A natural language example of user intent. For example, this could be a text string in an incident’s or case’s short description, a chat entry, or an email subject line. Utterances in the NLU model builder represent how a user would seek proper topic discovery.

Intent

The user's purpose in the utterance

Entity

The context or the details in the user utterance

Topic

Defines the dialog exchanged between a Virtual Agent and user to accomplish a specific goal or resolve an issue.

Topic Discovery

Replaces the Keyword approach to discovering topics by leveraging NLU to extract and interpret the user’s utterance and matches it to Virtual Agent topics.

Topic Switching

The ability of Virtual Agent to change the conversation from one intent to another intent

Small Talk

These topics run in NLU conversations that enable users to temporarily switch topics and return to the original conversational topic. This provides a response to a casual question that users might ask during a conversation, such as the time or date. A small talk topic can occur anytime within a conversation session and can be unrelated to the original conversation intent.

Setup Topics

Virtual Agent conversations share common characteristics such as a welcome greeting or a standard fallback response when the Virtual Agent does not understand user input. You have a collection of predefined setup topics that run automatically at appropriate points in a conversation, based on the context, Utterances (if NLU is enabled), or keywords that a user enters during the conversation.