Scoping, sequencing and gating a single-model car-price site from a 197-page topical map to a 199-URL launch in about 12 days, and what I chose not to build.
Topic
Ai Reliability
Projects
The product decisions behind a one-person AI content business: who it serves, where the quality bar sits, what I killed, and the honest numbers.
How I sequenced a CMS rebuild and AI workflows for desk editors in eight languages, kept the publish decision with each editor, and advised against funding an AI debate platform.
Writing
- The Day My LLM Judge Drifted — and How I Caught ItMy LLM judge quietly inflated scores and re-ranked my configs. The before/after data, the fix, and what a PM should require before trusting a judge.
- When Constrained Generation Beats Open GenerationLessons from shipping AI in a multilingual newsroom and running an eval-gated content pipeline: constrain the failure surface, not the model's talent.