9.0.x Release Details

• The refreshed user interface for the Kore.ai Platform – The Virtual Assistant designing features are packaged into Build, Deploy, Analyze and Manage sections, aligning them closely with the development lifecycle. All the features required to build tasks, train, and test are included under the Build menu. Channel enablement, integrations, publish flow, and bot definition management are under the Deploy menu.  Know more.
• Unified NLP Training – A simplified experience for training the Machine Learning and Fundamental Meaning Engines in one place. Intents can be trained using a unified interface, making it easier to switch between utterances, patterns, and rules. Know more.

Following are the enhancements to the entity rules in this release:

• • Ability to accept only ‘month and year’ as input for Date entity (returnOnlyMonthYear)
  • Ability to set preferred format for Date entity to avoid ambiguity scenarios (preferredDateFormat)
    Know more.

Bot training can be further refined by configuring the following additional settings for the NL engines:

• ML Network Types: Introducing Kore Advanced Embedding Network (KAEN)  a model which can understand the meaning of the sentence and at the same time give importance to the domain-specific terminology. Know more.
• Advanced NLP Configurations allow users to fine-tune the NLP engines using advanced controls. The following enhancements have been included in this release:
  • Custom configuration for auto spell correction support for ML predictions. Know more.
  • Additional configurations for the evaluation of the Fundamental Machine Engine Patterns. Know more.
  • Configure Softmax Temperature to define how confidently the ML Engine should identify the winning intent from the ML Model. Know more.
  • Configure Neurons in Hidden Layer to determine the intensity/rigor to be adopted while performing intent identification by the ML Model. Know more.

• Taxonomy based Knowledge Graph – Explore the new approach to build a Knowledge Graph with built-in flows to engage the user in a multi-turn conversation to disambiguate the path and find the right question. Proceed to the Advanced NLP Configurations section to enable this feature. This is a beta release for this feature and a few more updates are expected in the upcoming releases.  . Know more.
• Support for Display Name and Reference Id fields. Display name will be used for presenting the FAQ to the end-users in case of ambiguity while reference id can be used to add a reference to any external content used as a source for a given FAQ. Know more.
• Ability to present all FAQs as ambiguous if only the path is matched and no questions are matched. Know more.
• Ability to customize the order of displaying FAQs for disambiguation. Know more.

• Custom Dashboard now allows for exporting the details of a particular widget as a CSV file which can be shared with others and used for downstream processing. Know more.
• Ability to identify returning users of a bot. Use the isReturningUser parameter in the BotUserSession context object to identify returning users and customize the experience by sending an appropriate welcome message and more. Know more.
• Ability to exclude users or meta tags for filtering NLP Metrics and to view identified traits in the NLP Metrics. Know more.

• New Languages
  • Catalan, Tamil, Hindi, Marathi, and Telugu

• Support for Secure Forms and Password Fields: Enable Secure Form Data to redact form data during execution and from logs.
• The Date component allows you to choose your preferred date format
• The Phone Number component is enhanced to specify Default Country Code.
• The Checkbox component has an option to define the order in which the values are presented to the end-user and Checkbox Layout can be used to display the checkbox values in a grid view.
• Support for Digital Forms has been extended to Sample Bots.
  Know more.

• IVR/Voice Channels:
  • Enhanced voice channel experience with new controls for choosing how to process the input from the ASR Engines.  Know more.
  • Renaming of IVR channel VXML Properties to Call Control properties and extending their support to AudioCodes Channel. Know more.
  • Ability to define Voice Call Properties for fulfilling Sub-intents added to Group Nodes. Know more.
  • Payload enhancements to the async Webhook channel to include endReason, completedTaskId, and completedTaskName. Know more.
• Ability to send proactive messages to the users on Slack and MSTeam channels.

• Enhancements to Session History API to include the Containment Type, count of the Total Messages exchanged, and Tasks completed. Know more.
• New API has been introduced to export the individual billing sessions of a given bot. Know more.

• Introducing support to e-commerce journeys for subscriptions to various plans. Start using the platform with free sessions and pay-as-you-go and be charged only for the consumed sessions. Know more.
• SAML enhancements:
  • Option to map SAML attributes with various Roles and Groups in the Kore.ai account allies for automating the user authentication.
  • Ability to add multiple SAML certificates to support fallback
    Know more
• JWE support has been extended to the Webhook channel. Know more.