Retrieval-augmented generation (RAG)
Retrieval-augmented generation is a technique where an AI first searches trusted sources — a company's documents, a website, a database — and then writes its answer using what it found, ideally with citations. It reduces, but does not eliminate, made-up answers.
In one line, for a 12-year-old
RAG is when the AI looks things up in a book first, then answers — like an open-book test.
An example
Our own Keeper looks up today's headlines on AI Broadsheet before answering, and links to the stories it used.
Why it matters to people
Answers that cite sources let you check them yourself. When a tool gives no sources, treat its claims as unverified.