Notes from the build
What I learn building with AI agents: experiments, failures, and what I would do differently. Real projects, client details kept private.
- 2026-10-27
What ten months of building AI systems taught me
Seven lessons from building computer vision, catalog matching, AI agents and eval harnesses: data beats models, uncertainty is a feature, and a check that cannot run must say so. - 2026-10-06
pass, fail, error: a three-valued verdict for AI agent loops
Every check needs three outcomes: pass, fail and error. Why error must never count as either, and what that means for Karpathy-style agent loops.