Writing
Field notes on agentic engineering — harnesses, orchestration, and what it's like to stop reading your own code.
Teaching the Factory to Pick Its Own Tools
My AI dev platform was choosing models with a regex. A $54 accounting bug, one research paper, and a morning of planning later, Composer is building its own complexity-aware model router. Here's the design.
In Memory of Lucy
A poem for my beloved dog Lucy
The Inverse Architecture: Building the System That Builds the Systems
Four months ago I introduced Composer, my AI software factory. Since then it's shipped 642 pull requests for about $4K — and I've stopped reading the code. Here's the architecture everyone else is chasing backwards.
Hold It Loosely: What AI Is Teaching Me About Letting Go
After 30 years in software, I'd built my identity on the things I made. AI is teaching me to hold them loosely — to build, ship, and let go — because the half-life of cleverness has never been shorter.
Trust, but Verify: Letting AI Drive a Production Migration
Over four days, Claude rebuilt Leaderboard's entire golf data pipeline onto a new provider — new API client, a re-keyed production database, a zero-downtime cutover. I barely wrote a line. My job was to challenge every step, and a few times that's exactly what saved it.
How I Accidentally Used Claude as a Backup System
My autonomous agent platform marked a task DONE but never opened the PR — and then the worktree got cleaned up, taking 1,300 lines of validated work with it. Except it wasn't gone. Claude had been keeping a backup I never asked for.
Three Coding Agents, One Spec, and What I Actually Learned
I handed the same brief — build an interactive Go tutorial — to three different coding agents (Claude Opus 4.7, Gemini, GLM-5.1) and ran them side-by-side. Here's what the comparison actually shows.
19 Days, 239 Commits, and One Lesson in Restraint
I hadn't built a mobile app since the Objective-C days. With AI writing nearly all the code, I went from an empty scaffold to app-store-ready in 19 days. The hardest part wasn't building — it was knowing when to stop.
My Remote Agent Experiment: From Cloud Agents to My Own AI Dev Team
OpenClaw didn't work out. Cloud agents frustrated me. So I built my own orchestration platform — six AI agents that design, review, build, test, and document code while I sleep. Here's the story of Composer.
When AI Plays Your Cards
I built an AI poker tutor with two LLM-powered agents — one plays against you, the other coaches you. Here's the story of building The Nut, and what it taught me about where AI actually belongs in a game.
My Remote Agent Experiment: OpenClaw, Honest Results, and a Plot Twist from Anthropic
I set up a dedicated M4 Mac Mini running OpenClaw as a remote coding agent — isolated network, its own Apple ID, Slack interface. The vision was beautiful. The results were not. Then Anthropic announced exactly what I actually needed.
Getting Started with Agentic Dev — Part 1: Your Toolkit
Part 1 of a 3-part series on getting started with agentic software development. Everything you need to install and configure to start working with AI coding agents.