Skip to content
AEO Canon · the reference for answer-engine optimization
AEOCanon

Lesson 4 of 6

How AI Answers Are Built (RAG)

Retrieval-augmented generation is how answer engines stay current and cite sources. This lesson connects RAG directly to how you get cited.

Learning objectives

  • ▸Explain retrieval-augmented generation in plain terms.
  • ▸Describe the retrieve-rerank-generate-cite pipeline.
  • ▸Explain why RAG makes the passage the unit of AEO.

The lesson

Read the full lesson →How Does Retrieval-Augmented Generation (RAG) Work?Retrieval-augmented generation (RAG) works by retrieving relevant passages from an external source, then having a language model generate an answer grounded in them. It is the architecture behind every AI answer engine.7 min read

Key takeaways

  • ▸RAG retrieves real passages first, then generates an answer grounded in them.
  • ▸It's why AI answers can be current and can cite their sources.
  • ▸Because RAG quotes passages, the passage — not the page — is what you optimize.

Knowledge check

Knowledge check

0 / 3

  1. 1. What does RAG add to a base model?

  2. 2. Which is the RAG pipeline?

  3. 3. What does RAG make the unit of optimization?