RAG (retrieval-augmented generation)

RAG is a setup where the AI first searches a collection of your documents for relevant passages, then writes its answer using those passages. It combines search with writing.

It is how "chat with your documents" tools work — company wikis, policy libraries, support knowledge bases. Answers are grounded in your material rather than the model’s memory.

Assuming a RAG tool is always right. It can still misread a passage or miss the relevant document, so spot-check important answers against the source it quotes.

Search our handbook for the remote-work policy, then summarise it in three bullets and link the section you used.