RAG for Agents: From One-Shot Retrieval to Agentic Search

How retrieval actually works — chunking, embeddings, hybrid search, reranking — and what changes when an agent drives the search loop instead of a fixed pipeline. Plus grounding, citations, and the honest RAG vs long-context vs fine-tuning decision.

Content current as of 2026-09.

Lessons

1. Retrieval in one lesson
2. One-shot RAG vs agentic search
3. Grounding and citations
4. RAG vs long context vs fine-tuning
5. Evaluate retrieval before you blame the model