liveBook · Manning

Conversational action

As explained in Effective Conversational AI

A conversational action is a configured operation that starts under specified conversational conditions and performs a response or subsequent interaction step.

A conversational action is a configured operation that starts when specified user utterances are recognized and then performs a response or another interaction step. The simplest form detects an intent and returns an answer. section 2.1.2

Cake Shop question answering

For a store-hours action, configure utterances such as “Store hours” and “When are you open?”, connect them to an intent, and return “We are open Monday through Friday, 9:00 a.m. to 9:00 p.m.” Add more examples to improve recognition, then test variations and unfamiliar questions. section 2.1.2

Figure 2.2 Question-answering bots map user utterances to intents, which map to answers.
figure

Trace the basic mapping from user utterances to intents and from intents to answers. section 2.1.2

How Effective Conversational AI covers it

How deep it goes
Explains triggers, intent detection, responses, and next steps, but stops short of implementation code.
Examples
Uses Cake Shop background, store-hours, cake-options, cost, and Cake Club questions with sample utterances and answers.
What it assumes
Assumes familiarity with user questions and answers while teaching intent triggers and response configuration from the beginning.
What you can do after
Operate a basic question-answering action by configuring utterances, an intent, a response, and recognition tests.
How it connects
Connects user utterances with intents, responses, conditional logic, and subsequent interaction steps.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Effective Conversational AI. The section links point to the parts of the book it draws on.