What is large language model (LLM)?
An AI model trained on large amounts of text that can understand requests and generate human-like replies.
Large language model (LLM), explained
In a voice agent, the LLM reads what the caller said, decides what to reply and which action to take, such as checking a slot or booking it.
LLMs are guided by a system prompt and can be connected to tools and data so they answer from your business's real information.
See how these ideas come together in Chitti, Manolle's AI voice agent.
Related terms
- System promptThe instructions that set a voice agent's role, tone, rules and goals.
- Function calling (tool use)An LLM's ability to call software functions, such as "check availability" or "create booking", during a conversation.
- Hallucination (in AI)When an AI states something that sounds plausible but isn't true.
- 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.
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.