latest note · Sep 10, 2026
shipping eval loops that fit in a lunch break
what we tried to keep agent regressions visible without building a platform first.
also running
we write down what we try.
experiments in AI tooling and reasoning.
latest note · Sep 10, 2026
what we tried to keep agent regressions visible without building a platform first.
also running
we write down what we try.
experiments in AI tooling and reasoning.