AI Search & AI Overviews

Retrieval-Augmented Generation (RAG)

A technique where an LLM retrieves relevant information from external sources before generating an answer.

CurrentLast updated: 2026-09-16
Back to glossary

Retrieval-Augmented Generation (RAG) is a technique where a Large Language Model retrieves relevant information from external sources (like the web or a database) before generating an answer. RAG combines the generative capabilities of LLMs with up-to-date, grounded information. Google AI Overviews and Perplexity use RAG.

Why it matters

RAG is the architecture behind generative search. Understanding it helps explain why certain sources are cited over others.

ragretrievalgeneration

Let's talk

Your next customer might not click a blue link — they'll ask an AI. Be the answer.

Book a free strategy call and I'll audit your visibility across Google, AI Overviews, ChatGPT, and Perplexity — then map out exactly what it takes to be found and cited.