How deeply does Effective Conversational AI cover question-answering action?

Defines triggers, intent detection, response, and testing, while stopping short of conditional logic or multi-step dialogue.

Question-answering action

As explained in Effective Conversational AI

A question-answering action is a conversational action that detects an intent and provides an answer.

When users ask routine questions, a question-answering action detects the intent and returns a prepared answer, avoiding a longer dialogue. section 2.1.2

Configure each action with three practical elements:

Related user utterances that trigger intent recognition. section 2.1.2
An intent representing the user’s question. section 2.1.2
A response, usually simple static text; no conditional logic or next step is required. section 2.1.2

Cake Shop FAQ

Utterances such as “What are your store hours?” map to a store-hours intent and produce “We are open Monday through Friday, 9:00 a.m. to 9:00 p.m.” Testing an unrelated question prompts the bot to request a rephrasing. section 2.1.2

Table 2.2 Initial set of FAQ intents, with associated utterances and responses

Intent	Example utterances	Response
`#background`	Tell me about Cake Shop What's the background on your business? History of Cake Shop	Founded by Grandma Cake in 1980, we've made over 10,000 cakes for local residents!
`#store_hours`	Store hours What are your store hours? When are you open?	We are open Monday through Friday, 9:00 a.m. to 9:00 p.m.
`#cake_options`	Cake options Do you make wedding cakes? What kinds of cakes do you sell?	We offer cakes for many occasions, such as weddings, birthdays, anniversaries, retirement, and all- occasion cakes.
`#cost`	How much does a cake cost? Is there a minimum order value? Is there a surcharge for delivery?	Our cakes typically cost around $30, with a $5 delivery fee.
`#cake_club`	Cake rewards Cake Club Any special promotions or discounts?	Our Cake Club rewards program earns you a $10 gift certificate for every ten cakes you purchase.

Browse the FAQ table to compare intents, example utterances, and prepared responses. section 2.1.2

How Effective Conversational AI covers it

liveBook manning.com

Read Effective Conversational AI on liveBook Get the book at manning.com

Related concepts

conversational actionkind of · A conversational action is a configured operation that starts under specified conversational conditions and performs a response or subsequent interaction step.
actionkind of · An action is a choice or operation selected or performed by an actor that can affect a system or environment or produce an outcome.
intentionuses · Intention is a goal or purpose attributed to an agent and expressed or implied by a request, action, plan, or desired outcome.
outputproduces · An output is a result or response produced by a process, operation, or system, including data, content, actions, or signals.
static question-answering actionincludes · A static question-answering action detects an intent and returns a fixed response without conditional logic or a subsequent step.
actionkind of · An action is a lowest-level narrative-code unit representing a small, individual operation or event.

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.