GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Help & Learning Resources
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Using Workspaces
Release Notes
Current Version
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
Nodes & Connections
Overview
Node Types
Intent Node
Dialog Node
Entity Node
Entity Rules
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections Setup
Sub-Intent Scoping
User Prompts
Voice Call Properties
Dialog Task Management
Supported Entity Types
Supported Company Names
Supported Colors
Knowledge Graph
Introduction
Knowledge Extraction
Build Knowledge Graph
Create Node Structure
Build the Graph
Add FAQs
Add FAQs from an Existing Source
Run a Task
Traits, Synonyms, and Stop Words
Manage Variable Namespaces
Update Knowledge Graph
Introduction
Move Question and Answers Between Nodes
Edit and Delete Terms
Edit Questions and Responses
Knowledge Graph Analysis
Knowledge Graph Import and Export
Prepare Data for Import
From a CSV File
From a JSON File
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
Intelligence
Introduction
Event Handlers
Default Standard Responses
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentinment Management
Tone Analysis
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Health and Monitoring
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
NLP Insights
Conversations History
Conversation Flows
Analytics Dashboard Filters
Usage Metrics
Containment Metrics
Smart Bots
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Plan & Usage
Overview
Usage Plans
Support Plans
Invoices
Authorization
Multilingual Virtual Assistants
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data as Service
Data Table
Table Views
App Definitions
Sharing Data Tables or Views
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
Configure Agent Transfer
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
APIs & SDKs
API Reference
API Introduction
API List
API Collection
koreUtil Libraries
SDK Reference
SDK Introduction
SDK Security
SDK Registration
Web Socket Connect and RTM
Using the BotKit SDK
BotKit SDK Tutorial - Blue Prism
Widget SDK Tutorial
Web SDK Tutorial
ADMINISTRATION
Introduction to Admin Console
Administration Dashboard
User Management
Add Users
Manage Groups
Manage Roles
Assistant Management
Enrollment
Invite Users
Send Bulk Invites
Import User Data
Synchronize Users from AD
Security & Control
Using Single-Sign On
Security Settings
Cloud Connector
Analytics
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. How Tos
  5. Kore-Unblu Integration

Kore-Unblu Integration

Overview

Unblu is a conversational platform that allows agents and advisors in your organization to collaborate with your customers and website visitors. It enables collaboration through online channels like live chat, secure text messaging, and video chat to achieve a better customer experience.

Transferring a chat to a human agent from the bot is necessary if your bot is in the space of customer service. Chatbots are not meant to completely replace humans. At times, the chatbot fails to answer satisfactorily or the user wants to chat with a human being. If this happens, the chatbot should transfer the chats to a human agent or a customer care representative. To help users accomplish this task, Kore can be integrated with the Unblu application.

Here, the bot is the core of the entire solution. Apart from performing all its functionalities, the bot also acts as a proxy between users and agents.

  • Bot: Chat Bot that the user interacts with.
  • Users: Users are the customers who are using this bot.
  • Agent: Agents are humans who chat with users. The agent will also need a chat window. For this, you can use Unblu software.

Prerequisites

The prerequisites are listed below:

  • A fully functional bot.
  • An Unblu account.
  • Download BotKit SDK from Kore’s GitHub.
  • Download and install the <Node.js> file. The BotKit SDK requires <node.js> files to run on the same server where the SDK is installed. The <node.js> version must be v12.0 and above.
  • Ngrok to simulate the callback server application.

Configuration

To perform the Kore-Unblu integration, follow the below steps:

  1. Log in to the Kore bots platform with valid credentials.
  2. Select the Deploy tab from the top menu
  3. From Integrations select the Agent Transfer option
  4. On the Agent Transfer page, next to App Name, click Add (you can select an existing app from the drop-down if you have already created one)
  5. On the Create Client App window, enter the app name in the Name field.
  6. You can choose to enforce JTI or JWE encryption or both. For this use case we will ignore them.
  7. Click Next > Done.
  8. In the Callback URL field, enter the BotKit URL endpoint. For example, https://<domainname>/unblu.
  9. Click Save.
  10. Now, log in to the Unblu account with valid credentials.
  11. Click your profile on the top-right; under the Administration section, select Manage Account.
  12. On the Account Configuration page, by default, Account Overview is displayed.
  13. On the left pane, under the Site Integration section, select Domains.
  14. On the Domains page, click New Domain on the top-right.
  15. On the New Domain window, enter the URL in the Domain URL field. 
    Note: This is the Callback URL. Refer to step 7. If this is not a constant public IP or Ngrok IP, you must update the IP whenever it changes.
  16. In the Protocol field, select Both.
  17. Click Save.

After completing the above configurations, make the required changes in the <config.json> file. Refer to <sample_config_file.txt> for sample values.

  1. Go to <config.json> file and make the below-mentioned changes.
  2. Under the app section, paste the URL (Ngrok or publicly accessible URL). Refer to the below image.
  3. Under the credentials section, paste the Kore bot details: API Key (client secret), App ID (client id), and Bot Name. Refer to the below image.

    To find these details,

    1. Log in to the Kore bots platform with valid credentials.
    2. Select the Deploy tab from the top menu
    3. From Integrations select the BotKit option
    4. You can find the details as needed.
  4. Under the Unblu section, make the below changes:
    1. Paste Unblu credentials under the Unblu credentials section.
    2. Under the external_messenger section, enter the name, description, etc., you want to display in the chat.
      To access the external messenger details,

      1. Log in to the Unblu desktop application.
      2. On the left pane, under the External Integration section, select External Messengers.
      3. On the External Messengers page, select the respective messenger and you can find the messenger details.
    3. Under the agent section, enter the agent details you want to create.
    4. Under the named_area  section, enter a Name and Meta Tag ID.
      To create a named area,

      1. Log in to the Unblu application.
      2. On the left pane, under the Site Integration section, select Named Areas
      3. On the Named Areas page, click New Named Area on the top-right.
      4. On the New Named Area window, select a registered domain from the Domain Name drop-down list and enter a name in the Name field. You can also register a domain by clicking Register a New Domain.
      5. Click Save.
    5. Under the admin section, enter the Unblu username.
  5. After you have updated the <config.json> file, install the dependencies by executing the command npm i.
  6. Run the integration setup by executing the command npm start.   
    Note: The webhook URL must be the same in API Extensions, <config.json> file, and the external messenger section (Endpoint URL of the respective messenger) of your Unblu account as mentioned above (The Botkit URL in API Extensions, app.url, and unblu.custom.external_messenger).
  7. The agent transfer is configured at the dialog level. You can open the dialog task, and open the agent transfer node to see that the configuration is saved.
Menu