Retrieval-augmented generation
A method that grounds an AI's answers in specific, vetted documents instead of its general memory, which reduces hallucination. Often shortened to RAG.
A hospital sets up an assistant that answers staff questions from its own policy library and shows the document it drew on. A nurse asks about the heparin infusion protocol and gets a confident, cited answer from last year's version, because the revised protocol was added to the library and the old one was never taken out. Before launch, decide who owns the document collection and how superseded policies get removed, and make sure every answer displays the source's title and effective date so staff can spot an outdated one.
Terms like this come up in real clinical scenarios across the HelloAI courses: bite-sized modules with verifiable certificates. An account takes one minute, no password needed.
Sign in →