In partnership with
If you've spent years organizing your notes, building databases, and refining how you capture and retrieve knowledge—congratulations. You've been training for this moment without knowing it.
AI agents are everywhere right now. But here's what most people miss: the teams and individuals who are deeply invested in personal knowledge management are the ones best positioned to actually make agents work.
Not because they're more technical. Because they've already built the foundation agents need to perform.
Think about it. An AI agent is only as good as the context it can access.
If your knowledge lives in scattered docs, random Slack threads, and half-finished notes, your agent is flying blind. But if you've been intentional about how you structure information—clear databases, consistent tagging, well-organized pages—you've essentially built the operating system that agents plug into.
This week's digest is all about that intersection: knowledge management as the launchpad for AI agents. The articles below explore why this matters, what's changing, and how to start building systems that get smarter over time.
Let's get into it.
Want to get the most out of ChatGPT?
ChatGPT is a superpower if you know how to use it correctly.
Discover how HubSpot's guide to AI can elevate both your productivity and creativity to get more things done.
Learn to automate tasks, enhance decision-making, and foster innovation with the power of AI.
🔥 The Big Picture: Knowledge Management Meets AI Agents
This blog post created quite a stir on X. A viral essay arguing we've crossed a major AI threshold. After GPT-5.3 Codex and Claude Opus 4.6 both dropped on February 5th, Matt Shumer reports no longer being needed for technical work—AI now builds complete apps autonomously with judgment and taste.
Some (including myself) think it’s a little hyperbolic, but it’s undeniable that change is accelerating.
Ev Chapman gave her AI "Chief of Staff" its own Personal Knowledge System—Daily Notes, Working Patterns, Decision Log, and Threads—to solve context loss between conversations. Sound familiar? It's the same architecture we use for our own second brains! The takeaway is powerful: if you already maintain a personal knowledge system, you already understand how to build one for an AI agent. The skills transfer directly.
Speaking of second brains, Tiago Forte gives a clean breakdown of the key differences between Anthropic's two browser-controlling AI tools.
While Cowork offers zero-setup ease within the Claude desktop app, Claude Code delivers superior speed, reliability, and token efficiency through direct HTML reading rather than screenshot-based navigation. Start with Cowork to explore possibilities, then level up to Claude Code for complex workflows.
🤖 Going AI Native
Peter Yang's practical roadmap from AI novice to building personal agents. The standout insight: 80% of AI's value comes from Level 2 tools (voice dictation, meeting notes, projects). For those of us already capturing and organizing this information, we're not starting from scratch—we're starting from a position of strength. The gap between "organized knowledge worker" and "AI-native operator" is smaller than you think.
Experimental features that could transform Notion from a workspace into an orchestration layer for your entire tool stack. The leaked screenshots show scripting configuration and "Workers" capabilities that would let agents connect to external services like GitHub, Slack, and calendars. The real breakthrough? AI that writes the scripts for you based on plain language descriptions—making cross-platform automation accessible to everyone, not just developers.
Our upcoming session breaks down the real difference between Notion AI (great for quick answers) and Custom Agents (where the real work happens). It covers practical tips for building agents that actually perform, plus a preview of advanced features like Slack integrations, automation triggers, and workflow orchestration. A must-attend if I don’t say so myself. 😉
Ever finish a meeting with a great list of action items... only to forget about them until the next check-in? Same. In my latest video, I walk through how to set up a custom agent that automatically pulls tasks from your meeting notes and adds them straight to your task database—complete with project relations and due dates.
No more copy-pasting. No more things slipping through the cracks.
I cover how to structure your instructions page, configure triggers so the agent runs when you mark a meeting as done, and even set up notifications so your team knows when new tasks land.
Our upcoming session breaks down the real difference between Notion AI (great for quick answers) and Custom Agents (where the real work happens). It covers practical tips for building agents that actually perform, plus a preview of advanced features like Slack integrations, automation triggers, and workflow orchestration. A must-attend if I don’t say so myself. 😉
Final thoughts
Here's the thread connecting all of this: AI is moving from "tools you use" to "role-players that work with you."
Honestly, I started this newsletter to talk about practical productivity, but the level at which AI has enabled not only more productivity, but the ability to go deeper on important topics…it’s insane.
Whether it's agents that maintain their own knowledge systems, models that help build the next version of themselves, or Notion (maybe) rolling out features that turn workspaces into orchestration layers—we're watching the infrastructure of knowledge work get rebuilt in real time.
The founders and teams who'll thrive aren't the ones waiting for the perfect tool. They're the ones experimenting now, building systems that grow smarter over time, and treating AI as a collaborator rather than a search bar.
Start small. Pick a workflow. Hand it to an agent. Optimize. Repeat.
That's what I'm doing at least…I'll keep sharing what I learn along the way!
Until next time, Dave
ps. if you’ve noticed a different look, it’s because we’ve moved to Beehiiv!
