Tag
Evaluation
Everything on this site involving Evaluation — projects, articles, research and tools.
Why Your RAG Evaluation Is Wrong
Most RAG evaluations measure the wrong thing, on the wrong data, with a judge that rewards the wrong behaviour. Here is what to measure instead.
AI Research & Fact-Checking System
A research agent that decomposes a claim, gathers evidence from multiple sources, cross-checks agreement between them, and refuses to answer when the evidence is thin.
RAG Evaluation Lab
Most RAG systems are tuned by vibes. This is a reproducible harness that measures retrieval and generation separately, so you can see which half is failing.
Six RAG Chunking Strategies Compared
Fixed, recursive, semantic, structural, sentence-window and parent-document chunking measured on retrieval recall across three corpora.
RAG Evaluation Checklist
A one-page checklist covering the four measurement mistakes that make a worse RAG system look better.