Skip to main content


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

Troubleshooting the conversational channel

Updated on March 3, 2022

Perform tasks in Pega Intelligent Virtual Assistant™ (IVA) to address problems, troubleshoot accessibility issues, adjust the accuracy of chatbot responses, and ensure that the system works as expected. As a result, you improve the quality and health of your chatbot, which helps users to interact with your application more easily when they want to resolve their problems.

For example, you can help the system become more responsive to users by addressing an issue in which the chatbot is not always detecting the correct topics.
Before you begin: Create and configure the IVA, train the text analytics model, and simulate a conversation with the chatbot in the preview console. For more information, see Creating a Unified Messaging channel, Defining conversational channel behavior, and Training the model for the IVA channel. Channel developers and channel administrators update, troubleshoot, and maintain the IVA when the system is in a development, QA, or production environment.
Design Patterns: To learn more about troubleshooting natural language processing (NLP) issues in your chatbots, see also Troubleshooting NLP.
  • Previous topic Best practices for cleaning up training data in an IVA
  • Next topic Troubleshooting conversational channel issues

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.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us