RAG (retrieval-augmented generation)
RAG is a technique where an AI system first retrieves relevant documents from a trusted source and then writes its answer using them.
Why it matters
It helps reduce made-up answers and lets a system use up-to-date or private information without retraining the model. It does not remove errors: the retrieval can fetch the wrong text and the model can still misread it.
How to practice it
Building a small RAG pipeline is a practical exercise for computer science students, and judging its answers against the sources is a good review skill.