Published Release Notes

Data flow runs retry connections that fail

Real-time and batch data flow runs now retry dataset connections that fail when the related service is temporarily unavailable, for example, when a connection to a Cassandra database times out. With the automatic retries, you no longer need to run data-heavy and CPU-intensive jobs multiple times and the maintenance of data flow runs diminishes significantly.

For more information about accessing event details, see Creating a real-time run for data flows and Creating a batch run for data flows.

Optimized performance of decision strategies

Strategies that are part of data flows are now automatically optimized to achieve the best performance. You can also choose the properties that a strategy outputs to further increase the efficiency without additional strain on your hardware. 

For more information, see Adding strategies to dataflows. 

Improvements to the Email channel configuration and content analysis

To make the Intelligent Virtual Assistant™ (IVA) for Email more useful and easier to manage, you can track all the Email channel configuration changes that you or other operators make. The system now also detects defined entities and topics, not only in the contents of the email messages and its attached files, but also in the email subject field which improves the responsiveness of IVA to emails. You can map same text that appears in an email triage case to different entities. In previous versions of Pega Platform, only the email body was analyzed but with subject analysis, now the entire email is analyzed for topics and entities, including its salutation and signature.

For more information, see Tracking configuration changes in the Email channel and Enabling the analysis of subject field content during email triage.

Facebook and Web Chatbot configuration in the preview console

When you develop a Pega Intelligent Virtual Assistant™ (IVA) for Facebook or Web Chatbot, you can now teach interactive bot conversations by chatting with the bot in the preview console and guiding the artificial intelligence algorithm to the right responses. This ability greatly accelerates conversation development and simplifies configuration, while providing the developer with more transparency in the mechanisms that produce specific responses.

For more information, see Simulating a conversation and building a chatbot runtime and Testing and building a chatbot from the preview console.

Support for rich user interface controls in IVA for Web Chatbot

You can now use rich user interface controls in Pega Intelligent Virtual Assistant™ (IVA) for Web Chatbot because Pega Platform™ includes a framework for advanced user interface controls. You can use a date picker control and add file attachments while chatting with the chatbot. These features provide a richer and more robust user experience and they help the user accomplish tasks more quickly without the need for complex validation messages.

For more information, see Use rich user interface controls in Web Chatbot.

Analyze decision components with simulation tests

Gain a better understanding of how strategy components influence decision outcomes by using decision funnel explanations. By running simulation tests with the new Decision funnel explanation purpose, you can now break down the results of a decision funnel into granular analyses to assess how certain components and expressions influence the overall outcome.

For more information, see Interpret the decision funnel with simulation tests.

Support for rich HTML text in IVA for Email

Pega Intelligent Virtual Assistant™ (IVA) for Email now supports rich HTML text in email conversations, which enhances the overall user experience. You can enable this option in the Email channel configuration in IVA for Email to display rich text in email conversations for case triaging. Natural language processing (NLP) analysis works flawlessly in scenarios for all email content that contains rich HTML text.

For more information, see Enabling rich HTML text in emails.

Multiple actions triggering during intelligent email routing

Pega Intelligent Virtual Assistant™ (IVA) for Email now supports triggering of multiple actions during the intelligent routing of incoming emails, which improves the artificial intelligence capability of IVA for Email so that it is more responsive to user input. For example, you can set up intelligent routing for an Email channel to trigger multiple actions, such as creating a case and automatically replying to an email for the content that you receive.

For more information, see Intelligent email routing, Configuring routing conditions for automatic email handling, and Setting up intelligent routing in Intelligent Virtual Assistant for Email.

Support for machine learning as a service models

In Pega Platform™, you can now run advanced machine learning and artificial intelligence models that you develop in third-party tools. By configuring a connection with an external machine learning as a service provider, such as Google AI Platform, you can use the predictive power of your custom models to improve the predictions in your customer strategies.

For more information, see Connecting to a Machine Learning as a Service model and Configuring a machine learning service connection.

Improved rich user interface controls in IVA for Web Chatbot

In Pega Intelligent Virtual Assistant™ (IVA) for Web Chatbot, you can use additional rich user interface controls, such as the time and date picker or a simple form, to help users accomplish tasks more quickly and to limit errors. IVA for Web Chat can now also display a welcome message in the chat window, for example, to inform the user about the person with whom they are chatting.

For more information, see Streamline conversations in IVA for Web Chatbot with rich user interface controls.

Upgrade impact

The new Ul controls for Web Chatbot are enabled by default upon upgrade. If you do not want the controls enabled, you must disable them.

Also, if you have changed the styles for the welcome message, you may need to make changes to the welcome message to incorporate the new areas in the bot conversation area (such as quick replies).

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

Existing channels will behave as they did previously, so you should determine whether you want to use the new UI controls. If you want to use the new Ul controls, configure the new design-time options.

If you have changed the default styles for the welcome message, review the new settings to ensure that the welcome message is configured properly.