Language & NLP
Retrieval-augmented generationRAG
Retrieval-augmented generation (RAG) is a technique that grounds a language model's answers in an external knowledge source: it retrieves relevant passages from your documents at query time and feeds them to the model. It's how a voice agent answers accurately from your knowledge base instead of guessing.
RAG reduces hallucination and lets an agent stay current without retraining the model — you just update the underlying documents. It's the standard way to make a general LLM speak accurately about your specific business.
Related terms
Large language modelAn AI model trained on vast text that generates and understands language. LLMs are the reasoning engine inside modern conversational and voice AI.System promptThe instructions that define an AI agent's role, tone, rules and boundaries. The system prompt shapes how a voice agent behaves on every call.Natural language processingThe broad field of AI concerned with computers understanding, interpreting and generating human language — the foundation under conversational AI.
See Retrieval-augmented generation in a real call.
Book a 30-minute demo and watch Finn handle inbound and outbound calls end to end — no stack to assemble.
Try Finn for free