I'm John. I work on AI systems — the practical engineering underneath model behavior: evaluation, tool use, agent loops, the places where probability meets production code.

This is where I write about it. Mostly notes from things that surprised me, occasionally longer pieces when something is worth working out in public.

Recent writing

  1. 07 You can't save on overhead you weren't paying
  2. 06 Runway: capacity planning with calibrated uncertainty
  3. 05 Cairn: ranked attribution, not root cause
  4. 04 Anvil: the deploy gate run backward
  5. 03 Tessera: same engine, different scope, and what Anchor-from-round-1 looks like

All writing →

Elsewhere

About · RSS · GitHub