Quick definition · 2 min AI term

RAG

RAG (retrieval-augmented generation) lets an AI look things up before answering, so it can use your documents instead of only its training.

Think of it like

An open-book exam. Instead of answering from memory, the model first fetches the relevant pages, then writes.

Example

A “chat with your docs” tool uses RAG: it retrieves the matching passages, then the model answers from them.

Why it matters

RAG is how most “AI that knows your data” products work, and one of the most important patterns to understand.

Where you’ll see it