29 Oct 2026
How I run development with a coding agent
How I direct a coding agent before implementation, review its product checks and maintain the tools around it, with seven months of session logs and a proposed next step for a team.
Blog
RSS feedThe engineering decisions behind production systems — the tradeoffs, not the buzzwords.
20 Aug 2026
How I stopped re-explaining the project to every AI agent
Decisions lived in chats, then in two docs folders, then in one knowledge base that Claude Code searches by meaning. The episode that convinced me, and the rule that came with it: a found note is a claim, not a fact.
26 Jul 2026
Four AI reviewers, one schema, and a fix I reverted
I had four models audit the same Prisma schema twice each, verified every claim by script, and still implemented a critical finding the application had already solved. What eight AI reviews are good for, and what they are not.
05 Jul 2026
Mapping a legacy Prisma schema without reliable telemetry
More than 150 models, legacy pages still in production, and traffic data I could not trust. How I worked out which models a limited set of functions actually depends on, where the script needed a human, and what the result does not prove.
15 Jun 2026
I built an AI agent that knows me
A self-hosted AI agent with local embeddings, hybrid retrieval, and persistent memory over my own knowledge base — and why the hard part wasn't the model.
20 May 2026
Cutting a React Native app from 1.2GB to 350MB
My first mobile app started at 700MB, climbed past 1.2GB, and got OOM-killed on real devices. The full teardown of how it reached a stable 350MB — and why the real leak was the shape of the app, not a setting.