Skip to main content

Language & NLP

Large language modelLLM

A large language model (LLM) is an AI model trained on massive amounts of text that can understand and generate human language. In a voice agent, the LLM is the brain — it decides what to say or do next, grounded in your knowledge base and rules.

LLMs enable open, unscripted conversation, which is why modern agents can improvise instead of following fixed branches. Grounding techniques like retrieval-augmented generation keep an LLM's answers accurate to your data.

See Large language model in a real call.

Book a 30-minute demo and watch Finn handle inbound and outbound calls end to end — no stack to assemble.