Published Release Notes

Support for Cloud AutoML topic detection models

In Prediction Studio, you can now connect to topic detection models that you create in Cloud AutoML, Google's cloud-based machine learning service. You can then use the models to categorize and route messages from your customers.

For more information, see Broaden your selection of topic detection models by connecting to third-party services (8.5).

Control group configuration for predictions

You can now configure a control group for your predictions in Prediction Studio. Based on the control group, Prediction Studio calculates a lift score for each prediction that you can later use to monitor the success rate of your predictions.

For more information, see Customizing predictions.

Response timeout configuration for predictions

You can now set a response timeout for your predictions in Prediction Studio. By setting a response timeout, you control how Prediction Studio registers customer responses that later serve as feedback data for your predictions.

For more information, see Customizing predictions.

External data flow rules are deprecated

External data flows are now deprecated and no longer supported. To improve your user experience with Pega Platform™, the user interface elements associated with these rules are hidden from view by default. Identifying unused features allows Pega to focus on developing and supporting the features that you need.

For more information, see Deprecated: External data flows.

Support for nested Declare Trigger rules

Pega Platform™ now supports nested Declare Trigger rules so that you can conveniently create correlations between actions in your case types. Declare Triggers rules invoke an action when a specified event takes place in a case type. You can now design more complex scenarios faster by nesting more Declare Trigger rules that work in the context of running another Declare Trigger rule. For example, when a case participant changes a postal code in their personal details, a Declare Trigger rule runs and a respective customer service representative (CSR) receives an email. After the CSR receives the email, a nested Declare Trigger rule runs and your application creates a document with the updated personal details and attaches it to the case.

For more information, see Develop applications faster with nested Declare Trigger rules (8.5), Declare Trigger rules.

Visual Business Director data is automatically cleaned after a retention period expires

To avoid negative impact on system resources, such as memory and disk space, Pega Platform™ automatically cleans out collections data accumulated in Visual Business Director after the time period specified in the vbd/dataRetentionTimeout dynamic system setting.

Upgrade impact

In versions of Pega Platform earlier than 8.5, collections data was not automatically removed. From version 8.5, the data is removed after 465 days (15 months) by default.

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

If the default data retention period does not meet your requirements, you can change it by editing the vbd/dataRetentionTimeout setting.

For more information, see "Configuring the data retention period for Visual Business Director" in the Pega Customer Decision Hub 8.5 Upgrade Guide on the Pega Customer Decision Hub product page.

Optimization check utility available for legacy strategies

Ensure that your strategies are compatible with the optimized strategy execution engine introduced in Pega Platform™ 8.1 by running a post-upgrade utility that checks strategies within your application for areas that you can optimize, for example, by reducing the number of page properties that are copied from one shape to another. Running the utility produces a report that you can use to plan the required updates to your strategies.

For more information, see Make your strategies compatible with the optimized strategy execution engine by using a check utility.

Uploading customer responses into adaptive models is no longer available

The option to train adaptive models by uploading a static list of historical interaction records has been deprecated in Pega Platform™ 8.5.

Upgrade impact

In versions of Pega Platform earlier than 8.5, it was possible to train an adaptive model by uploading historical data of customer interaction. After the upgrade to version 8.5, this option is no longer available.

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

Use data from a report definition to train adaptive models. For more information, see Training adaptive models.

More flexibility for Date Time predictors in adaptive models

You can configure adaptive model predictors that indicate the amount of time that has elapsed since a particular event. In versions of Pega Platform™ earlier than 8.5, you could only specify the absolute date and time, for example, the date when a subscriber last visited one of your brick-and-mortar store locations. In Pega Platform 8.5, you can also indicate the amount of time that has passed, for example, the number of days since a subscriber purchased a new service plan.

For more information, see Adding a predictor to an adaptive model.

Support for validations in Declare Expression rules

Pega Platform™ now correctly evaluates validations on target properties in Declare Expression rules. As a result, any validations defined on properties that have Declare Expression rules in previous releases, now work correctly. 

Upgrade impact

Any unintended validations on properties that have configured Declare Expression rules, both default and user-defined, might cause issues in an application upon saving work objects and data objects that refer to Declare Expression rules.

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

If you experience issues when saving objects, debug your application by setting the declareexp/target/validation/disable dynamic system setting to true. If your application works correctly after the change, it means that validations on Declare Expressions cause the issues. For your application to work correctly, analyze the log files and remove any unintended validations.

For more information, see Declare Expression rules.