Agentic Systems

1. Which Expertise Carries Forward?

   Platform shifts change which parts of experience remain useful. AI gives delegation and delivery experience another application: making work repeatable without losing the ability to judge it.

   Nov 12, 20266 min read

2. The Hire Who Never Remembers

   People keep asking what kind of person is good at AI. My bet is a skill instead: the written half of management, the only half that reaches an agent's next session.

   Oct 19, 20268 min read

3. There's No Replicator Yet

   An AI agent did nearly all of a family member's data entry, missed one or two items, and almost got written off. All-or-nothing is a replicator's bar, and nothing I use with AI clears it yet.

   Oct 14, 20266 min read

4. Making club videos without opening a video editor

   Our club-video work moved from hand editing in CapCut to agent-authored HyperFrames compositions and automated renders. The finished campaign shows what changed—and what still needed a person.

   Oct 10, 20266 min read

5. The Connector You Can't OAuth

   I asked the new Siri what it could infer from a week of texts. The answer was not a better chatbot. It was inference over a graph no OAuth connector gets.

   Sep 15, 20267 min read

6. Who Is Still Driving?

   Using AI takes practice, but a product that needs an expert to catch its mistakes should say so before someone relies on it.

   Sep 6, 20264 min read

7. Rigorous About the Wrong Question

   I asked an AI agent to audit my app for the person it was built for. It sent five sub-agents to check documents and none of them looked at the screen.

   Sep 3, 20267 min read

8. The Audit Reproduced the Failure

   A small inspection of one runaway session became repeated parallel work before it had earned that expansion. The 119-of-118 report was the alarm.

   Aug 23, 20267 min read

9. Nobody Owns What the Agent Leaves Running

   My machine ran out of resources, so I handed an agent four screenshots and typed one word: fix. It did a good job. A day later, twenty-two connector processes were still running, every one of them marked disabled in config. Nothing had failed — and that turns out to be the interesting part.

   Aug 23, 20267 min read

10. Everything I Was Afraid of Worked

    Last October I published a post arguing that agent safety is an architecture problem: the model proposes, hard-coded code disposes, a human approves. Then I built exactly that for a youth sports club's website and used it for an hour. I found seven things wrong with it. None of them were in the part I had been afraid of.

    Aug 17, 202611 min read

11. The Agent Needs a Safety Label

    AI standards already exist. What teams still need is a current, workflow-level record of what one configured agent may do, how it was tested, where it must stop, and when its evidence expires.

    Aug 13, 20268 min read

12. The Loudest Voice in My Voice Corpus Isn't Mine

    A pipeline mines my agent sessions into a character sheet that gets loaded as context. The top-ranked correction in it is a deny message from a hook I installed, quoted back at me across 117 sessions.

    Aug 7, 20267 min read

13. The Cut You'll Make Twice

    A written rule is not a control until the system has a place to enforce it and a failure record that proves what happened.

    Aug 6, 20266 min read

14. One Component I Didn't Already Have

    A coding-agent plugin with 66,000 stars keeps landing in my inbox. The version that could actually run on my machine ships eight components. Seven of them my setup already does, can't use, or would pay for twice.

    Jul 31, 20266 min read

15. Please Only Apply If You're an AI Agent

    Firecrawl posted a job only a machine could apply for. Months later, on a different stage, an engineer said the mirror-image thing: don't build me an agent, build my agent a way in. Same shift, two ends of the same transaction — and an economics paper that almost, but doesn't quite, tie them together.

    Jul 14, 20269 min read

16. The Migration That Ate Two Columns

    I rebuilt a database table and it silently deleted two columns I needed. No error. Every test for the thing I was changing passed. Here's what actually caught it.

    Jun 16, 20264 min read

17. Red Is the Good News

    Three bugs that would have shipped clean. None of them threw an error. The only thing that caught them was a test written to fail first, against the real thing.

    Jun 16, 20265 min read

18. I Wrote the Rule Down. I Broke It Anyway.

    There's a file in my project whose only job is to stop me from making one mistake. I made it three times in a row. The difference between a rule and a wall.

    Jun 16, 20264 min read

19. The Gate Verifies the Work. It Never Looks at the Plan.

    Thirteen features shipped green. The designs were all wrong. The system made being wrong cheap—but only on one side of the work.

    Jun 16, 20265 min read

20. Where the API Stops

    I once mapped the civil war between human interfaces and machine-native ones at the scale of companies. Then I fought both sides of it in a single afternoon, in a single pipeline — and a human had to close the seam.

    Jun 15, 20269 min read

21. Open Kitchen

    I went looking for other cooks and found closed kitchens — not hostile, just complete. The Bear turned out to be the show that named what's actually missing in agent-assisted work, and what it might cost me to build the alternative.

    Jun 11, 20266 min read

22. The A/B Test That Built the Lathe

    I pasted a two-paragraph plan into a terminal and walked away for two days. The strategy package that came back was good. Then I asked Claude to do it again from a template, without me in the feedback loop. The template version landed at 70-80% of the quality in 10-15x less time. The gap — and the loop that closed it — has a name from another century.

    May 24, 20269 min read

23. The Scaffolding the Agent Doesn't Build

    I sent Adam Bender's Google I/O talk to Claude with a note calling it the most insightful take I'd heard on AI and our industry, and asked for a LinkedIn caption. The draft came back confessing things about my work that weren't true. The story of why is the same story Bender is telling on a Google I/O stage.

