Skip to main content

         This documentation site is for previous versions. Visit our new documentation site for current releases.      

Adding a stand-alone conversation process for a conversational channel

Updated on August 10, 2021

To improve and simplify how Pega Intelligent Virtual Assistant™ (IVA) collects information for your application, create and configure a stand-alone conversation process. By adding a conversation process to your channel, your chatbot interacts with users in a consistent, logical, and conversational way by asking questions, displaying text, or starting another conversation process.

For example, you can create a stand-alone conversation process for a chatbot that asks users their location in the United States and as a result, sends the users a message with the correct contact telephone number for your organization in the specified location.
Before you begin: Create and configure an IVA channel for Digital Messaging or Legacy Webchat.
You can also create a conversation process for a case type in your application. As a result, the system automatically responds to chat messages in the context of a case and saves user responses in the case properties. For more information, see Adding a case type conversation process for a conversational channel.
Note: You can reuse a stand-alone conversation process that you save in the system in another IVA channel for your application.
  1. In the Digital Messaging or Legacy Webchat channel, click the Configuration tab.
  2. In the Conversation flows section, click Add conversation.
  3. In the Create conversation window, in the Name list, select Create new conversation.
  4. In the New conversation name field, enter a name for the conversation process, and then click OK.
  5. In the Conversation command list, enter a name for the response command for the conversation process, and then click Submit.
  6. In the Conversation flows section, in the Flow name column, click the name of the conversation process that you created in the previous steps.
  7. In the flow canvas, modify the primary path in the conversation process by connecting and configuring the following conversation shapes:
    Ask a question
    Asks a question to the user in the chatbot in a button, quick reply, yes/no, or open format, and saves the answer in case properties.
    Send a message
    Displays a text message to the user.
    Conversation flow
    Starts another existing conversation process within the flow that is either stand-alone or for a case type.

    You can also configure additional useful shapes that are available in the context of the conversation. For more information, see Editing the conversation smart shapes and Flow shapes.

    For example: The following figure shows a conversation process for a chatbot that uses conversation shapes to ask users their location in the United States and display a contact telephone number for each location.
    A conversation process with conversation smart shapes
    A conversation process with three Send a message shapes and one Ask a question shape.
  8. Optional: To test the created flow that includes the conversation shapes in the preview console, in the top-right corner of the page, click the Run conversation icon.
    For more information about using the preview console to simulate a conversation, see Simulating a conversation and building a chatbot.
  9. Click Save.
  10. Optional: To display chatbot details on the Configuration tab, in the conversation flow toolbar, click Go back.
For example:

The following video demonstrates improvements in the chatbot authoring experience. You will learn how to use the new smart shapes to build a conversation process for an IVA:

What to do next: Add case commands to the IVA. For more information, see Adding case commands for a conversational channel.

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best. is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us