AI glossary · Agents
Intent
In one sentence
An intent is the goal behind what a person writes or says to a chatbot or AI agent, such as booking, cancelling or asking for a price. Recognising it lets the system decide what to do with the message.
Also known as: user intent · chatbot intent · intent recognition · intent detection
What is an intent?
Every message has a purpose behind it. “Are you open on Sunday?”, “what time do you close tonight?” and “are you open right now?” are different sentences with the same intent: checking opening hours. Grouping thousands of ways of saying the same thing under one intent is what makes it possible to automate the answer.
Put it to work
An AI agent on your WhatsApp, CRM included
From €49/mo + VAT
It replies to customers on WhatsApp and logs every conversation in the CRM.
See the WhatsApp agentThe concept comes from natural language understanding, the part of language processing concerned with meaning. The intent answers “what”; entities answer “with which details”.
| Message | Intent | Entities |
|---|---|---|
| ”Can you move my Thursday appointment to Friday?” | Reschedule | Thursday, Friday |
| ”How much is a scale and polish?” | Ask price | scale and polish |
| ”I’ve been waiting a week for my order” | Complain | order |
Related to this term
UTIO WhatsApp
- 3 users and 500 AI conversations
- CRM and shared inbox included
- Built from your website in a minute
- 14-day free trial, no card needed
From €49/mo + VAT
See the WhatsApp agentHow it works
- Define the catalogue of intents the business wants to handle, with a description of each.
- The system classifies each message into one of them, which is a form of text classification. This used to need hundreds of training phrases; now a language model works from the description.
- It measures its confidence. If confidence is low, it asks a clarifying question rather than guessing.
- It triggers the action: a reply, a step in a conversation flow or a tool.
- It handles what doesn’t fit: messages with no recognised intent get a generic reply or go to a person.
In an AI agent, the intent isn’t always an explicit label: the model interprets it and decides directly. Thinking in intents is still useful for designing what the agent should and shouldn’t do.
Example
A dental practice in Bath reviews a month of WhatsApp messages and finds that 80% fall into six intents: book an appointment, move it, cancel it, ask about prices, check whether a dental plan is accepted, and report pain. The agent handles the first five. The sixth, being urgent and clinical, always goes to the team with a clear alert.
Intents at UTIO
With UTIO’s WhatsApp agent you don’t build an intent catalogue by hand: the agent understands what each customer is asking for from your instructions and your business information. What matters is the outcome: every conversation ends up as an appointment in the calendar, a lead in the pipeline with its assigned sales rep, a task or a ticket in the CRM.
The use cases already running in production, such as appointments and bookings or support, are listed under verticals.
Frequently asked questions
What's the difference between an intent and an entity?
The intent is what the user wants (to move an appointment). Entities are the details that come with it (Thursday, 10am, with Mary). A system needs both in order to act.
How many intents should a chatbot have?
Enough to cover most of the real messages your customers send, usually somewhere between ten and thirty. It's better to start with a few handled well and a clear route to a person for everything else.
What if a message contains several intents?
It happens all the time: 'I'd like to move my appointment, and how much is a colour?'. Systems built on language models pick up both and deal with them in turn; classic ones often keep only one.
Related terms
- Natural language understanding (NLU)
Natural language understanding (NLU) is the part of NLP that deals with the meaning of a message: what the person wants (their intent) and which specific details they give (entities such as dates, names or products).
- Chatbot
A chatbot is a program that holds text conversations with people, on a website or on WhatsApp, to answer questions or guide them through a task. It either follows fixed rules or uses a language model to understand what people write.
- Conversation flow
A conversation flow is the predefined path of an automated conversation: the steps, questions and replies a bot follows depending on what the user answers, usually drawn as a branching diagram.
- Text classification
Text classification is the AI task of automatically assigning one or more categories to a piece of text, such as an email or a message: type of request, topic, priority or language. It's the basis for sorting, prioritising and routing work.
- Human handoff
Human handoff is the point at which a chatbot or AI agent passes the conversation to a member of staff, together with the context it has gathered, because the case needs it, a rule requires it or the customer asks for it.
Updated on