GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Help & Learning Resources
Release Notes
Current Version
Recent Updates
Previous Versions
Deprecations
Request a Feature
CONCEPTS
Design
Storyboard
Overview
FAQs
Conversation Designer
Overview
Dialog Tasks
Mock Scenes
Dialog Tasks
Overview
Navigate Dialog Tasks
Build Dialog Tasks
Node Types
Overview
Intent Node
Dialog Node
Dynamic Intent Node
GenAI Node
GenAI Prompt
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections
Node Connections Setup
Sub-Intent Scoping
Entity Types
Entity Rules
User Prompts or Messages
Voice Call Properties
Knowledge AI
Introduction
Knowledge Graph
Introduction
Terminology
Build a Knowledge Graph
Manage FAQs
Knowledge Extraction
Import or Export Knowledge Graph
Prepare Data for Import
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Knowledge Graph Analysis
Answer from Documents
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Intent Discovery
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
Intelligence
Introduction
Event Handlers
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentinment Management
Tone Analysis
Default Standard Responses
Ignore Words & Field Memory
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Conversation Testing Overview
Create a Test Suite
Test Editor
Test Case Assertion
Test Case Execution Summary
Glossary
Health and Monitoring
NLP Health
Flow Health
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Dashboard Filters
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
Create Custom Dashboard Filters
LLM and Generative AI Logs
NLP Insights
Task Execution Logs
Conversations History
Conversation Flows
Conversation Insights
Feedback Analytics
Usage Metrics
Containment Metrics
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Team Collaboration
Plan & Usage
Overview
Usage Plans
Templates
Support Plans
Invoices
Authorization
Conversation Sessions
Multilingual Virtual Assistants
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Feedback Survey
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
HOW TOs
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
Design Conversation Skills
Create a Sample Banking Assistant
Create a Transfer Funds Task
Create a Update Balance Task
Create a Knowledge Graph
Set Up a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Add Data to Data Tables
Update Data in Data Tables
Add Data from Digital Forms
Train the Assistant
Composite Entities
Use Traits
Use Patterns for Intents & Entities
Manage Context Switching
Deploy the Assistant
Configure an Agent Transfer
Use Assistant Functions
Use Content Variables
Use Global Variables
Intent Scoping using Group Node
Analyze the Assistant
Create a Custom Dashboard
Use Custom Meta Tags in Filters
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
SDK Security
SDK Registration
Web Socket Connect and RTM
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
SDK Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
Widget SDK Tutorial
Web SDK Tutorial
ADMINISTRATION
Introduction to Admin Console
Administration Dashboard
User Management
Add Users
Manage Groups
Manage Roles
Data Tables and Views
Assistant Management
Enrollment
Invite Users
Send Bulk Invites
Import User Data
Synchronize Users from AD
Security & Control
Using Single-Sign On (SSO)
Two-Factor Authentication (2FA)
Security Settings
Cloud Connector
Analytics
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Advanced Topics
  5. Universal Bot
  6. Defining a Universal Bot

Defining a Universal Bot

Kore.ai’s Universal Bots facilitate a scalable, modular approach to bot building by linking several standard individual bots into one.

  • Modularity: Build separate bots that address domain-specific issues and then integrate them to optimally interoperate.
  • Scalability: Start building bots that address key use cases and keep adding additional bots to address more use cases.

Before starting with creating a Universal Bot, let us understand how Universal Bots work and how they differ from Standard Bots.

Bot Behavior

Universal bot responses vary with the number of bots and tasks that match the user intent along with their relevance (exact matches or suggestions). The Natural Language Processing (NLP) engine processes the utterances sent to the linked bots, detects the user intents, and ranks them based on relevance. As a developer, you can test and train the bot responses as explained in Test the Universal Bot.

Following the table shows how universal bot responses operate in various possible NLP outcomes:

NLP Outcome Bot Response
Only one exact match found from any of the linked bots Executes the task with the exact match
Exact matches found in more than one linked bot Tries to match the invocation names from the user utterance with the bot results, else prompts the user to select one.
Exact matches found with two or more tasks of a single linked bot Disambiguates using the current bot context, else prompts the user to select one.
Suggestions found in more than one linked bot Evaluates the individual scores and executes the winning intent based on the P&R settings.
Suggestions found with two or more tasks of a single linked bot Executes the winning intent based on the P&R settings.
Only one suggestion found Shows the suggestion to the user asking if they would like to select it
No exact match or suggestion found Checks for intent in the Universal Bot – small talk or fallback bot

Standard Bots vs. Universal Bots

Universal Bots connect multiple Standard Bots into a single bot. They support most Standard Bot features with a few exceptions.

