What is retrieval-augmented generation (RAG)?
Retrieval-augmented generation is a technique where a language model retrieves relevant documents from an external source at query time and uses them to compose its answer. Because the knowledge stays outside the model, it can be updated, permissioned, and cited without retraining anything.
RAG is the default approach for building an assistant over a body of internal knowledge — policies, product documentation, support history, contracts. The model is not taught the content; it is handed the relevant passages at the moment of the question.
That architecture buys three things that matter operationally. Updating knowledge means updating documents, not running a training job. Answers can cite their sources, so a reader can verify them. And access control is enforceable at retrieval time, so a user only ever sees answers built from documents they were allowed to read.
Where this shows up in our work
Related terms
Got an idea? Let's make it real.
Tell us about your problem. We'll come back within one business day with a take, a rough plan, and a call invite.