Skip to main content

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

Use the decisioning enabled NLP text analyzer in IVAs and Email Bots (8.3)

Updated on May 3, 2021

Pega Intelligent Virtual Assistants™ (IVAs) and Pega Email Bots™ for conversational channels now support the new intelligent natural language processing (iNLP) text analyzer. This advanced text analyzer is decisioning enabled to help provide quicker and smarter responses. As a result, you can create more sophisticated IVAs and Email Bots that are based on decisioning strategies. The decisioning capability in the system integrates text analytics with strategies, propositions, and interaction history, to provide the context for making better next-best-action decisions. In addition, you now configure the text analyzers for all IVAs and Email Bots on the Behavior tab for each conversational channel.

The following screenshot shows the Behavior tab in the Web Chatbot channel configuration.

Web Chatbot channel - Behavior tab
Web Chatbot channel - Behavior tab

You can reuse a single instance of the advanced Interaction text analyzer in all of the conversational channels, for example, Email Bot, IVA for Facebook, and IVA for Web Chatbot. You can also define a separate text analyzer for Email Bot that performs text analysis of each area of interest, for example, the email body, the email attachments, and the email subject, respectively.

For more information, see Web Chatbot channel behavior, Configuring text analyzer definitions for the Web Chatbot channel, and Defining advanced Web Chatbot text analyzer configuration.

  • Previous topic Process emails in multiple languages in an email bot (8.4)
  • Next topic Copy training data and model to another IVA or Email Bot environment (8.3)

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