Intention
Intention is a goal or purpose attributed to an agent and expressed or implied by a request, action, plan, or desired outcome.
Effective Conversational AI
A user intent is the goal, purpose, or desired action that a user expresses or implies in a conversational interaction.
- How it is used
- Identifies the user’s goal so a chatbot can answer, begin a process flow, or route the request.
- How deep it goes
- Defines intents through utterance groupings and works through response, flow, coverage, and testing decisions without detailing classifier internals.
- Examples
- Uses store-hours questions, password problems, flight-booking requests, and claim-status flows to distinguish phrasing, goals, and next steps.
- What you can do after
- Build it from scratch by grouping real requests into intents, choosing actions and fallbacks, and testing recognition against unseen utterances.
AI-Powered Search
User intent is the goal or information need that motivates a person's query or interaction with a search system.
- How it is used
- Guides the choice of relevant content, answers, navigation, or actions in search and recommendation experiences.
- How deep it goes
- Explains three intent dimensions and works through query classification, while treating any inferred goal as uncertain.
- Examples
- Contrasts factual, support, product, and action queries; classifies sample queries against indexed Stack Exchange categories.
- What you can do after
- Apply it via semantic knowledge graph query classification to inform search filters, ranking changes, or navigation choices.
WordPress Power Toolkit: Harness AI to build next-level websites
User intent is the motive or objective underlying a user's search query.
- How it is used
- Aligns keywords and website content with the motive behind a search to satisfy visitors and improve search performance.
- How deep it goes
- Defines four intent types and gives examples, while linking intent to semantics, related terms, and topical depth.
- Examples
- Uses fishing searches about destinations, knots, lure comparisons, purchases, methods, equipment, and locations.
- What you can do after
- Apply intent categories to select keywords and create content that answers the audience's informational or purchasing goal.
Read how WordPress Power Toolkit: Harness AI to build next-level websites explains intention →
The Art of AI Product Development
A user’s underlying goal or requested task expressed through an interaction.
- How it is used
- Focuses AI products on user tasks the model can handle and guides users toward those supported requests.
- How deep it goes
- Explains intent through product decisions and examples, but does not detail technical intent-detection methods.
- Examples
- Uses chatbot question guidance, unauthorized investment-advice requests, and product-description rewrites.
- What you can do after
- Apply intent boundaries by testing real user questions and steering requests toward supported tasks.
Read how The Art of AI Product Development explains intention →
Build an AI Agent (From Scratch)
User intent is the goal or desired outcome underlying a user's request to an AI system.
- How it is used
- Guides agent prompt rules for choosing immediate action versus clarification.
- How deep it goes
- States the clear-versus-ambiguous rule and sample prompt wording, but does not specify how to detect ambiguity.
- Examples
- Uses weather search, calculation, and file analysis to illustrate acting on clear requests.
- What you can do after
- Configure agents to act on clear requests and ask minimal clarifying questions when intent is unclear.
Read how Build an AI Agent (From Scratch) explains intention →
Natural Language Processing in Action, Second Edition
An intent is a category representing an objective that a user wants an NLP system or chatbot to carry out.
- How it is used
- Maps user messages to conversational goals, such as starting a chat or requesting a task.
- How deep it goes
- Defines intent and demonstrates keyword detection for greeting versus unknown, while pointing toward regular expressions as an extension.
- Examples
- Uses “Hello Joshua” to illustrate greeting detection and a Ukrainian translation query to illustrate a task intent.
- What you can do after
- Build a simple keyword recognizer that assigns greeting or unknown intent, then extend its rules with more categories or regular expressions.
Read how Natural Language Processing in Action, Second Edition explains intention →
Related concepts
- intuitioncontrasts with · Intuition is the formation of a judgment or insight without deliberate, explicit analytical reasoning.
- goalcontrasts with · A goal is a desired outcome or state that an actor or system aims to achieve and that can guide action or evaluation.
- contextpart of · Context is the surrounding information, state, or circumstances that condition how an entity, event, or task is interpreted or how a system behaves.
- actioncontrasts with · An action is a choice or operation selected or performed by an actor that can affect a system or environment or produce an outcome.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.