card-sized computer on a diplomat’s desk in Singapore. The point isn’t that the price is better or worse than any specific product — it’s that the primitives are now accessible enough that a non-developer can assemble them into a working production system.

    His own thesis on why he published it: “Sharing the blueprint boosts the edge — the specific composition will be obsolete in months, but the builder’s ability to compose the right pieces is the durable advantage.” That’s as clean a statement of the AI-literacy case as we’ve seen from anyone, let alone a sitting foreign minister.

    The Broader Signal

    Singapore continues to be the most Claude-dense environment we track. The same week Balakrishnan published NanoClaw, a Claude Code meetup at Grab HQ drew 1,291 registrants. GIC (Singapore’s sovereign wealth fund) is a co-investor in Anthropic’s infrastructure JV. The country has institutional capital, developer community density, and now a sitting cabinet minister publishing working Claude architecture on GitHub. That triangle is unusual.

    Balakrishnan’s quote from the CNBC Converge Live fireside the day after publishing NanoClaw: “The diplomat who learns to work with AI will have a meaningful edge. I think that edge is now.” He wasn’t talking about chatbots. He was talking about a system running on his desk, integrated into his actual workflows, that he personally built and that he personally depends on.

    That’s a different kind of AI adoption signal than a press release about an enterprise partnership.

    Frequently Asked Questions

    What is NanoClaw?

    NanoClaw is an open-source Claude-powered personal AI assistant framework built by developer Gavriel Cohen. Singapore’s Foreign Minister Dr Vivian Balakrishnan published his own NanoClaw implementation on April 21, 2026 — a self-hosted assistant running on a Raspberry Pi 5 that connects to WhatsApp, Gmail, and voice notes, runs scheduled tasks, and maintains a persistent knowledge graph that grows smarter over time.

    How much does NanoClaw cost to run?

    Balakrishnan’s setup uses approximately $80 in hardware (Raspberry Pi 5) and roughly $5–20 per month in Anthropic API fees depending on usage volume. The software components (NanoClaw, Mnemon, OneCLI, Whisper, Baileys) are all open source. The full architecture is published at gist.github.com/VivianBalakrishnan/a7d4eec3833baee4971a0ee54b08f322.

    Did Vivian Balakrishnan write the code himself?

    He described his process as “tool assembly” rather than traditional coding — composing existing open-source components using Claude Code to handle implementation. He confirmed on X that he never used an IDE and that Claude Code made all edits. He has no traditional software development background; he’s a trained ophthalmologist and career diplomat.

    How is NanoClaw’s memory different from standard chatbot memory?

    Standard chatbots are stateless — each session starts from zero. NanoClaw uses Mnemon, a knowledge graph that extracts discrete facts and insights from conversations and documents into structured, retrievable entries. The system synthesizes knowledge rather than just storing raw text, meaning it compounds in usefulness over time rather than simply accumulating history.

  • Claude Dreaming Explained: Why AI Agents That Learn Between Sessions Change the Game

    Claude Dreaming Explained: Why AI Agents That Learn Between Sessions Change the Game

    Last refreshed: May 15, 2026

    At the Code with Claude conference on May 6, Anthropic announced a Managed Agents feature called Dreaming. The press covered it briefly — VentureBeat, 9to5Mac — but mostly as a developer story. The Harvey result (a legal AI company reporting roughly a 6× task completion rate increase) was cited but not unpacked. This is the non-developer version of that story, written for people who run workflows, manage operations, or use Claude professionally without writing code.

    What Dreaming Actually Does

    Here’s the mechanism in plain terms. Normally, when an AI agent finishes a session, it’s done. Whatever it learned — the patterns it noticed, the decisions it made, the context that turned out to matter — stays in that session and disappears when the session closes. The next session starts fresh.

    Dreaming changes that. After a session ends, the agent reviews what happened: it reads its own memory store alongside the session transcripts and produces a new, improved version of its memory. Duplicates are merged. Stale information is replaced. New patterns that emerged from the session get incorporated. The next session doesn’t start from scratch — it starts from a richer, more accurate knowledge base.

