Skip to content
Agent YAP

What is it?

RAG (Retrieval-Augmented Generation)

A technique where, instead of relying only on what a model learned during training, the system retrieves relevant external information (from documents, databases, or the web) and feeds it into the model before it answers. This keeps answers current and grounded. "Naive" RAG retrieves a fixed set of documents once; more advanced and "agentic" versions retrieve repeatedly and adapt. RAG is a whole topic of its own in this material.

From the AI agent glossary

Where RAG is explained

  1. From Naive RAG to Agentic RAG: The EvolutionAgentic RAG · The five stages of RAG
  2. Retrieval: RAG vs Tools vs Long ContextArchitecture and System Design · The three strategies
  3. Practical Guidance: When and How to Use Agentic RAGAgentic RAG · Lesson 1: Agentic RAG is not always the right default
  4. The Building Blocks of Agentic IntelligenceAgentic RAG · The four core agentic patterns
  5. How Memory Is Built and RetrievedAgentic Memory · How a production pipeline does write and manage: AgentCore

Every term, A to Z