Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation (RAG) retrieves relevant documents or records first, then asks the model to answer using that material.
It powers “chat with your docs,” in-app help, and support copilots that must stay tied to your knowledge base, not the open internet.
Share
What it means
RAG = search step + generation step: find chunks likely to contain the answer, inject them into the prompt, then produce a reply grounded in those sources.
Why designers should care
RAG UX must show sources, gaps, and confidence when nothing relevant is found. Otherwise users trust fluent wrong answers.
Example
An internal policy bot answers “Can I expensed rideshare?” with quoted handbook sections, links to the source PDF page, and “Not found in policy” when retrieval returns nothing.
Common mistakes
- • Citations that do not match the generated sentence users read.
- • No empty state when retrieval fails, the model improvises instead.
- • Hiding which workspace or date range search covered.