    The Anthropic documentation describes it this way: a dream reads an existing memory store alongside past session transcripts, then produces a new reorganized memory store with insights no single session could see alone. Docs: platform.claude.com/docs/en/managed-agents/dreams.

    This is a developer-layer feature — it requires implementation, not just subscribing to a plan. But understanding what it does helps you ask the right questions about the tools you’re evaluating and the agents you’re eventually going to run.

    Why Harvey’s 6× Result Is the Right Hook

    Harvey is a legal AI company. Their workflows are exactly the kind of work where this matters: complex research tasks that span multiple sessions, with context that compounds over time. A lawyer doesn’t approach a new matter without the knowledge they’ve accumulated from previous matters. Historically, AI agents did. Each new session was a blank slate.

    Harvey reported roughly a 6× task completion rate increase after implementing Dreaming. That’s not a benchmark number from a controlled test — it’s a production system showing measurable improvement from session-to-session memory refinement. The mechanism is the same as how human expertise compounds: not by accumulating raw experience, but by periodically synthesizing and reorganizing what’s been learned.

    Whether 6× holds across every use case is unknown. The direction of the effect is the signal. Agents that improve between sessions outperform agents that don’t. That gap widens over time.

    The Cowork Parallel

    We run our own Cowork setup — Claude operating scheduled tasks, content pipelines, and site management workflows on our behalf. The Dreaming announcement is relevant to us not because we’re going to implement it today (it’s developer preview, invitation-only access), but because it’s the roadmap signal for where agentic AI is heading.

    The systems we’re building now — Cowork routines, scheduled tasks, skill libraries — are the foundation that Dreaming-style memory will eventually sit on top of. Agents that accumulate context across sessions. Workflows that get better at your job the more you run them. That’s the direction. The Harvey result is the first public production evidence that the direction is real.

    What This Looks Like for Non-Developer Workflows

    Dreaming isn’t in consumer Claude products yet — it’s a developer preview. But the pattern it represents is worth thinking about now for anyone who uses AI in recurring work:

    • Legal and compliance work: Each matter builds on prior matter context. An agent that synthesizes what it learned from 50 prior research sessions before starting the 51st is doing something closer to what an experienced associate does.
    • Operations and project management: Recurring status meetings, weekly reports, vendor communication — these have patterns. An agent that notices “the Friday report always needs these three data sources” and incorporates that into its working memory doesn’t need to be told again.
    • Content and editorial work: Our own content pipeline is a clear example. Style preferences, site-specific constraints, recurring topic clusters — knowledge that currently lives in skill files and desk specs. Dreaming is the mechanism that would let an agent accumulate and refine that knowledge from session experience rather than requiring it to be manually specified.
    • Customer-facing workflows: Agents that handle recurring customer interactions and improve their response quality based on what worked in prior sessions — without a human having to manually update a prompt each time something changes.

    Current Access Status

    To be direct about where this stands today:

    • Dreaming: Developer preview only. Invitation-based access. Not available in claude.ai or any subscription tier.
    • Multiagent Orchestration: Public beta. Available via the Claude API.
    • Outcomes: Public beta. Available via the Claude API.

    If you’re not a developer implementing your own Claude agents, Dreaming isn’t something you can use yet. It will become relevant when it moves to GA and when products built on top of it surface in tools you already use. The Harvey result is the preview of what those products will eventually be able to do.

    Our Take

    The briefing note we wrote when this story broke said: “Dreaming is the story the press mostly missed.” The Harvey 6× result landed in VentureBeat but was treated as a developer-tier data point. We think it’s more broadly significant than that.

    What makes expertise valuable isn’t the accumulation of raw information — it’s the synthesis. A junior lawyer with access to the same case law as a senior partner isn’t equally useful, because the senior partner has synthesized 20 years of patterns into a working model that guides their reasoning. Dreaming is Anthropic’s attempt to give agents a version of that synthesis capability. It’s early, it’s developer preview, and the 6× figure is from one company’s specific workflow. But the direction is clear, and it’s the right direction.

    For anyone building with Claude or evaluating where agentic AI is heading: this is the development worth tracking most closely from the May 6 announcement. Not the SpaceX rate limits (immediately useful), not the Managed Agents public beta (available now), but Dreaming — because it’s the piece that changes the fundamental model of how AI agents improve over time.