    May 24, 20266 min read

24. I Don't Write Any Code

    I spent a session trying to map my skills across sixty-five projects and the output came back dressed up as a senior engineer. That wasn't right. The correction I typed back is the one I think a lot of people are currently refusing to type back.

    Apr 21, 20266 min read

25. Skip the Steps

    Supabase added a 'Copy prompt' button that bypasses their entire setup guide. It's a small UI change that reveals a big design shift — and it pushed me from 'context engineering' to 'probability engineering' as the real frame for agent-native tooling.

    Mar 25, 202610 min read

26. The Cart Is a Protocol Now

    Etsy and Wayfair are already processing agentic checkout through Google's Universal Commerce Protocol. OpenAI and Stripe shipped a competing one. Cart and checkout are becoming infrastructure services — and the standards war is already here.

    Mar 19, 20269 min read

27. The 48-Hour Artifact

    I pointed an AI agent at a product initiative and didn't write a single line of code or a single word of copy. Two days later: 11 prototype pages, 4 strategic documents, cross-industry research with 30+ citations. And a trust problem I still can't solve.

    Mar 16, 202611 min read

28. Can vs. Should

    I've been asking 'can an agent do this?' so reflexively that I stopped noticing when the answer should have been 'but should it?'

    Mar 7, 20269 min read

29. What If the Fork Is the Problem?

    I just mapped the civil war inside every agent system. Both paths sound reasonable. But what if splitting investment across both means neither gets finished?

    Mar 1, 20268 min read

30. The Civil War Inside Every Agent

    Every agent system is fighting the same battle: learn to navigate human interfaces, or demand native ones. The industry is doing both. The question is who adapts to whom.

    Mar 1, 20267 min read

31. From Aegis to SpecChain: When Governance Meets Reality

    I built a Constitutional AI Governance Framework. Thirteen articles. HMAC attestations. Democratic amendment processes. Every validation function returned hardcoded perfection. The governance thinking was real. The code was theater. Here's what survived the extraction.

    Feb 21, 20269 min read

32. Two Doors for Agents

    GitHub wants agents to explore. Google wants websites to hand them a menu. Two competing philosophies for the same problem—and the one you start with will shape your migration cost when they inevitably converge.

    Feb 18, 20267 min read

33. From Research Paper to Working Toolkit in One Session

    I had a 46-citation research paper about autonomous documentation. Academic frameworks rarely survive contact with a real codebase. So I asked an agent to turn theory into working code—and watched what happened.

    Feb 4, 20267 min read

34. Spec-Driven Development with Multi-Agent Orchestration

    The problem with AI coding assistants isn't capability—it's coordination. A single agent can write code. But who checks the work? Who remembers what was decided? I built a system where specialists implement and verifiers catch drift.

    Feb 4, 20267 min read

35. When the Voice Guide Becomes the Problem

    I wrote a voice guide to help AI match my writing style. It worked too well—the AI learned the example phrases, not the principles behind them. Here's how I fixed it, and what it taught me about the difference between describing a voice and understanding one.

    Jan 21, 20265 min read

36. The Graveyard

    How many ideas die in the space between waking and coffee? Vercel's Agent Skills announcement made me think about what changes when engineering judgment becomes installable—and who gets to build things when the execution gap narrows.

    Jan 21, 20264 min read

37. The AI Analyst

    We're not short on people who can chat with a bot. We're starved for people who can deconstruct a business process into atomic units an AI can actually execute. That gap has a name now.

    Jan 12, 20269 min read

38. The Agentic Student

    College students aren't just using AI chatbots anymore. They're building automation systems, running local LLMs, and treating software engineering as a just-in-time capability. The 'Chat Terminal' era is over.

    Jan 10, 20266 min read

39. No Room for Tourists

    Wade Foster doesn't send memos about AI. He runs hackathons and show-and-tells. That distinction matters more than most CEOs realize—and it's the same thing I've been telling my own teams.

    Jan 5, 20269 min read

40. The Storefront That Builds Itself

    Every e-commerce platform is racing to add AI features. But what if the real opportunity isn't AI features—it's AI architecture? What if the store itself could generate in real-time?

    Dec 3, 20256 min read

41. It's the Artist, Not the Pen

    If I handed you my camera right now—same lens, same settings, same light—would you get the same shot? The tools are available to everyone. The output isn't.

    Nov 27, 20254 min read

42. One More Version

    I used to say 'just one more level' until 3am. Now I say 'just one more version.' The game changed. The compulsion didn't.

    Nov 27, 20254 min read

43. Thankful for My Robot Army

    It's Thanksgiving. And while I'm grateful for the usual things—family, health, increasingly creative leftover sandwiches—I need to take a moment to thank the team that really made this year possible. They don't eat. They don't sleep. And they never ask for PTO.

    Nov 27, 20253 min read

44. My AI Agents Have Rules. They Break Them. So I Built a Cop.

    Instructions arent enough. To make agentic workflows reliable, I had to build a meta-agent to police my coding agents. Welcome to the unglamorous world of AI Ops.

    Oct 28, 20254 min read

45. I Don't Trust My AI Agents, So I Build Them Cages

    Agentic software is powerful, but it needs guardrails. Im finding the most important work isn't coding, but architecting the systems that constrain the code.

    Oct 26, 20254 min read

Looking beyond essays? Search all writing