Skip to content

RAG

Ground the model in your documents instead of its memory.

retrieval-augmented generationchunkingmetadatahybrid searchrerankingcitations

Lessons

  1. 23.1RAG: answering from your documentsThe model doesn't know your hotel's pet policy. RAG looks it up and hands it over just in time, so answers come from your facts, with sources. 30 min RAG builder
  2. 23.2Chunking strategies: cutting documents so retrieval worksSearch returns pieces of documents, not whole documents. How you cut those pieces decides whether the AI can ever find the answer. 30 min RAG builder
  3. 23.3Hybrid search and rerankingKeyword search finds exact codes, vector search finds meaning. Use both to collect candidates, then a careful reranker to put the best one first. 30 min RAG builder
  4. 23.4Citations, grounding and knowing when to say “I don't know”Giving the model the right documents doesn't mean it will use them. Here's how to get answers that cite real sources, and say "I don't know" when they can't. 30 min RAG builder

On the job: try it on your own project

Pick a set of documents your team or users ask questions about. Ask Claude Code to build a tiny RAG prototype on a branch: chunk, retrieve, answer with citations. Write ten real questions and check each answer: was the right chunk retrieved, and is the answer grounded? Record a short findings note on chunking and retrieval quality before anyone builds the real thing.

Can you do this now?

0/4. Anything you can't tick yet: reopen that lesson's practice ladder.