Glossary

Retrieval-augmented generation

Also called: RAG

A technique where an AI model looks up relevant information from a business's own documents before answering, instead of relying only on what it learned in training.

The system searches a knowledge base (service lists, policies, FAQs) for passages that match the question and gives them to the language model along with the question. Answers stay closer to the business's real information and can be kept current by updating the documents.