    Frequently Asked Questions

    What is Claude Dreaming?

    Dreaming is a Claude Managed Agents feature (developer preview as of May 2026) that lets AI agents review and reorganize their own memory between sessions. After a session ends, the agent reads its memory store alongside session transcripts and produces an improved memory store — merging duplicates, replacing stale information, and surfacing patterns from the session. The next session starts with a richer knowledge base than the previous one ended with.

    What did Harvey report about Dreaming?

    Harvey, a legal AI company, reported roughly a 6× task completion rate increase after implementing Dreaming in their Managed Agents workflow. Harvey’s use case involves complex legal research spanning multiple sessions — exactly the kind of work where session-to-session memory improvement has the highest value.

    Can I use Dreaming in claude.ai?

    No. As of May 2026, Dreaming is a developer preview available only to selected developers implementing their own Claude agents via the Anthropic API. It is not available in the claude.ai interface or through any subscription tier.

    How is Dreaming different from Claude’s memory feature in claude.ai?

    Claude’s memory feature in claude.ai extracts key facts from conversations and injects them into future sessions as a summary. Dreaming is a more sophisticated agent-layer system where the agent itself reviews and reorganizes its full memory store and session history, producing a restructured knowledge base — not just a collection of extracted facts. They serve different purposes at different layers of the stack.

    When will Dreaming be available to non-developers?

    Anthropic hasn’t announced a GA timeline for Dreaming. It will likely surface in consumer and professional products after the developer preview phase completes and the implementation patterns are well understood. Harvey’s result suggests the mechanism works in production; the path to broader availability depends on how Anthropic packages it for non-developer deployment.

  • AI for Moving Companies: Free Claude Skills and Prompts

    AI for Moving Companies: Free Claude Skills and Prompts

    Last refreshed: May 15, 2026

    Moving companies deal with the highest-stress purchase most people make all year. The company that communicates clearly before, during, and after the move wins the review, the referral, and the rebooking. Claude handles the communication layer. Everything here is free.

    How to Use This Page

    Claude Skills go into Claude Project Instructions. Books for Bots are PDFs you upload to Claude Projects. Prompts work in any Claude conversation.

    Claude Skills for Moving Companies

    Skill 1: Quote Follow-Up and Booking Writer

    Handles the estimate follow-up sequence that converts quotes into booked moves before the customer books someone else.

    Paste into Claude Project Instructions:

    You are a sales communication assistant for a moving company.

When I describe a pending quote situation, produce:

DAY 2 FOLLOW-UP: Friendly check-in. Any questions about the estimate? We're here to help. Under 75 words.

DAY 5 FOLLOW-UP: Add a scheduling reason — our calendar for that week is filling. One clear call to action. Under 75 words.

DAY 10 FINAL TOUCH: Leave the door open. No pressure. Under 60 words.

BOOKING CONFIRMATION: They've booked. Confirm all details, what to expect next, who to contact with changes. Organized and warm. Under 150 words.

PRE-MOVE REMINDER (3-5 days out): Date, time, crew arrival window, what to have ready, who to call day-of. Clear and practical. Under 150 words.

Tone: helpful and reliable. Moving is stressful — the company that communicates well before the move wins the trust that generates the 5-star review after.

    Skill 2: Claims and Complaint Communication Writer

    Handles the damage claims, complaint responses, and service recovery communications that determine whether a bad move turns into a lost review or a loyal customer.

    Paste into Claude Project Instructions:

    You are a customer resolution assistant for a moving company.

When I describe a complaint or claim situation, produce:

DAMAGE CLAIM ACKNOWLEDGMENT: We received their claim. Here's what happens next, timeline, who they'll hear from. Under 100 words. No admission of liability.

CLAIM RESPONSE: What we found, what we're offering, next steps. Factual, fair, professional. Under 150 words.

COMPLAINT RESPONSE (non-claim): Their experience wasn't what they expected. Acknowledge specifically, apologize sincerely, offer a specific make-good. Under 150 words.

