# Retrieval-augmented generation

> Fetching documents at question time and giving them to a language model to write its answer from.

## What it means in practice

Usually shortened to RAG. It explains why AI answers change without any model being retrained: the retrieval step ran again and returned a different set of pages. It also explains why being cited is partly a retrieval problem rather than a writing problem, and why the same brand can appear in one engine and not another that retrieved from a different index.

## Category

Concept in How AI answers work.
This definition is editorial category vocabulary, not a metric refd computes.