Building the systems
that build the software.
I spent three decades building and operating software. Now I design the workflows that let AI agents build it: specifications, review loops, and checks before anything reaches production. I write about what works, what breaks, and where human judgment still matters.
02 — Start here
Three field notes on building with agents, checking their work, and knowing when to stop.
How I build
Why I built Composer to coordinate specialized coding agents through design, implementation, and review.
How I verify
What I caught during an AI-built production migration, and why a configuration flag was not a rollback plan.
When I stop
What building a mobile app with AI taught me about scope, restraint, and deciding when it was ready.
03 — Latest
ALL 33 POSTS →
The Finish Line Keeps Moving
Before TutorPro's soft launch, I had agents rebuild its help center from the source code. They found a tutor who couldn't accept a parent's request while 13,758 tests passed, and every pass since has found more. Quality is still the hard part of agentic development, and I want your ideas for closing the gap.
04 — Selected work
ALL PROJECTS →
Composer
A work queue and orchestration platform that coordinates specialized AI agents through design, implementation, testing, and review.
TutorPro
Tutoring management software for scheduling sessions, managing student records, and communicating with parents and students.
Leaderboard Fantasy
A fantasy golf platform for running contests, managing rosters, and tracking tournament scores.
05 — Off the clock
PERSONAL POSTS →
Husband, father, and the family's on-call network engineer. When I'm not tuning agent definitions I'm fishing, golfing, or dominating at Mario Kart. More about that →