If you only read one thing
Start with the piece that turns evals from a measurement project into a product operating loop.
Series
Practical AI Evals
A reading path for teams that need AI quality to become inspectable, fixable, and steadily better. The point is not to worship a metric. The point is to build the loop that tells you what broke, why, and what to change next.
Who this is for
- Engineering leaders trying to make AI quality less mysterious.
- Product teams shipping agents, RAG, onboarding assistants, copilots, or workflow automation.
- Builders who have traces, dashboards, and prompts, but not a reliable improvement loop yet.
Recommended order
-
Essay · ai · evals · engineering
A streamlined system for AI evaluation that closes the gap between seeing problems and fixing them.
-
Essay · ai · rag · evals
How Frigade Slashed Latency & Boosted User Helpfulness
-
Essay · ai · flywheel · evaluation
-
Essay · ai · evals · flywheel
An AI Maturity Model
-
Essay · ai · evals
A Practical Guide to Evaluation-Driven Improvement
Where to go next
Use the AI Evals topic hub for concepts, TILs, and future case-study links.