Most RAG demos work. Most RAG systems don't.
I write about what breaks between the prototype and the hundredth user — retrieval quality, evals, cost and latency — and I publish the measurement behind every number.
One essay, when there is something measured to report.
No spam. One click to unsubscribe.
Free resource
The 30-point production readiness checklist for RAG systems
What to measure before the hundredth user finds the gap
Recent essays
RetrievalRerank before you upgrade the model
Most confidently wrong RAG answers are retrieval failures. Log each chunk's rank before and after reranking, measure hit@k, and fix the right stage first.
Failure modesWhat your assistant does when the vector store is down
Every retrieval system has a bad day. The ones that survive it decided in advance what degraded means, and never let a failed lookup sound confident.
Retrieval
Your RAG isn't hallucinating. Your retriever is missing.
Most "hallucination" bugs are retrieval failures wearing a costume. Here is how to tell the two apart before you reach for a bigger model or a longer prompt.
About Nitish