ESCALATION FOLLOW-UP: They're still unhappy. We want to make this right. What we're offering. Final offer framing. Under 100 words.

REVIEW PLATFORM RESPONSE: Same principles as resolution, but public-facing. Under 100 words. No defensiveness. Invite them to call.

Tone: responsible and fair. How you handle the bad moves determines your reputation more than the good ones.

    Skill 3: Review and Referral Writer

    Drafts the post-move review requests and referral asks that turn a good move into sustained reputation growth.

    Paste into Claude Project Instructions:

    You are a reputation and referral assistant for a moving company.

When I describe a completed move, produce:

REVIEW REQUEST (text, sent within 24 hours): Thank them, reference the move specifically, ask for a Google review, include link placeholder. Under 75 words. One ask.

REVIEW REQUEST (email follow-up, 48 hours): Slightly warmer version. Reference anything specific about the move. Under 100 words.

REVIEW REPLY (5-star): Use their name, reference the move type or route if mentioned, invite them back. Under 60 words.

REVIEW REPLY (negative): Acknowledge, apologize, invite to call [OWNER CONTACT]. No arguments. Under 75 words.

REFERRAL ASK: To someone who had a great move. Genuine, brief, specific about who we help. Under 80 words.

Tone: grateful and professional. Moving reviews drive more business than almost any other marketing.

    Skill 4: Corporate and Commercial Account Communication

    Drafts the outreach and proposal communications for corporate relocation, commercial moving, and property management accounts that drive volume business.

    Paste into Claude Project Instructions:

    You are a B2B communication assistant for a moving company.

When I describe a commercial opportunity, produce:

CORPORATE HR OUTREACH: Introduce us as a preferred relocation partner. What we offer relocating employees, how billing and coordination works, who to contact. Under 125 words.

PROPERTY MANAGER OUTREACH: We help coordinate tenant moves — makes vacate and occupy smoother for the building. What we offer. Under 100 words.

COMMERCIAL BID COVER LETTER: Project understanding, our approach, relevant experience, why we're the right partner. Under 200 words.

ACCOUNT FOLLOW-UP: After a corporate move or first commercial job. How did it go, how can we serve this account better, what else we offer. Under 100 words.

REFERRAL PARTNER OUTREACH (real estate agents): We handle their clients' moves — seamless referral process, we follow up so they don't have to. Under 100 words.

Tone: professional and service-oriented. Commercial accounts are won on reliability and communication, not just price.

    Books for Bots

    PDFs coming soon. Email will@tygartmedia.com to get on the list.

    Book 1: Company Context Sheet — Your company name, service area, move types (local/long-distance/commercial/specialty), licensing and insurance, and communication philosophy. Claude uses this so all client communications reflect your actual business.

    Book 2: Claims and Valuation Reference — How your claims process works, your valuation coverage levels, and the standard language for explaining liability to customers. Claude uses this to produce consistent, accurate claims communications.

    Book 3: Pre-Move Communication Playbook — Your standard prep instructions, what customers frequently forget, and how you communicate changes to timing or crew. Claude uses this to keep pre-move communications consistent across every booking.

    Ready-to-Use Prompts

    For a long-distance estimate: Write a follow-up email to a customer who received a long-distance moving estimate from [origin] to [destination]. They haven’t responded in 5 days. Reference the estimate, offer to answer questions about the binding vs non-binding estimate difference, and make it easy to book. Under 125 words.

    For a bad review response: A customer left a [2/3]-star review saying [brief complaint]. Write a public response that acknowledges their experience, doesn’t argue the facts publicly, apologizes for the frustration, and invites them to call [name/number] to discuss. Under 90 words.

    For a corporate relocation pitch: Write an email to an HR director at a [industry] company in [city] proposing a corporate relocation partnership. Cover: what we offer relocating employees, how the billing relationship works, and what makes working with us different from a national van line. Under 150 words.

    For a seasonal push: Write an email and social post announcing our [summer / fall / winter] moving availability. Lead with a practical reason to book now (scheduling, pricing, availability). Under 100 words each. Not desperate — just timely.

    Free. Custom moving company builds at tygartmedia.com/systems/operating-layer/.