RAG (retrieval augmented generation)
Retrieval augmented generation (RAG) is an approach that retrieves relevant information and supplies it to a language model when generating a response. It can use documents, search results or other records outside the model’s training. Retrieval quality and the model’s use of the supplied context both affect the answer, including whether its claims are supported.
Why it matters for a business
RAG explains how an assistant can use a recent service page without waiting for a new model to be trained. It also explains why bad source data can produce a bad answer. An owner’s practical concern is the quality and accessibility of information available for retrieval.
Example and evidence
An illustrative support assistant retrieves a returns policy before answering a customer. If it retrieves the old policy, a fluent answer may still be wrong. AIGROW’s source research concerns observed web source use; it cannot expose every provider’s internal retrieval architecture.
What to do next
Maintain one clear, current source for important policies and service facts. Remove contradictory versions where you control them. State dates and applicability when details change. Check whether a generated answer matches the actual retrieved source.
Common question
Related terms
Sources and method
Sources checked on 2026-10-09. Examples marked illustrative are not measured business results.
Check your own business in AI answers
Run the free scan to see which assistants name your business and which facts need attention. A scan is a sample, not a promise of future recommendations.