Ensure that Pega Intelligent Virtual Assistant (IVA) asks the correct follow-up
questions to user input, by modifying the chatbot responses. By simulating a
conversation and modifying chatbot response questions in the preview console, the IVA
learns how to obtain additional clarifying information about the correct case type from
the user in a quick and conversational manner.
For example, in a request for
a car insurance quote, during a user interaction, an IVA asks questions about the make,
model, and year of production of the car, and then automatically stores the answers in the
properties of the business case.
Before you begin: For the IVA to respond to user input by asking questions, add a conversation to a
case type for your application. For more information, see
Adding a conversation to a case type.
-
In the header of Dev Studio, click the name of the application, and then click
Channels and interfaces.
-
In the Current channel interfaces section, click the icon
that represents your existing Alexa, Unified Messaging, or Web
Chatbot channel.
-
In the channel, click the Behavior tab.
-
At the top of the preview console, turn on the Show
analysis switch.
-
In the preview console, in the right panel, enter a command.
For example: To request a car insurance quote, enter: I would like to request
a car insurance quote.
Result: The preview console starts a Car Insurance case and
displays a follow-up question, for example: What is the make of the
foreign-made car?
-
To view additional options for the displayed question, click the
View folder contents icon below the question in the
preview console.
-
In the Edit question window, in the Question
text field, edit the text for the question.
For example: To have the IVA ask a question about any car make, enter the following
text: What is the make of the car?
- Optional:
To map the follow-up question from the IVA to a property, edit the
Map answer to property field.
For example: To map a response to a property requesting the make of a car, enter
.Make.
-
Click Save.