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.
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.
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.
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.
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.
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.
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.
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.
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.
Announcing AI Labs, a personal portfolio of AI experiments built for learning, tinkering, and sharing knowledge the way the web was meant to work.
How migrating from a hand-rolled AI tool-calling system to Spring AI 1.1's native tool support cut our orchestration code nearly in half—and made adding new capabilities trivial.
How I migrated Leaderboard Fantasy from GCP to a VPS, moved from GitLab to GitHub, and set up automated backups—all in about 7 hours with Claude Code as my DevOps partner.
A quick tip for Claude Code users: add a custom statusline hook to see model info, API limits, context usage, and git branch at a glance.
How a 26-year veteran developer went from vibe coding to orchestrating AI agents—and shipped 367,000 lines of code across two platforms in eight months. A reflection on growth, process, and why experience still matters in the age of AI.
How I orchestrate cloud agents, local agents, and git worktrees to tackle multiple GitHub issues in parallel—and why spreading the load across compute environments has changed how I think about velocity.
How a custom Claude Code spec-writer command, wired into GitHub CLI and a wall of standards, lets me turn vague feature ideas into precise, 3–8 hour GitHub issues at high velocity.
My evolution from using basic AI coding assistants to orchestrating a full cloud and local AI agent workflow that's producing software at 10-20x my professional pace.
How AI coding agents like Claude Code, Codex, and Warp have accelerated my development workflow and helped me build Leaderboard Fantasy faster than ever before.
A step-by-step guide to deploying Spring Boot applications to Google App Engine. From zero to production with gcloud app deploy.