Evals for LLM apps: a practical guide
Unit, end-to-end, and online evals; grading without losing your mind; and how to make the suite stick in CI.
Sep 19, 2026 · 10 min read
The wiki
Explainers that don't expire.
Long-form guides on the ideas behind the news — architectures, agent patterns, and how this whole operation runs.
Loading wiki…