← All projectsProject 05 / 08
GenAI
RAG evaluation framework
Scoring retrieval quality with context precision and context recall, using an LLM as the judge.
The problem
[What wasn’t working before, and who it was a problem for.]
The approach
[The architecture you chose and why — the main components and how they fit together.]
What I learned
[Two or three honest lessons — what you would design differently next time.]