Retrieval
RAG (retrieval-augmented generation)
Looking up relevant material from your own documents and giving it to the model, so answers are grounded in your data rather than its training.
RAG is how you make a general-purpose model answer questions about your business.
The flow is: take the user's question, search your documents for relevant passages, put those passages into the prompt, and ask the model to answer using them. The model contributes language ability; your documents contribute the facts.
Done properly this dramatically reduces hallucination and lets answers cite their sources. Done badly — embedding everything and hoping similarity search sorts it out — it produces a convincing demo that falls apart on real questions.
Retrieval quality decides answer quality. The search step deserves as much engineering as the model call.