Intent tells you what someone wants. Entities tell you the particulars. In the message asking whether a boiler service is available next Thursday morning in Bristol, the intent is a booking enquiry and the entities are the service, the day, the time of day and the location. Without the entities you have a vague enquiry; with them you have something a human can act on immediately.
Traditional systems handled this with pattern rules and trained models per entity type, which worked well for rigid formats like dates and email addresses and poorly for anything fuzzy. Language models are considerably better at the messy cases, including relative references such as tomorrow or the week after next, and details expressed in ways nobody wrote a rule for. They still benefit from a clear definition of which fields actually matter to your business.
In Clerkzo, extraction is what turns a conversation into a usable record. When a visitor describes what they need, the relevant details are captured alongside the transcript so a booking request or lead arrives with context attached rather than as a bare name and email. Nobody on your team has to read the whole exchange to work out what was being asked.
Related terms
Browse all 142 terms- Fallback ResponseA fallback response is what a chatbot says when it cannot answer a question, either because the request falls outside its scope or because nothing in its knowledge base supports a reliable answer.
- Conversation FlowConversation flow is the path a chat takes from the opening message to a resolution, including the order questions are asked, the branches available and the points where the conversation can end or transfer to a human.
- Dialogue ManagementDialogue management is the part of a chatbot that decides what to do at each turn of a conversation, tracking what has been said, what information is still missing and what should happen next.
- Chatbot PersonaA chatbot persona is the consistent character a chat widget presents to visitors, covering its name, tone, level of formality and how it handles moments like uncertainty, complaints or requests it cannot fulfil.