Enabled Features and Configurations

This section assumes that you understand the fundamentals of standard bots. Details relevant to the Universal Bots alone are listed here. We recommend you to refer to the relevant standard bot documentation for help with the basics.
The Feature column entries in the following table provide URLs to the standard bot documentation.
The Learn more links in the Description column refer to the universal bot documentation.

Feature Description
Natural Language
Testing Since the universal bot links together standard bots, the Natural Language Processing (NLP) settings are optimized to accurately recognize the relevant bot and intent. You can test and train the universal bot like a standard bot with small differences. When you train the task it happens at the linked bot level. Learn more.
Training

(UB 2.0)

Post ver7.3 of the platform, the Universal Bot 2.0 can be trained, the approach is slightly different from the standard bots. Learn more.
Standard Responses The universal bot will hold a limited set of standard responses that are relevant to bot level functions like greetings. Go to Natural Language -> Default Conversation, to access the Standard Responses section to edit the relevant standard responses.
Batch Testing Universal bots only support testing Custom-defined utterances and not Developer-defined utterances and Succesful user utterances.
The Custom-defined utterances test suites remain similar to the standard bots’ except that the JSON Dataset file that you upload should contain a bot name along with the intent and input for every test case. Also, the downloaded batch test report shows the results with corresponding bot names.
Default Dialog Universal bots come with a default dialog task that gets triggered for unidentified intents. You can customize this task or import a new one. Learn more.
Event-Based Bot Actions With ver8.0, you can choose different tasks from the linked bots for various events. Learn more.
Help When a user types Help during a chat, a standard bot responds with the list of tasks that it can perform, allowing the user to select a task name to execute.

When it comes to Universal bots, if a user types Help, the bot responds with the names of linked bots. The user cannot select or execute a task from the list.

Channel Configuration
All Universal bots do not obtain the channel configurations of the linked bots and need an independent channel configuration. You can set up new channels for the universal bot independent of the linked bot channels. The published tasks in the linked bots execute from the universal bot channels. Learn more.
Settings
General Settings Universal and standard bots share the same general settings.
Language Management Universal bots do not obtain the enabled languages of the linked bots. You must enable default and additional languages explicitly for the universal bot. But when user utterances are made in an enabled language, the universal bot routes it to only those linked bot tasks that support the language. For example, if German is enabled for the universal bot and a user utters in German, the NLP engine looks for all the linked bot tasks that support German and sends the utterance to those tasks. Learn more.
Developer Collaboration Works similar to standard bots. Once you share a Universal Bot with other developers, they can link and unlink bots.
Change Logs Universal bot change logs record all the changes applicable to the standard bots, plus the following:

  1. Linking of a bot
  2. Un-linking of the bot
  3. Change to default dialog
  4. Publishing of default dialog
Import & Export bot

(supported from ver7.1)

Like standard bots, you can export and import the published and unpublished universal bots. Since universal bots deal with linked bots the following need to be taken care of:

  • Export of a universal bot – only the reference to the linked bot (reference id) will be included not the entire linked bot definition;
  • Import of the universal bot – in the environment where the bot is being imported to, the platform checks for the bots with reference id matching the linked bot. If found they are automatically linked to the imported universal bot. Also you should have permissions for the linke bot, else it will not be linked. Ensure that you import the linked bots before importing the universal bot.
Delete bot Like standard bots, you can delete the unpublished universal bots.
Variable Management

(UB 2.0)

Like standard bots, you can define global and content variables in universal bots. In addition, you can choose whether or not the variables can be propagated to the linked bots.
API Extensions
SDK toolkit Enabled with the following events – on message, on hook, on event, on alert
Agent Transfer Agent Transfer can be configured for a Universal Bot. The Agent Node needs to be added in default dialog and addition of any subsequent nodes after the agent node is not allowed.
WebHook Node Multiple webhook nodes can be placed in the default dialog. When a webhook node is reached during the conversation, the platform invokes the BotKit similar to that of a Standard Bot.
SDK as Channel Enabled
Analyze
Chat History All the Universal Bot chats get recorded. Any initiated training will affect the individual linked bot.
Publish
All You can select one or more linked bots and publish the Universal Bot. Learn more about the publish flow.

