Measuring retrieval: recall@k, MRR, and a golden set you'll maintain
Build the harness that tells you whether a change helped. Bootstrap a golden set from your own corpus, separate retrieval failures from generation failures, and stop shipping on vibes.
Tutorial9 minadvanced
Write the eval first
Prompt engineering without an eval is just vibes with extra steps. Here's how to build a scoring harness in an afternoon, and why twenty examples beat two thousand.
Article6 min