Published Release Notes

Automatic model training when mapping entities to case properties in Email Bot

You can now initiate automatic feedback to entity models in Pega Email Bot™, during manual mapping of email content to a case property.

To enable automatic feedback, you set the Work-Channel-Triage.pyIsRuntimeFeedback rule to true in Pega Platform™. By default this feature is disabled. Enabling this feature ensures that the email bot is more responsive by automatically copying detected entities, such as names, locations, dates, and ZIP codes, to case type properties of a case type.

For more information, see Email triage, Email channel NLP model and Enabling the NLP model training for the email channel.

Email bots now support multiple languages

You can now configure Pega Email Bot™ to perform text analysis, use training data and triage emails in multiple languages, for example, English, French, German, and Spanish. By detecting topics and entities from emails in different languages, the system can suggest the correct business case and provide an email response in the user's own language.

For more information, see Selecting languages for an Email channel and Enabling automatic language detection for text analysis.

Support for seamless transitions between IVAs and customer service representatives

To ensure the best user experience in chat sessions with a Pega Intelligent Virtual Assistant™ (IVA), customer service representatives (CSRs) can now step in and take control of a chat session multiple times, when the chatbot is not capable of correctly answering the user. After the user problem is resolved, the CSR can seamlessly switch control of the chat session back to the chatbot.

Rules can no longer access Pega internal Java packages

You can no longer create rules that access Java packages that reference internal APIs (syntax com.pega.platform.*.internal*). This change does not affect rules that access Pega public API packages.

If you encounter issues when running existing rules that reference internal Pega APIs, contact Pega Support.

Upgrade impact

After an upgrade to 8.4 and later, clients can no longer save new or modified rules that access Pega internal APIs; existing rules that reference internal APIs can still be run but cannot be modified. 

What steps are required to update the application to be compatible with this change?

Following a software upgrade to 8.4 or later, clients can refactor existing rules into guardrail compliant rules. To find rules to refactor, run the validation tool from designer studio (Application > Tools > Validation) to identify what rules fail validation; failed rules that include the message "Test compilation failed : Illegal internal class reference : com.pega.internal.XYZ" can updated to reference appropriate APIs.

Unified Messaging Desktop integration with Pega Platform

You can now use the Pega Unified Messaging Desktop™ customer service solution with a Pega Platform™ application so that customer service representatives (CSRs) and other users, such as managers, can respond to user requests more quickly and in a more consistent manner. With integrated Pega Unified Messaging Desktop, CSRs can escalate user requests from Pega Intelligent Virtual Assistants™ (IVAs) by using case processing and artificial intelligence alongside Pega Customer Service™

For more information, see Develop a single IVA channel to chat across different messaging platforms.

Client-server deployment of Hazelcast

Pega Platform™ now supports the client-server model for the Hazelcast service, which provides cluster communication and distributes Pega Platform features across nodes. This optional deployment model introduces independent scalability for both servers and clients in Pega Platform, improving stability for deployments that use a large number of nodes.

The Hazelcast client-server model is intended for select environments running Pega Platform 8.4 across a large number of nodes and should be deployed only when directed by Global Client Support.

Reports with visualizations of performance and automation levels for the email bot

In the Email Manager portal, you can now use built-in reports to visualize Pega Email Bot™ performance and the automation levels that are related to received emails, triaged cases, and created business cases. You can plug the reports to display the report data in other portals, for example the Case Manager portal. Based on the information displayed in the reports, you can adjust the machine learning models to achieve greater automation in the system.

For more information, see Viewing the reports for the Email channel and Built-in reports for the email bot.

Automatically update dependent applications to use the latest versions of built-on applications

You can now automatically update dependent applications to use the latest versions of built-on applications. When you import an archive that you created from a product rule, you can update all dependent applications to be built on the latest application versions in the archive.

For more information, see Updating dependent applications with the latest versions of built-on applications.

Improved experience when building an IVA and Email Bot in App Studio

Build your Pega Intelligent Virtual Assistant™ (IVA) and Pega Email Bot™ while working only in App Studio. This approach makes the design process easier and more intuitive, and saves you time. You can now modify the advanced text analyzer configuration while working in App Studio. In addition, if you have access to Dev Studio, you can edit the text analyzer rule from App Studio for your chatbot or email bot by clicking a link to open the settings in Dev Studio.

For more information, see Adding a text analyzer for an email bot and Adding a text analyzer for an IVA.

Triage cases archiving in the email bot (Pega Cloud Services)

For Pega Platform™ that is installed in Pega Cloud^® Services, you can configure Pega Email Bot™ to archive resolved triage cases that are older than a specified number of days. Archiving triage cases improves the overall performance of your system by reducing the primary storage consumption and cost because the system places such resolved triage cases in a secondary storage.

For more information, see Archiving resolved emails for an email bot (Pega Cloud Services).