Event Management

Let us see the behavior of Universal Bots for the following BotKit events in Linked Bots:

  • End of Conversation (see below)
  • On Message
  • Agent
  • Webhook
  • Event
  • Alert Events

When a child bot is in context i.e., a task from a child bot is in progress, then the events related to the child bots will be triggered based on the configurations set up by the developer:

  • If an event is enabled in child bot, then the event will be forwarded to child bot BotKit
  • If an event is not enabled in child bot and
    • if that event is enabled in Universal bot, then the event will be sent to Universal bot BotKit
    • if that event is not enabled in Universal bot as well, then the event will not be forwarded to any BotKit.

Following table summarises the above scenarios and behavior:

Event Name Child Bot Status Universal Bot Status Expected Behavior
On Message Enabled Event sent to child bot BotKit
Disabled Enabled Event sent to Universal BotKit
Disabled Disabled Invalid scenario. The event does not trigger in this case
All other events Enabled Event sent to child bot BotKit
Disabled Enabled Event sent to Universal BotKit
Disabled Disabled Same as the current behavior. E.g. dialog reaches Webhook node but ‘on Hook’ event is not enabled

End of Conversation

The following table depicts the bot behavior for the end of the conversation event:

Conversation ends End of Conversation Event in Universal Bot End of Conversation Event in Linked Bot Behavior
Universal Bot Enabled Enabled or Disabled Trigger event in Universal Bot
Universal Bot Disabled Enabled or Disabled No event triggered
Linked Bot Enabled or Disabled Enabled Tigger event in Linked Bot
Linked Bot Enabled Disabled Tigger event in Universal Bot
Linked Bot Disabled Disabled Event not triggered

Next Steps

  • You can start creating your Universal Bots by referring here.
  • You can learn about training the Universal Bots from here.

Defining a Universal Bot

Kore.ai’s Universal Bots facilitate a scalable, modular approach to bot building by linking several standard individual bots into one.

  • Modularity: Build separate bots that address domain-specific issues and then integrate them to optimally interoperate.
  • Scalability: Start building bots that address key use cases and keep adding additional bots to address more use cases.

Before starting with creating a Universal Bot, let us understand how Universal Bots work and how they differ from Standard Bots.

Bot Behavior

Universal bot responses vary with the number of bots and tasks that match the user intent along with their relevance (exact matches or suggestions). The Natural Language Processing (NLP) engine processes the utterances sent to the linked bots, detects the user intents, and ranks them based on relevance. As a developer, you can test and train the bot responses as explained in Test the Universal Bot.

Following the table shows how universal bot responses operate in various possible NLP outcomes:

NLP Outcome Bot Response
Only one exact match found from any of the linked bots Executes the task with the exact match
Exact matches found in more than one linked bot Tries to match the invocation names from the user utterance with the bot results, else prompts the user to select one.
Exact matches found with two or more tasks of a single linked bot Disambiguates using the current bot context, else prompts the user to select one.
Suggestions found in more than one linked bot Evaluates the individual scores and executes the winning intent based on the P&R settings.
Suggestions found with two or more tasks of a single linked bot Executes the winning intent based on the P&R settings.
Only one suggestion found Shows the suggestion to the user asking if they would like to select it
No exact match or suggestion found Checks for intent in the Universal Bot – small talk or fallback bot

Standard Bots vs. Universal Bots

Universal Bots connect multiple Standard Bots into a single bot. They support most Standard Bot features with a few exceptions.

Enabled Features and Configurations

This section assumes that you understand the fundamentals of standard bots. Details relevant to the Universal Bots alone are listed here. We recommend you to refer to the relevant standard bot documentation for help with the basics.
The Feature column entries in the following table provide URLs to the standard bot documentation.
The Learn more links in the Description column refer to the universal bot documentation.

Feature Description
Natural Language
Testing Since the universal bot links together standard bots, the Natural Language Processing (NLP) settings are optimized to accurately recognize the relevant bot and intent. You can test and train the universal bot like a standard bot with small differences. When you train the task it happens at the linked bot level. Learn more.
Training

(UB 2.0)

Post ver7.3 of the platform, the Universal Bot 2.0 can be trained, the approach is slightly different from the standard bots. Learn more.
Standard Responses The universal bot will hold a limited set of standard responses that are relevant to bot level functions like greetings. Go to Natural Language -> Default Conversation, to access the Standard Responses section to edit the relevant standard responses.
Batch Testing Universal bots only support testing Custom-defined utterances and not Developer-defined utterances and Succesful user utterances.
The Custom-defined utterances test suites remain similar to the standard bots’ except that the JSON Dataset file that you upload should contain a bot name along with the intent and input for every test case. Also, the downloaded batch test report shows the results with corresponding bot names.
Default Dialog Universal bots come with a default dialog task that gets triggered for unidentified intents. You can customize this task or import a new one. Learn more.
Event-Based Bot Actions With ver8.0, you can choose different tasks from the linked bots for various events. Learn more.
Help When a user types Help during a chat, a standard bot responds with the list of tasks that it can perform, allowing the user to select a task name to execute.

