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. 12 Show me the math
  2. 11 Three passes, one fail: pre-registering the validation of a capacity planner
  3. 10 A flat datacenter network has no hierarchy to blame
  4. 09 A cheap model with a hard gate beats a frontier model with a good prompt
  5. 08 You can't review your way out of a god object

All writing →

Elsewhere

About · RSS · GitHub