Language & NLP
Intent recognition
Also called: intent detection · intent classification
Intent recognition is identifying the underlying goal behind a caller's utterance — 'book an appointment', 'check my balance', 'speak to a person' — so the agent can route the conversation and take the right action.
It's a core NLU task. Traditional systems used fixed intent lists; LLM-based agents can handle open-ended intents and combine intent with extracted details in one step.
Related terms
Natural language understandingThe part of AI that works out what a person means — their intent and the key details — from natural language, not just the literal words.Entity extractionPulling the specific details out of what a caller says — dates, names, amounts, phone numbers — that the agent needs to complete a task.Dialogue managementKeeping track of context across a multi-turn conversation — what's been said, what's still needed — so the agent stays coherent.
See Intent recognition 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