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. Universal Bots

Universal Bots

Kore.ai’s Universal Bots facilitate a scalable, modular approach to Bot building by helping you link several Bots into one.

Universal Bot is a container bot that can be linked with one or more Standard Bots. When a user interacts with the Universal Bots, it routes the user utterance to the appropriate linked bot for intent detection or task fulfillment.

Note: A universal Bot doesn’t own the linked bots, but it interprets the user utterances and maps them to the correct linked bots. The changes that you make to a linked bot task from inside the universal bot, such as training the task, are saved directly to the linked bot. Also, you cannot create any task for the universal bots except for customizing a default dialog task that gets created automatically with every universal bot.

Highlights

  • The universal bot acts as a single interface for the Bot users of an enterprise, across business lines or products or services.
  • Standard bots that aim to meet a specific purpose can be built independently and then be associated with a Universal bot by linking them to the Universal Bot.
  • The developer can view and analyze all user interactions from within the Universal bot and also train the respective bots with additional training data.
  • The developer can train the Universal bot for identifying the relevant bots from a user utterance, using the ranking and disambiguation model. Universal Bot can be trained in three aspects:
    • Using example utterances like the Machine Learning model. This would help identify a set of linked bots as possible matches to the user utterance.
    • Invocation Names that would identify a specific linked bot from the user utterance.
    • Invocation Phrases that would identify a specific intent in a specific bot from the user utterance.
      Refer here to know more about training a Universal Bot.
  • This trained Universal Bot can then be published so that when the end-users interact with Universal bot, it will perform intent recognition across all linked bots to understand the user’s intent and engage the appropriate bot to perform the task.
  • In the case of ambiguity in identifying an appropriate bot or task, a sub-dialog is initiated to obtain confirmation from the user.
  • Universal bots also provide a  Fallback Bot for gracefully handling any untrained/un-recognized requests.
  • Linked bots can be marked as Inclusive bots that need not be trained with sample utterances to participate in the bot scoping process (introduced in ver8.0).
  • Apart from this, the developer can define eligible bots ie. assign specific bots to specific end-users so that only the intents from these bots are made available to them.

Implementation

The following flow chart shows the working of a Universal bot:

The following is the explanation for the above process flow:

  • Universal Bot checks if any eligible bots are defined.
  • If defined, then the list of eligible bots is obtained, else the user intent is checked against any Small Talk, etc.
  • If eligible bots not defined then all the linked bots are considered as eligible.
  • Once the linked eligible bots list is there, Universal Bot identifies the bots that qualify using the invocation phrases. (See the bot training page for details)
  • The user utterance is sent to the scoped bots and the results are processed by the Universal Bot’s Ranking and Resolver engine.

Universal Bot – upgrade

Post ver7.3 release of the platform, new Universal Bots would be versioned as 2.0.

We recommend you upgrade since the older version of universal bot will be deprecated soon. The previous version of Universal bot has the following limitations:

  • Training – you cannot train the universal bot, need to depend upon the training of the linked bots for proper functioning.
  • There are performance issues with the older version if the number of linked bots exceeds 5 or the total number of intents exceeds 100.
  • Variable Management is not possible from the older version of Universal bot.

Older version universal bots will prompt you to Upgrade when:

  • you open the universal bot; or
  • when from the left navigation menu you access Natural Language -> Training.

Once you upgrade, follow these steps to ensure that the user utterances are routed to the relevant linked bots:

  • Train the Universal Bot to identify the linked bots by providing Training Utterances or Invocation Names. The Universal Bot will route the user utterances only to the identified linked bots.
  • Mark linked bots as Fallback Bots. The utterances are routed to the Fallback bots when no other linked bots are qualified from the training provided. A maximum of 15 linked bots can be marked as Fallback bots.
  • Review the linked bot identification flow from the Utterance Testing module.

Refer here for more on training the Universal Bot.

Next Steps

  • Know more about Universal Bots and compare with Standard Bots behavior from here.
  • You can also start creating your Universal Bots by referring here.

