Chatbot Overview
Conversational Bots
Intents & Entities
Intelligent Bots
Kore.ai's Approach
Kore.ai Conversational Platform
Bot Concepts and Terminology
Natural Language Processing (NLP)
Bot Types
Bot Tasks
Starting with Kore.ai Platform
How to Access Bot Builder
Working with Kore.ai Bot Builder
Building your first Bot
Getting Started with Building Bots
Using the Dialog Builder Tool
Creating a Simple Bot
Release Notes
Latest Updates
Older Releases
Deprecations
Bot Builder
Creating a Bot
Design
Develop
Storyboard
Dialog Task
User Intent Node
Dialog Node
Entity Node
Supported Entity Types
Composite Entities
Supported Time Zones
Supported Colors
Supported Company Names
Form Node
Logic Node
Message Nodes
Confirmation Nodes
Service Node
Custom Authentication
2-way SSL for Service nodes
Script Node
Agent Transfer Node
WebHook Node
Grouping Nodes
Connections & Transitions
Managing Dialogs
User Prompts
Alert Tasks
Alert Tasks
Ignore Words and Field Memory
Digital Forms
Digital Views
Knowledge Graph
Terminology
Building
Generation
Importing and Exporting
Analysis
Knowledge Extraction
Small Talk
Action & Information Task
Action Tasks
Information Tasks
Establishing Flows
Natural Language
Overview
Machine Learning
Model Validation
Fundamental Meaning
NLP Settings and Guidelines
Knowledge Graph Training
Traits
Ranking and Resolver
NLP Detection
Advanced NLP Configurations
Bot Intelligence
Overview
Context Management
Session and Context Variables
Context Object
Dialog Management
Sub-Intents
Amend Entity
Multi-Intent Detection
Sentiment Management
Tone Analysis
Sentiment Management
Default Conversations
Default Standard Responses
Channel Enablement
Test & Debug
Talk to Bot
Utterance Testing
Batch Testing
Record Conversations
Publishing your Bot
Analyzing your Bot
Overview
Dashboard
Custom Dashboard
Conversation Flows
Bot Metrics
Advanced Topics
Bot Authorization
Language Management
Collaborative Development
IVR Integration
Data Table
Universal Bots
Defining
Creating
Training
Customizing
Enabling Languages
Smart Bots
Defining
Sample Bots
Github
Asana
Travel Planning
Flight Search
Event Based Bot Actions
koreUtil Libraries
Bot Settings
Bot Functions
General Settings
PII Settings
Customizing Error Messages
Manage Sessions
Bot Management
Bot Versioning
Using Bot Variables
API Guide
API Overview
API List
API Collection
SDKs
SDK Overview
SDK Security
SDK App Registration
Web SDK Tutorial
Message Formatting and Templates
Mobile SDK Push Notification
Widget SDK Tutorial
Widget SDK – Message Formatting and Templates
Web Socket Connect & RTM
Using the BotKit SDK
Installing
Configuring
Events
Functions
BotKit SDK Tutorial – Agent Transfer
BotKit SDK Tutorial – Flight Search Sample Bot
Using an External NLP Engine
Bot Administration
Bots Admin Console
Dashboard
User Management
Managing Users
Managing Groups
Managing Role
Bots Management
Enrollment
Inviting Users
Bulk Invites
Importing Users
Synchronizing Users from AD
Security & Compliance
Using Single Sign-On
Security Settings
Cloud Connector
Analytics
Billing
How Tos
Creating a Simple Bot
Creating a Banking Bot
Transfer Funds Task
Update Balance Task
Context Switching
Using Traits
Schedule a Smart Alert
Configure Digital Forms
Add Form Data into Data Tables
Configuring Digital Views
Add Data to Data Tables
Update Data in Data Tables
Custom Dashboard
Custom Tags to filter Bot Metrics
Patterns for Intents & Entities
Build Knowledge Graph
Global Variables
Content Variables
Using Bot Functions
Configure Agent Transfer
  1. Home
  2. Docs
  3. Bots
  4. What's New
  5. What’s New

What’s New

This section contains release information for the Kore.ai Bots Platform v8.1 released on Feb 20th, 2021.

See Major Previous Releases

Highlights

  • Contextual NLU – New features have been introduced to simplify the designing of complex Contextual NLU experiences like follow-ups, digressions, and amending of entities. These features include – Different Intent Model configurations for Bot level and Dialog level intents; Scoping, training, and fulfillment of contextual intents, and much more.
  • End-user can be provided with an improved entity behavior through customization of prompts and error messages and much more.

