Retrieval-Augmented Generation (RAG)
RAG is the technique where an AI retrieves external documents at query time to ground its answer — a key route to being cited.
Retrieval-Augmented Generation (RAG) is an AI architecture in which the model fetches relevant external documents at the moment of a query and uses them to ground its response, rather than relying solely on what it memorized during training. It’s why assistants can answer about recent events and cite live sources.
RAG matters for discovery because it creates a real-time competition for retrieval: if your content is indexed, well-structured, and authoritative, it’s more likely to be pulled in and reflected (and cited) in the answer.
Optimizing for RAG-based assistants means treating your public content like a knowledge base the model can quote — clear, factual, and easy to extract.