When it comes to Universal bots, if a user types Help, the bot responds with the names of linked bots. The user cannot select or execute a task from the list.

Channel Configuration
All Universal bots do not obtain the channel configurations of the linked bots and need an independent channel configuration. You can set up new channels for the universal bot independent of the linked bot channels. The published tasks in the linked bots execute from the universal bot channels. Learn more.
Settings
General Settings Universal and standard bots share the same general settings.
Language Management Universal bots do not obtain the enabled languages of the linked bots. You must enable default and additional languages explicitly for the universal bot. But when user utterances are made in an enabled language, the universal bot routes it to only those linked bot tasks that support the language. For example, if German is enabled for the universal bot and a user utters in German, the NLP engine looks for all the linked bot tasks that support German and sends the utterance to those tasks. Learn more.
Developer Collaboration Works similar to standard bots. Once you share a Universal Bot with other developers, they can link and unlink bots.
Change Logs Universal bot change logs record all the changes applicable to the standard bots, plus the following:

  1. Linking of a bot
  2. Un-linking of the bot
  3. Change to default dialog
  4. Publishing of default dialog
Import & Export bot

(supported from ver7.1)

Like standard bots, you can export and import the published and unpublished universal bots. Since universal bots deal with linked bots the following need to be taken care of:

  • Export of a universal bot – only the reference to the linked bot (reference id) will be included not the entire linked bot definition;
  • Import of the universal bot – in the environment where the bot is being imported to, the platform checks for the bots with reference id matching the linked bot. If found they are automatically linked to the imported universal bot. Also you should have permissions for the linke bot, else it will not be linked. Ensure that you import the linked bots before importing the universal bot.
Delete bot Like standard bots, you can delete the unpublished universal bots.
Variable Management

(UB 2.0)

Like standard bots, you can define global and content variables in universal bots. In addition, you can choose whether or not the variables can be propagated to the linked bots.
API Extensions
SDK toolkit Enabled with the following events – on message, on hook, on event, on alert
Agent Transfer Agent Transfer can be configured for a Universal Bot. The Agent Node needs to be added in default dialog and addition of any subsequent nodes after the agent node is not allowed.
WebHook Node Multiple webhook nodes can be placed in the default dialog. When a webhook node is reached during the conversation, the platform invokes the BotKit similar to that of a Standard Bot.
SDK as Channel Enabled
Analyze
Chat History All the Universal Bot chats get recorded. Any initiated training will affect the individual linked bot.
Publish
All You can select one or more linked bots and publish the Universal Bot. Learn more about the publish flow.

Event Management

Let us see the behavior of Universal Bots for the following BotKit events in Linked Bots:

  • End of Conversation (see below)
  • On Message
  • Agent
  • Webhook
  • Event
  • Alert Events

When a child bot is in context i.e., a task from a child bot is in progress, then the events related to the child bots will be triggered based on the configurations set up by the developer:

  • If an event is enabled in child bot, then the event will be forwarded to child bot BotKit
  • If an event is not enabled in child bot and
    • if that event is enabled in Universal bot, then the event will be sent to Universal bot BotKit
    • if that event is not enabled in Universal bot as well, then the event will not be forwarded to any BotKit.

Following table summarises the above scenarios and behavior:

Event Name Child Bot Status Universal Bot Status Expected Behavior
On Message Enabled Event sent to child bot BotKit
Disabled Enabled Event sent to Universal BotKit
Disabled Disabled Invalid scenario. The event does not trigger in this case
All other events Enabled Event sent to child bot BotKit
Disabled Enabled Event sent to Universal BotKit
Disabled Disabled Same as the current behavior. E.g. dialog reaches Webhook node but ‘on Hook’ event is not enabled

End of Conversation

The following table depicts the bot behavior for the end of the conversation event:

Conversation ends End of Conversation Event in Universal Bot End of Conversation Event in Linked Bot Behavior
Universal Bot Enabled Enabled or Disabled Trigger event in Universal Bot
Universal Bot Disabled Enabled or Disabled No event triggered
Linked Bot Enabled or Disabled Enabled Tigger event in Linked Bot
Linked Bot Enabled Disabled Tigger event in Universal Bot
Linked Bot Disabled Disabled Event not triggered

Next Steps

  • You can start creating your Universal Bots by referring here.
  • You can learn about training the Universal Bots from here.
Menu