16 posts across articles, notes and newsletter issues.
The on-site assistant for my studio is live, with a spend cap, a fallback and a human-reviewed learning queue. Plus what building Andor taught me about agent completion states.
Most agent failures I debug are tool design failures. Names, schemas, descriptions and error messages decide whether a model calls the right tool with the right input.
A quick note on M-Pesa Daraja's sandbox. It will silently accept a duplicate STK push request that production would reject, so idempotency keys need testing against real behaviour, not just the docs.
The first issue of Build notes. What this newsletter is, what it is not, and what I am building right now: an AI coding agent for VS Code and my studio's website.
