← CurriculumWeek 05 / 10 · Systems
05

RAG: Retrieval-Augmented Generation

Understand how AI accesses information it wasn't trained on — and learn the discipline of choosing RAG vs. simpler patterns.

Topics covered

  1. 01What RAG is and what problem it actually solves
  2. 02Vector embeddings explained without math
  3. 03Vector databases: Pinecone, Chroma, Supabase Vector — what to pick when
  4. 04When to RAG vs. when to just paste context
  5. 05Chunking, embedding, retrieval, re-ranking — the four-stage pipeline
  6. 06RAG failure modes: bad chunks, irrelevant retrieval, stale data
  7. 07Building and evaluating a real pipeline end-to-end

Build challenge

Deliverable

Working RAG bot over a real Outpost knowledge base — must answer 5 evaluation queries correctly with cited sources.