NLU & NLP Features

  • Contextual NLU
    • Enhanced Group Node functionality to enable scoping, training, and control the behavior of sub-intents. These features would ensure an improved user experience with follow-ups, digressions, and amending entity values. Know more
      For an use case example, refer here.
    • Support for Multiple Intent Models within a virtual assistant to simplify the training of sub-intents without adding noise or impacting the training given for the primary intents of your bot. In this approach, all the primary intents of the bot can be a part of the Bot Level Intent Model, and each of the Dialog tasks can have its own ML Model consisting of all the sub-intents added to it. Know more.
    • Support for training sub-intents with entities using NER. Know more.
  • Bot training can be refined by configuring the following additional settings for the NL engines:
    • With the ability to customize the Ranking and Resolver Engine configurations, you can now choose the elimination rules, normalization of scoring, and thus control the winning intent selection behavior. Know more.
    • Network Type, Transformer, has been introduced to support sentence encoder. Know more.
    • Export option for the K-fold cross-validation reports has been introduced. Know more.
    • Trait support in Batch Testing has been enhanced. This includes the result of a true positive when the traits are matched over and above the expected matches. Know more.
    • Support for understanding emojis present in the user utterance. Know more.
  • Entity Behavior
    • Entity Rules can be defined to enable business rules for validating the input for an entity node. Earlier these rules had to be set using a script node, now you can define these rules from the Instance Property of the Entity Node. Know more. For more information regarding the supported entity rules, refer here.
    • Retry behavior when fetching user inputs can be customized in terms of the number of retries allowed and the bot behavior when a user exceeds the retry limit. Know more.
    • The order in which the error prompts are presented to the user in the event of a wrong entry for an entity value can be customized. Know more.
    • Default values can be set for Hidden and Optional entitiesKnow more.
    • The entities identified from user utterances can be replaced with the respective entity placeholders for better intent detection. Know more.
    • Support has been extended to include the formatted address in the context for the Address entity. Know more.
    • Company entity has been enhanced to include a bigger corpus, support language-specific variations, and better grouping of the companies and new entity rules. Know more.
  • Language Updates
    • Support for the Norwegian language.
    • Support for the Hindi language.

    Know more

Bot Development and Lifecycle Management Features

  • Bot Definition Management
    • In the Debug Logs, now you can view the details of the Chat History associated with the session for which the logs were added. Know more.
    • The message presented to the end-user for obtaining authorization to connect to external systems can be customized using the koreUtil.getCurrentOptions() function. Know more.
    • In Custom Dashboard, to simplify the promotion of versions between environments,  you can now create a custom widget using Custom Tags that are not yet available. Be aware that the widget would be rendered empty till the custom tag is populated. Know more.
    • Ability to set the custom message (instead of the original message) in the Chat History when the message is modified in the BotKit before sending to the user. Know more.
    • Different user conversation sessions, for example, pre-login user sessions and post-login user sessions,  from SDK Channel can be merged giving a seamless user experience.
  • New APIs have been made public to assist the bot versioning and bot promotion between environments:
    • API to modify the Thresholds and Configurations, and Advanced NLP Settings. Know more.
    • API to create, run and manage Batch Test Suites. Know more.
    • API for enabling Web/Mobile SDK, Webhook, Slack, and MS Teams channels. Know more.
  • Universal Bot functionality has been enhanced to include the following:
    • Ability to define ML Threshold per linked bot so that the NLP experience can be customized based on the training provided for each of the linked bots. Know more.
    • You can now use the SDKs to define the linked bots to be made eligible to your users when interacting with the Universal Bots. Know more.
    • In addition to the Universal Bot’s Default Dialog, you can now choose the tasks from any of the linked bots to define the behavior of the events. Know more.

Administration and Security Enhancements

  • Audit logs have been enhanced for capturing User Management changes triggered using Public APIs
  • You can choose to secure the connections with the platform by enforcing JTI Claims and/or JWE Encryption. Know more.
  • Support has been extended for Multi-region active-active deployment (For on-prem customers)
  • The ability to store multiple value sets for Environment Variables has been added. This can be used so that an appropriate variable set can be selected while promoting the bot definition to a different environment without manual intervention. (For on-prem customers). Know more.

SDK Versions

The following is the recommendation for the versions compatible with this release:

Release Details

For a full list of updates made in this release, refer here.

Deprecations

  • Kore.ai Directory Agent for AD Sync will no longer be supported and will be discontinued in the upcoming release. You can use the cloud-based connector or use Public APIs for synchronizing your users. Refer here for details on cloud connector and here for details on user management APIs.

See here for details.

Menu