What is retrieval-augmented generation (RAG)?
A technique where an AI looks up relevant information before answering, instead of relying only on what it learned in training.
Retrieval-augmented generation (RAG), explained
With RAG, a voice agent searches your knowledge base during the call and answers from what it finds, which reduces made-up answers.
RAG works best when the source material is well organised: one clear answer per topic, current prices and policies, and no contradicting old documents. The agent can only be as accurate as what it retrieves.
See how these ideas come together in Chitti, Manolle's AI voice agent.
Related terms
- Knowledge baseThe business information a voice agent answers from, such as prices, timings, policies and FAQs.
- Hallucination (in AI)When an AI states something that sounds plausible but isn't true.
- Large language model (LLM)An AI model trained on large amounts of text that can understand requests and generate human-like replies.
See an AI voice agent at work on your calls.
See the complete system live: marketing, lead capture, AI voice calling, sales conversion, and analytics.