Agent capacity is cheap now and getting cheaper; my attention is the fixed, scarce resource. Everything I build is attention-budget design: the autonomy…

I replaced my portrait-centered homepage hero with the Mind on Fire mark rendered as living pixels, surrounded by every essay I've published as clickable constellations. Here's why, how it works, and the ember easter egg.

I replaced my portrait-centered homepage hero with the Mind on Fire mark rendered as living pixels, surrounded by every essay I've published as clickable constellations. Here's why, how it works, and the ember easter egg.

I run two AI agents — Claude Code for infrastructure, Hermes for content — both controlled from my phone. Here's the split-brain architecture and why separation of concerns matters for AI agents too.

A year ago at WorkOS nobody could get a single Devin AI session working. We abandoned it. Now Devin AI is one of our most-used agents in Slack — shipping PRs, fixing bugs, running data queries. And I'm using Devin AI to write blog posts with pixel art and three.js animations.

You have about ten seconds to wow your user and convince them you're already solving their problem. The model, the stack, the architecture — none of it matters if the door is wrong. Time-to-value is the moat now.

I went from blacking out on stage in front of 4,000 engineers to sleeping fine before jet-lagged days of talks abroad. Here's the whole pile of crumbs that got me there — medication, mindset, slides, reps, and putting your talks online.

My rule for AI agents: anything reversible runs unattended, anything irreversible or outbound stops for a human. Here is how I drew that one line across three bots and enforced it in code, not willpower.

I reviewed Vercel's eve agent framework by building a real three-agent business team for my site — content, ops, and growth bots that deploy to Vercel and collaborate over Slack and eve channels. The friction is part of the review.

A stranger online said AI made him suspicious of all writing — that he now interrogates every sentence asking whether a machine wrote it. That's the wrong question. On craft in the era of AI, and why I'm still the spark, the bellows, and the quench.

The unit of useful agent work is a reviewable artifact — a PR, a draft, a diff — not a chat reply. A chat reply evaporates. A PR sits in a queue with your name on it until you decide. Here's why I build agents that hand me coals, using my own blog bot as the worked example.

Before a draft reaches me, my blog bot hands it to two cold readers from different model families that score it against a rubric and force a revision loop. The implementation, the gate, and a real pass where it caught my own AI tell.

What my AI inbox-screener actually does to the templated cold outreach hitting my inbox. Three real auto-sends, the footer that draws the line, and where this goes next.

Join 4,000+ engineers getting weekly insights on AI engineering, RAG pipelines, developer tools, and building with LLMs.