This section contains release information for the Kore.ai Experience Optimization Platform v9.3 released on July 23rd, 2022.
This update includes new features and enhancements to enable the operations and business users proactively monitor and improve the performance of the virtual assistants using actionable insights from the platform.
The following are some of the key features included in this release:
Virtual Assistant Health and Monitoring
The new Health and Monitoring feature provides a goal-driven approach to improve the accuracy of the virtual assistant’s NLP model. The training data is analyzed along with the test coverage and test results of the Batch Test suites to provide insights into the performance of the NLP Model. The feature also recommends corrective actions to address issues identified in the training data. Learn more.
The training data validations now include incorrect intent patterns, short training utterances, and incorrect entity annotations. Learn more.
The Batch Testing feature now provides a visual summary of the test results along with the test coverage details. You can also review the test execution summary for every intent type, drill-down to specific test cases, view the expected and matched results, and view the detailed NLP analysis. You can also tag specific test case results that need follow-up actions and collaborate with your team to improve the performance. Learn more.
The new Overview Dashboard provides a summary of key metrics like conversations and containment, users, intent identification rate, goal completion rate, and more. You can also drill down to the individual dashboards to view complete information. Learn more.
The new Users Dashboard provides the trend of the number of users interacting with the virtual assistant. The dashboard also provides the trend of new users of the virtual assistant and also provides cohort analysis of the Returning Users. Learn more.
The Analyze module now has a new navigation menu to easily navigate between various dashboards. Learn more.
The new Conversations History module feature helps you analyze the user interactions by summarizing the key events identified during the conversation. Intent identifications, entity or confirmation retries, task execution failures, etc., are some of the key events tracked. Along with the summary, you can also see the complete conversation transcript to make data-driven decisions. You can also tag conversations that need follow-up actions and collaborate with your team to resolve them. Learn more.
The new Unhandled Utterances section in the NLP Insights feature captures the utterances that did not result in intent or entity identification while executing entities or confirmations. These utterances help you identify any potential issues in the conversation design or new use cases for your virtual assistant. Learn more.
Custom Training for None Intent
The None Intent can now be trained to include the FAQs from Knowledge Graph to avoid potential conflict between the dialog and FAQ intents. You can also train the None Intent with your custom training utterances to cover any use cases that are currently not part of your virtual assistant. The None Intent configuration is moved from the Advanced Configurations to the Machine Learning configurations section. Learn more.
Sunshine Conversations Channel
The Kore.ai XO Platform supports the Sunshine Conversations (previously Zendesk Sunshine) Messaging Channel to launch your virtual assistants. OAuth-based authorization for channel integration and in-built live agent transfer to Zendesk via Switchboard are now supported. Learn more.
WhatsApp Messaging Channel for Infobip
The Kore.ai XO Platform now allows the user to add and delete up to 20 phone numbers to the same virtual assistant for Infobip on the WhatsApp Messaging Channel. The Platform will automatically respond to the ‘from number’ (source number) in the incoming request. Learn more.
Change of Account/Workspace Ownership
The platform now allows enterprise account/workspace owners to transfer the ownership to another registered user by assigning the ‘Primary Master Admin’ role. Learn more.
Contextual Topic Guides
You can now access learning resources like training courses, videos, and FAQs about various modules from the Topic Guides section. Look for the shortcut icon next to the module name to open contextual Topic Guides. Learn more.
NLP Training Updates
This update also includes the following updates to the NLP training modules
- The platform now supports out-of-the-box Bot Synonym lists for Simplified Chinese and Traditional Chinese languages. Learn more.
- The Address entity includes the full formatted address for you to easily parse specific parts of the address like city name, country name, etc. Learn more.
- The Phone Number entity is enhanced to accept additional formats. Learn more.
Web Client SDK 2.0 – New Framework
The Web SDK Client is upgraded to v2.0 to include a significant number of enhancements. Some of the key updates are:
- Customize Templates using Angular or ReactJS frameworks.
- Adopt the plug-in based architecture to integrate only the required features. For example, you can use the Graph Templates plug-in, Pickers plug-in, STT/TTS features distributed as plug-ins
- Supports easy deployment by embedding the script tag on your website code.
You can learn more about the Web SDK 2.0 from here.
Discontinuation of Universal Bots 1.0 Version
The 1.0 version of Universal Bots is no longer supported. These bots will be auto-migrated to the 2.0 version as part of this release.
The following are the new features and enhancements for managing Process Assistants:
Introduction of Portal User Role
You can now invite a new user to a Process App with the ‘Portal User’ role. Users with this role can only access the portal to create or manage process instances. Learn more.
Add Multiple Alert Recipients
The Process Assistants now support adding multiple recipients to the Notify (To) field in the Alerts section while drafting an instance failure notification message. Learn more.
Adding Nodes to Process Builder
The Process Assistants now allow users to add a node between the process flow steps with a simple drag-and-drop action. Learn more.
Process Failure Notification Delivery
Process Assistants can now deliver the failure notifications to an external application/endpoint by defining an API request. Learn more.