Intent
Also called User intent, Intent recognition
In chatbots, an intent is the goal behind a user's message, such as checking an order, asking about pricing or requesting a refund. Traditional chatbots classify each message into one of a fixed list of intents to choose a scripted reply; language-model chatbots infer intent without a predefined list.
Example
"Where's my stuff?", "Has my order shipped?" and "Tracking please" all share the intent "order status".
Why it matters for a website chatbot
Older bots needed every intent mapped by hand, and anything unmapped failed. A language-model chatbot handles new phrasings on its own. With ChatBento, reading the inbox shows which intents are most common, so you know which answers to make strongest.
See it in practice: Pre-sales questions
Related terms
- Conversational AIConversational AI is the field of technology that lets computers hold natural conversations with people in text or speech. It combines language understanding, dialogue management and language generation, and powers chatbots, voice assistants and phone systems that respond to what people say rather than to fixed menu choices.
- Fallback messageA fallback message is what a chatbot says when it can't understand a request or doesn't have an answer. Good fallbacks admit the limit plainly and offer a next step, such as rephrasing, a link or contact with a person, instead of guessing or repeating the same unhelpful reply.
- Quick repliesQuick replies are clickable buttons in a chat window that offer ready-made questions or answers, so users can tap instead of typing. They're used to start conversations, guide people toward common topics and make chat easier on mobile. Users can usually still type their own message instead.