---
title: What is Retrieval-augmented generation? · Aeonav
description: A method where a model fetches relevant documents at answer time and writes from them.
canonical: https://www.aeonav.fivecoder.com/glossary/retrieval-augmented-generation
updated: "2026-09-15"
---

[AI search glossary](http://www.aeonav.fivecoder.com/glossary)

# Retrieval-augmented generation

Also known as RAG

A method where a model fetches relevant documents at answer time and writes from them.

RAG is why a model can answer questions about events after its training cutoff, and why fresh, well-structured content can show up in answers quickly. The engine retrieves sources, then generates a response grounded in them.

It is also why AEO works at all. If you are among the documents retrieved for a query, you can influence the answer, even though you never see the index.

## Go deeper

- [How long it takes to get cited by AI](http://www.aeonav.fivecoder.com/blog/how-long-to-get-cited-by-ai)
- [How agentic AI search reads your pages](http://www.aeonav.fivecoder.com/blog/do-llms-txt-files-matter-for-aeo)

## Related terms

[Grounding](http://www.aeonav.fivecoder.com/glossary/grounding)[AI citation](http://www.aeonav.fivecoder.com/glossary/ai-citation)[Semantic search](http://www.aeonav.fivecoder.com/glossary/semantic-search)

## See it in your own data

Aeonav is an open-source AI visibility platform. Self-host it for free and track how AI answer engines mention and cite your brand.

[Get started](http://www.aeonav.fivecoder.com/docs/getting-started)[Compare tools](http://www.aeonav.fivecoder.com/ai-visibility-tools)