- Home
- Insights
- The revenue lexicon
- Retrieval-augmented generation
Glossary
Retrieval-augmented generation (RAG)
Artificial intelligence
Retrieval augmented generation (RAG) is the technique that makes an artificial intelligence system answer from the company's own documents: the system first searches the archives it has been pointed at for the relevant passages, then writes the answer out of those passages.
Its purpose is to tie every answer to a source that can be checked, and it narrows the room for invention that a model left alone with its training allows itself.
An example
The customer service desk of a machinery manufacturer answers delivery questions by reading the management system and the uploaded manuals, and every answer arrives with the document it came from. Whoever receives it can open that document and check, and whoever signs it knows what they are putting their name to.
What are your business challenges?
Tell us about your priorities and the objectives you want to reach.
You will receive a free, targeted answer within one working day.