Universal Bots

Kore.ai’s Universal Bots facilitate a scalable, modular approach to Bot building by helping you link several Bots into one.

Universal Bot is a container bot that can be linked with one or more Standard Bots. When a user interacts with the Universal Bots, it routes the user utterance to the appropriate linked bot for intent detection or task fulfillment.

Note: A universal Bot doesn’t own the linked bots, but it interprets the user utterances and maps them to the correct linked bots. The changes that you make to a linked bot task from inside the universal bot, such as training the task, are saved directly to the linked bot. Also, you cannot create any task for the universal bots except for customizing a default dialog task that gets created automatically with every universal bot.

Highlights

  • The universal bot acts as a single interface for the Bot users of an enterprise, across business lines or products or services.
  • Standard bots that aim to meet a specific purpose can be built independently and then be associated with a Universal bot by linking them to the Universal Bot.
  • The developer can view and analyze all user interactions from within the Universal bot and also train the respective bots with additional training data.
  • The developer can train the Universal bot for identifying the relevant bots from a user utterance, using the ranking and disambiguation model. Universal Bot can be trained in three aspects:
    • Using example utterances like the Machine Learning model. This would help identify a set of linked bots as possible matches to the user utterance.
    • Invocation Names that would identify a specific linked bot from the user utterance.
    • Invocation Phrases that would identify a specific intent in a specific bot from the user utterance.
      Refer here to know more about training a Universal Bot.
  • This trained Universal Bot can then be published so that when the end-users interact with Universal bot, it will perform intent recognition across all linked bots to understand the user’s intent and engage the appropriate bot to perform the task.
  • In the case of ambiguity in identifying an appropriate bot or task, a sub-dialog is initiated to obtain confirmation from the user.
  • Universal bots also provide a  Fallback Bot for gracefully handling any untrained/un-recognized requests.
  • Linked bots can be marked as Inclusive bots that need not be trained with sample utterances to participate in the bot scoping process (introduced in ver8.0).
  • Apart from this, the developer can define eligible bots ie. assign specific bots to specific end-users so that only the intents from these bots are made available to them.

Implementation

The following flow chart shows the working of a Universal bot:

The following is the explanation for the above process flow:

  • Universal Bot checks if any eligible bots are defined.
  • If defined, then the list of eligible bots is obtained, else the user intent is checked against any Small Talk, etc.
  • If eligible bots not defined then all the linked bots are considered as eligible.
  • Once the linked eligible bots list is there, Universal Bot identifies the bots that qualify using the invocation phrases. (See the bot training page for details)
  • The user utterance is sent to the scoped bots and the results are processed by the Universal Bot’s Ranking and Resolver engine.

Universal Bot – upgrade

Post ver7.3 release of the platform, new Universal Bots would be versioned as 2.0.

We recommend you upgrade since the older version of universal bot will be deprecated soon. The previous version of Universal bot has the following limitations:

  • Training – you cannot train the universal bot, need to depend upon the training of the linked bots for proper functioning.
  • There are performance issues with the older version if the number of linked bots exceeds 5 or the total number of intents exceeds 100.
  • Variable Management is not possible from the older version of Universal bot.

Older version universal bots will prompt you to Upgrade when:

  • you open the universal bot; or
  • when from the left navigation menu you access Natural Language -> Training.

Once you upgrade, follow these steps to ensure that the user utterances are routed to the relevant linked bots:

  • Train the Universal Bot to identify the linked bots by providing Training Utterances or Invocation Names. The Universal Bot will route the user utterances only to the identified linked bots.
  • Mark linked bots as Fallback Bots. The utterances are routed to the Fallback bots when no other linked bots are qualified from the training provided. A maximum of 15 linked bots can be marked as Fallback bots.
  • Review the linked bot identification flow from the Utterance Testing module.

Refer here for more on training the Universal Bot.

Next Steps

  • Know more about Universal Bots and compare with Standard Bots behavior from here.
  • You can also start creating your Universal Bots by referring here.
Menu