What is retrieval-augmented generation (RAG)?
Retrieval-augmented generation is a method in which an AI system first looks up relevant information from trusted sources, then uses a language model to write an answer based on what it found.
Why it matters
A language model on its own knows nothing about an organisation’s current prices, policies or products. Retrieval-augmented generation lets it answer from the organisation’s own content instead of from general training. Answers become more accurate and easier to check, and the content can be updated without retraining the model. It reduces wrong answers but does not remove them.
How it works
The organisation’s documents are split into passages and indexed so they can be searched by meaning. When a question arrives, the system retrieves the passages that best match it. Those passages are passed to the language model together with the question and an instruction to answer only from them. Many systems also show which source each answer came from.
Example
A customer asks whether a warranty covers water damage. The system searches the warranty documents, finds the clause on liquid damage and passes it to the model. The model replies that water damage is excluded and links to the clause. If no relevant passage is found, a well-designed system says it does not know and offers to connect the customer to a person.
