Blog

Notes on AI engineering, full-stack architecture and the products I build, from LLM pipelines and evals to shipping on web and mobile.

Oct 27, 20264 min read

How I built an LLM eval harness that took AI output from 24% to 97% valid

A blind pairwise judge, a pinned prompt registry and one harness bug that silently inverted our model rankings. A practical guide to LLM evals for code generation.

LLM Evals AI Engineering

Five AI-generated Krofile digital business cards side by side