Glossary · R
Retrieval-augmented generation
Retrieval-augmented generation is the method by which an answer engine fetches relevant documents at query time and composes its answer from them, rather than from its training data alone.
Extended definition
In more detail.
The engine converts the question into a search, retrieves candidate passages, selects those it judges most relevant and trustworthy, and generates a response that draws on them, often citing them. This is why the structure of a page matters: a clear, declarative passage that answers the question is what gets retrieved and quoted. It is also why crawl access matters: a page the retriever cannot fetch cannot be used, whatever its quality.
In our work
Where it appears.
The capability pages on this site lead with a declarative answer block because retrieval systems lift the passage that answers the question. See page specification and editorial standards.
By David Selakovic · Published 2026-10-16 · Revised 2026-10-16 · Reviewed every 180 days