This release includes features that help enhance the user experience by enabling intent detection based on Traits and Context Management, event transition based on Sentiment Analysis. Many features have been improved to allow for building better and efficient Bots.

Traits

Kore.ai introduces a new NLP feature called Traits using which bots can identify the attributes/entities which can be inferred from user utterances and improve intent detection. The utterances may not directly convey any specific intent, but the traits present in the utterances can be used to drive the intent detection and bot conversation flow. Learn more.

Sentiment-based event management

Newly introduced bot level sentiment based event feature will now allow you to intelligently identify the changes in the tone of the conversation and automatically perform actions matching the mood of the user. Learn More.

Context Management

You can now configure follow-ups and nested intents across FAQs and dialog tasks. Context management is further improved to handle timeouts against conversations on hold. Learn More.

Other Enhancements

A new Entity – Remote Lookup has been introduced with an ability to call remote services to populate entity values. This entity can be used to perform custom validations through a service call to external systems and then extract the entity value by mapping the response to ‘List of values’ entity. Learn More.
Composite Entities have been enhanced with support for Entity Patterns in addition to Composite Patterns.
Knowledge Collection – Search in Answer configuration will allow the identification of FAQs by matching the user input against the answer section, instead of only matching with questions. This will be applied only if no FAQs are identified from questions. Learn more.
Language Detection: A new in-house algorithm has been implemented for identifying the end-user language.
In addition to the existing platform support for 14 languages, you can now create and publish bots in the Russian, Polish, and Ukranian languages. Learn more.
Fundamental Meaning and Knowledge Collection configurations can be language specific, for Multilingual Bots.
Bot Analytics enhancements (learn more):
- Channel-specific Unique ID is displayed in the Bot Analyze statistics
- Inclusion of Webhook nodes under the ‘Performance’ tab in Analyze module
- Ability to distinguish ambiguity cases in Analyze
Conversation Flow has been enhanced for experience improvements and coverage of interruptions and linked tasks. Learn More.
Knowledge Collection has been enhanced for:
- improved developer experience for extracting and organizing FAQs;
- added support for auto-correction, customization of stop words and engine improvements;
- customizing interruption settings for FAQs;
- handling of deleted FAQs or nodes in the published copy of the Bot.
Improved Meta Tags functionality allows for adding tags from the Bot builder UI for each node and use these tags as filters in insights and metrics pages.
Provision to enable multiple webhook channels has been made. Learn More.
Ability to send unmasked PII data when Agent conversation is in progress. Learn More.
On on-prem installations, the Bot Admin has the option to disable all self-sign options for Bot platform users. Learn More.
>Support for new channels:
- Bots platform now supports WhatsApp as a channel along with On-Prem version of Skype for Business
- Kore.ai platform now supports rich text media messages with images, quick replies and Rich card carousels on SMS channel using RCS Business Messaging.
- Open source enterprise messenger Mattermost is also supported now.
Kore.ai now provides integration with Blue Prism RPA and also LiveBank SDKs