Published Release Notes

New text analytics APIs for Intelligent Virtual Assistant

Pega Platform™ now provides text analytics APIs that separate Intelligent Virtual Assistant and text analyzers into independent modules. This solution prevents integration issues when you change your text analyzer configuration.

For more information, see Text analytics APIs.

Optimized performance of embedded decision strategies

The performance of embedded strategies has now been optimized so that these strategies take less time and fewer CPU and memory resources to complete. This enhancement increases the performance of cloud and on-premises deployments.

For more information, see About Strategy rules.

New method of aggregating real-time events

Event Strategy now uses the approximate median for calculating aggregations. Approximate median calculation replaces the existing method because it requires fewer system resources for saving or loading the event strategy state. In addition, you can now calculate aggregated values by using a new Landmark window type. The window type captures all values of specific event properties from the start of the data flow that references the event strategy.

For more information, see Adding aggregations in event strategies.

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.

Anypicker control in a condition builder

The condition builder now uses the Anypicker control to categorize the entities, such as fields or when conditions, that your application compares at run time. As a result, you can create conditions in a simplified and accelerated way. You can also select fields that are up to four levels deep within field groups.

For more information, see Create conditions faster with an Anypicker control (8.4), Adding an Anypicker control, Defining conditions in the condition builder.

Extended language support in text analytics

Pega Platform™ text analytics now supports 9 more languages. You can build entity and topic detection models to analyze text in the Japanese, Russian, Turkish, Danish, Norwegian, Swedish, Polish, Croatian, and Czech languages. In addition, Pega Platform now includes a default small talk detection model for each of these languages.

For more information, see Language support for NLP and Out-of-the-box text analytics models.

Historical data extraction for adaptive models

Adaptive models now support the extraction of historical customer responses for offline analysis. Additionally, you can use the historical data to build a model in a machine learning service of your choice.

For more information, see Extract historical responses from adaptive models for offline analysis (8.4).

Improved reliability of Visual Business Director

Improvements to the reliability of Visual Business Director (VBD) eliminate the impact of temporary access loss to the VBD cluster. The improvements include the ability to continue writing data to a VBD dataset while the corresponding server node is unavailable, enhancements to single-case data flows that write data to VBD, and a reduction in the VBD cache size.

For more information, see Eliminate the impact of temporary access loss to the VBD cluster (8.4).

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.

Strategies are now available as a condition type in proposition filters

When designing proposition filters, you can now include strategy outcomes as a condition to be evaluated. Select a strategy and specify the component that you want to use as output to include more advanced decisioning in your proposition filters.

For more information, see Enrich your Proposition Filter rules with conditions based on strategy results.