Defining response commands for a conversational channel
To automate business processes and save the time that case workers spend answering simple questions that are typical of a case type, you can define response commands so that Pega Intelligent Virtual Assistant™ (IVA) correctly reacts to user input. The chatbot detects the best response for a topic, which is the detected subject matter of the conversation, by using text analysis, and then automatically invokes a response type.
For example, when a customer asks for help during an interaction with your chatbot, the system can immediately display a menu of available options as the response command.You can also add case commands to the IVA, so that the system automatically starts a case in the application based on user input. All suggested cases and suggested responses that you define are topics.
- In the navigation pane of App Studio, click Channels.
- In the Current channel interfaces section, click the icon that represents your existing Digital Messaging channel.
- In the channel, click the Configuration tab.
- In the Content section, select a method for modifying a
response command:
- To add a new response command, click Add response.
- To edit an existing response command, click the Switch to edit mode icon for a response displayed in the list.
- In the Response type list in the Response
configuration window, select and configure a response type:
Choices Actions Authenticate the user in the system - Select Authenticate.
- If you configure multiple languages for the chatbot, select a language for the response text.
- In the Response text area, enter the text that you want to display in the selected language.
- Optional: To configure additional languages for the response text, repeat steps 5.b through 5.c.
- Optional: To add another text to display to the user, below the Response text area, click Add new, and enter additional text.
Cancel the current work in the interaction session - Select Cancel.
- If you configure multiple languages for the chatbot, select a language for the response text.
- In the Response text area, enter the text that you want to display in the selected language.
- Optional: To configure additional languages for the response text, repeat steps 5.b through 5.c.
- Optional: To add another text to display to the user, below the Response text area, click Add new, and enter additional text.
- Optional: To add a command to a menu that the system displays after you cancel current work, click Add item.
- In the Menu item list, select the command that you want to invoke for the menu item.
- In the Label field, enter the menu item name that you want to display in the system.
- Optional: To add more commands that you want to display as menu items, repeat the last three steps.
Display a rich text menu by using a data transform in the IVA for Legacy Webchat - Select Custom.
- In the Data transform field, select
a data transform rule.The rich text menu in the IVA for Legacy Webchat looks similar to a Facebook generic template. The menu consists of a title, subtitle, link to an image, and up to three menu options. You can use the default pyPopulateOutboundData data transform as an example for the IVA.
Link to a specified Facebook account in the IVA for Facebook - Select Link.
- If you configure multiple languages for the chatbot, select a language for the response text.
- In the Response text area, enter the text that you want to display to the user in the selected language.
- Optional: To configure additional languages for the response text, repeat steps 5.b through 5.c.
- Optional: To add another text to display to the user, below the Response text area, click Add new, and enter additional text.
- In the Title field, enter a title for the Facebook account to which you want to link.
- In the Authentication callback URL field, enter the authentication URL for the Facebook account to which you want to link.
Display a menu with a list of available commands - Select Menu.
- In the Menu template list, select to display the menu items as simple menu buttons or quick replies.
- If you configure multiple languages for the chatbot, select a language to define for the response text and menu item labels.
- In the Response text area, enter the text that you want to display to the user in the selected language.
- Optional: To add another text to display to the user, below the Response text area, click Add new, and enter additional text.
- Optional: To add a command to a menu,click Add item.
- In the Menu item list, select the command that you want to invoke for the menu item.
- In the Label field, enter the menu item name that you want to display in the system in the selected language.
- To add more commands to display as a menu item, repeat the last three steps.
- Optional: To specify response text and menu item labels in additional languages, repeat steps 5.c, 5.d, and 5.h.
Restart work on a case that is currently being processed in the session - Select Restart.
- If you configure multiple languages for the chatbot, select a language for the response text.
- In the Response text area, enter the text that you want to display to the user in the selectd language.
- Optional: To configure additional languages for the response text, repeat steps 5.b through 5.c.
- Optional: To add another text to display to the user, below the Response text area, click Add new, and enter additional text.
Display a text message to the user - Select Text.
- If you configure multiple languages for the chatbot, select a language for the response text.
- In the Response text area, enter the text that you want to display to the user in the selected language.
- Optional: To configure additional languages for the response text, repeat steps 5.b through 5.c.
- Optional: To add another text to display to the user, below the Response text area, click Add new, and enter additional text.
- In the Response command field, enter or modify a user
command for the response type.Through text analysis, a user command provides the input that determines the best response command type that the system detects.
- If the response command requires authentication, select the Requires authentication checkbox.
- Click Submit.
- Optional: To add or edit more response commands, repeat steps 4 through 8.
- Click Save.
Previous topic Adding case commands for a conversational channel Next topic Configuring a text prediction for an IVA