GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Working with the Builder
Building a Virtual Assistant
Using Workspaces
Release Notes
Current Version
Previous Versions
Deprecations

CONCEPTS
Design
Storyboard
Dialog Tasks
Overview
Dialog Builder
Node Types
Intent Node
Dialog Node
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Group Node
Agent Transfer
User Prompts
Voice Call Properties
Dialog Task Management
Connections & Transitions
Component Transition
Context Object
Event Handlers
Knowledge Graph
Introduction
Knowledge Extraction
Build Knowledge Graph
Add Knowledge Graph to Bot
Create the Graph
Build Knowledge Graph
Add FAQs
Run a Task
Build FAQs from an Existing Source
Traits, Synonyms, and Stop Words
Manage Variable Namespaces
Update
Move Question and Answers Between Nodes
Edit and Delete Terms
Edit Questions and Responses
Knowledge Graph Training
Knowledge Graph Analysis
Knowledge Graph Import and Export
Importing Knowledge Graph
Exporting Knowledge Graph
Creating a Knowledge Graph
From a CSV File
From a JSON file
Auto-Generate Knowledge Graph
Alert Tasks
Small Talk
Digital Skills
Digital Forms
Views
Introduction
Panels
Widgets
Train
Introduction
ML Engine
Introduction
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
NLP Configurations
NLP Guidelines
Intelligence
Introduction
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Sentinment Management
Tone Analysis
Test & Debug
Talk to Bot
Utterence Testing
Batch Testing
Conversation Testing
Deploy
Channels
Publish
Analyze
Introduction
Conversations Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Meta Tags
Dashboards and Widgets
Conversation Flows
NLP Metrics
Containment Metrics
Usage 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
Masking PII Details
Variables
IVR Settings
General Settings
Assistant Management
Data Table
Table Views
App Definitions
Sharing Data Tables or Views

HOW TOs
Build a Flight Status 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
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
Web SDK Tutorial
Widget SDK Tutorial
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

ADMINISTRATION
Introduction
Assistant 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 & Compliance
Using Single-Sign On
Security Settings
Cloud Connector
Analytics
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Builder
  5. Digital Views

Digital Views

Interactions with virtual agents are typically conducted using chat/messaging tools, voice channels, or digital assistants. In the majority of the cases, the virtual agents respond to the user queries only when the users have requested some information. This works well for conducting on-demand tasks that need user input for execution and the result is usually a short response, confirmation, or acknowledgment. But, with the emergence of Digital Assistants, the need for proactive updates to users through engaging user interface has become a key requirement. This can be achieved by providing engaging interfaces that present relevant information to end-users with minimal need for user input. These interfaces can also trigger mobile/web apps from within the chatbot.

Using Digital Views from the Kore.ai Bots platform, you can design interactive components, panels, and widgets, to proactively present relevant information to your customers. Panels are the placeholders that hold one or more widgets. Widgets are individual components that display information to the end-users. Your customers can interact with your bot either in conversation mode or directly get the required information from the widgets.

This document gives an overview of the working and implementation of Panels & Widgets. For an step-by-step usage instructions, refer to this how to.

Use Case

  1. Using Digital Views, an organization offers to its employees a single interface for various work-related activities.
  2. Multiple panels constitute a Digital View.
  3. Each of the panels gives access to various functions like Sales, HR, ITSM, etc.
  4. The employee accesses these panels for information pertaining to each of the above functions and performs follow-up actions.
  5. As an example, HR Panel has multiple widgets showing:
    • Company-wide announcements
    • Leave balance
    • Benefits and enroll for additional benefits through bot conversation.

Setup

You can access Digital Views from under the Digital Skills menu under Build and setup Panels and Widgets.

Following are the steps to setting up Panels and Widgets:

  • Configure Widgets: Define widgets by connecting them either to your bot tasks or any other source like JavaScript generating JSON file. In cases where you are using the bot task as a source, ensure that the message is formatted properly for the Widget SDK channel.
  • Preview the Widgets: Preview your widgets from the Bot Builder.
  • Set up Panels: You may create multiple panels and each panel can host widgets that present relevant information. You can use the pre-defined widgets or create new ones.
  • Test the Panels to see how the Panels and Widgets are rendered in the chat window.
  • Publish the Bot: Publish the bot so that the panels and widgets are made available for your end-users.
  • Host the Panel: You can choose to host your widgets independently or co-host them along with the web SDK. You can download the SDKs from the Kore.ai GitHub page. Do ensure to enable WidgetSDK as a channel.

Configure Widgets

Widgets are individual components that can communicate with the bot for presenting information to the end-users. The source of information for widgets is from a Dialog Task or a JSON using any of the pre-defined widget templates.

To configure widgets, follow the below steps:

  1. Click Create Widget to create a widget.
  2. On the New Widget window, enter the following details:
    • Name of the widget
    • Display Name for the widget
    • Auto Refresh to set the frequency with which this widget needs a poll for fresh data. The refresh is applicable only when the panel containing the widget is active.
    • Source for a widget can be either from the execution of Dialog Task or from JavaScript defining a JSON:
      • JSON is specified in the JavaScript Editor that is presented.
      • Dialog Task option allows you to trigger a task and present the output in the widget.
        1. Select Dialog Task drop-down will list all available tasks in the current bot, select one from the list.
          Note: In the connected Dialog Task make sure to use a Message node to present the required information in the widget using any of the supported widget templates.
          You can use the icon next to the Dialog Task to open the Dialog Task for checking the task details like entity names etc.
        2. Any entities used by the selected Dialog Task need to be pre-populated with values by mapping Entity Name with Entity Values.
        3. If the selected Dialog Task has any authorization profile defined, the same is displayed here.
    • Save the Widget.
  3. After you save, the widget will be In Development state. You can Edit or Delete the widget.
  4. Edit widget, apart from allowing modification to any of the above fields, will allow you to Run & Preview the widget.
    You can save the preview as the thumbnail display for the widget.

Set up Panels

Panel refers to containers that hold one or more widgets. You can add an existing widget to the panel or create new widgets.

  1. Click Create Panel to create a panel.
  2. On the New Panel window, enter the following details:
    • Name of the Panel.
    • Display Name for the Panel.
    • Panel Icon to display in the chat window (URL to the location).
    • Save the Panel.
  3. After you save, the panel will be In Development state.
  4. Click Add Widget to add widgets to the panel. Select widgets from the drop-down list.
  5. You have the following options for a given panel:
    • Edit the panel details;
    • Add Form to add existing forms;
    • Add Widget to add existing widgets;
    • Panel Management to add existing forms/widgets, or remove already added forms/widgets from the panel.
    • Test the individual panel – this opens the talk to bot window along with the panel listing with the current panel active and data presented;
    • Delete the Panel.

  6. Test panels open the Talk to Bot window listing all the panels with the chat window active. You can interact and test the panels.

Publish

Publish your bot ensuring that the panels and widgets are selected.

Refer here for details on Publishing a Bot

Hosting

Widget SDK is provided by the platform for hosting and managing panels and widgets. You can choose to host your widgets independently or co-host them along with the WebSDK. You can download the SDKs from the Kore.ai GitHub page. Do ensure to enable WidgetSDK as a channel. Refer to this tutorial on how.

Menu