Latest by Alex
04 · The Lab
Public benchmarks can shortlist a model. Your product eval has to decide
Aug 17, 2026 · 19 min
04 · The Lab
A model name is not a product version
Aug 7, 2026 · 18 min
04 · The Lab
OpenRouter Classifiers can label AI spend. First prove the labels
Jul 25, 2026 · 18 min
04 · The Lab
When AI generates the whole page, test the whole page
Jul 20, 2026 · 18 min
The expert uses it
Alex builds every experiment on Y Build
Same tooling, your account. Prompt to a deployed app on your own domain.