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 Node (v2, BETA)
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
Guardrails
Intelligence
Introduction
Event Handlers
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentiment 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
Guidelines
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
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
Web SDK
How the Web SDK Works
SDK Security
SDK Registration
Web Socket Connect and RTM
Tutorials
Widget SDK Tutorial
Web SDK Tutorial
BotKit SDK
BotKit SDK Deployment Guide
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
Installing Botkit in AWS
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer

ADMINISTRATION
Intro to Bots Admin Console
Administration Dashboard
User Management
Managing Your Users
Managing Your Groups
Role Management
Manage Data Tables and Views
Bot Management
Enrollment
Inviting Users
Sending Bulk Invites to Enroll Users
Importing Users and User Data
Synchronizing Users from Active Directory
Security & Compliance
Using Single Sign-On
Two-Factor Authentication for Platform Access
Security Settings
Cloud Connector
Analytics for Bots Admin
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Channel Enablement
  5. Adding the Google Assistant channel

Adding the Google Assistant channel

Important: The Google Assistant Conversational Actions will be sunsetted on June 13, 2023. For details, see Conversational Actions sunset.

Requirements

Google Assistant as a channel should ideally be enabled for VAs that are specifically built to work on voice-based channels. Ensure to review the following before you enable Google Assistant as a channel:

  • You have an account that allows you to build a project in Actions on Google, link it to an agent in dialog flow, configure actions, and enable fulfillment using webhook integration.
  • Ensure that your dialog tasks contain the Message node as the last node only.
  • Alert task notifications are currently not supported.
  • Some of the Hold & Resume options with explicit messages to the user will not work.
  • Task execution will not be automatically resumed when users provide authorization using web forms. After providing authorization, users have to re-initiate the task.
  • Web form-based responses are not supported for Action, Information, and Alert tasks. and enable fulfillment using a webhook integration.

Step 1: Create a Google Actions Project

  1. Log in to Actions on Google Console, click Go To Actions Console.
  2. Click Add/import project. Provide all the details in the required fields and click Create Project.
  3. After your project is created, you are redirected to the project’s Get Started page.
  4. On this page, you must select a category for your project. Select the project category as Custom and click Next.
  5. After your category is selected, you must select a project template. Scroll down to the bottom of the page and select Click here to build your Action using DialogFlow, this will redirect you to the project’s overview page.
  6. Click the Modify languages in Settings option to update the languages in which your actions are displayed.
  7. Go back by clicking on the Overview tab on top of the page.
  8. Now click Decide how your Action is invoked under the Quick Setup. This opens up the Develop tab.
  9. Now proceed to the Invocation option on the left pane. Provide a name that users use to invoke your actions.
  10. Click Save on the top-left of the page. You may review other options available.

Step 2: Define Actions

  1. Next, you must define Actions. Actions are the tasks that you intend your project to fulfill. Click Actions on the left pane and click Add Your First Action. A new window with options to either build a custom intent or to choose built-in intents is displayed. Choose an appropriate option as per your requirement.
  2. Actions on Google will redirect you to the Dialogflow application for defining the action definition. If you are new to Dialogflow, you are requested to register on Dialogflow. Once your Dialogflow account is set up, you are redirected to the Console of Dialogflow to create a new Agent. Click Create to complete the creation of a new agent.
  3. Once your agent is created, click Intents on the left pane. Dialogflow will add two intents by default viz. Default Fallback Intent and Default Welcome Intent.
    1. Default Fallback Intent is used to respond to any user input that does not match any of the other intents defined in the intent.
    2. Default Welcome Intent is used to respond to the user on the first input. If no other intent is created in Dialogflow, these two intents will be used to address all user inputs.
  4. As you expect your Kore.ai assistant to fulfill all your user requests, you must turn on Webhook Calls for both these intents. Once enabled, Dialogflow will route all user requests reaching any of these two intents to your Kore.ai assistant.
  5. Select Default Fallback Intent to open the intent details and go to the end of the page. Under the Fulfillment section, turn on the toggle to Enable webhook call for this intent option. Click Save to update your changes.
  6. Go back to the Intents on the left pane, select Default Welcome Intent to open the intent details, and go to the end of the page. Under the Fulfillment section, turn on the toggle to Enable webhook call for this intent option.
  7. Click Save to update your changes.

Step 3: Enable Fulfillment

  1. Next, Enable Fulfillment. To configure the webhook integration between your Dialogflow agent and Kore.ai assistant, click the Fulfillment option on the left pane and enable the Webhook toggle switch.
    • Open the assistantin the Kore.ai XO Platform and access the Channel Enablement option and select the Google Assistant channel.
    • Go to the Configurations tab and copy the Webhook URL provided there and update it in the URL field in the Fulfillment section of Dialogflow.
    • From the Configurations tab of the Google Assistant channel page on the builder, copy the Access Token. This token must be added as a header key in the Dialogflow Fulfillment screen.
    • Under the Webhook option of the Fulfillment section, add the key as Access-token and update the copied access token as the value for this key.
  2. Go to the end of the page and click Save.

Step 4: Test using Simulator

  1. Your configurations to enable the channel are all set up now. Actions on Google provides a built-in simulator to test your assistant. For this, you must first enable few additional options of your Google account’s Activity Controls as per the details provided here.
    1. After you have configured these controls, in the Dialogflow console, click Integrations on the left pane and then click the Google Assistant. A popup window with Google Assistant’s integration settings is displayed. Review the required settings and then click Test at the bottom of the window.
    2. This redirects you back to the Google Action Console and opens up the test tab. Now, you can start testing your assistant using Google’s in-built emulator.
  2. Once you have configured the integration and tested your assistant, you must deploy your bot for making it available to potential users. Proceed to the Deploy on the top and furnish all the required information and submit for release by clicking Save on the top-right of the page. Your action will be available on Google Assistant Explore only after your release submission is approved.
  3. Proceed to the Configurations tab on the Google Assistant channel page to continue with the channel setup process.

Step 5: Enable the channel

  1. In the XO Platform, select the assistant you want to add the channel to.
  2. Go to Deploy > Channels > Google Assistant.
  3. Go to the Configuration tab, select Yes and Save your change to enable the channel.

After the channel is enabled and all configurations are verified, you can optionally publish the assistant to make it available for end-users, with the new channel. Learn more about Publishing your Virtual Assistant.

To learn more about working with Channels within the Kore.ai XO Platform, please see Channel Enablement.

Adding the Google Assistant channel

Important: The Google Assistant Conversational Actions will be sunsetted on June 13, 2023. For details, see Conversational Actions sunset.

Requirements

Google Assistant as a channel should ideally be enabled for VAs that are specifically built to work on voice-based channels. Ensure to review the following before you enable Google Assistant as a channel:

  • You have an account that allows you to build a project in Actions on Google, link it to an agent in dialog flow, configure actions, and enable fulfillment using webhook integration.
  • Ensure that your dialog tasks contain the Message node as the last node only.
  • Alert task notifications are currently not supported.
  • Some of the Hold & Resume options with explicit messages to the user will not work.
  • Task execution will not be automatically resumed when users provide authorization using web forms. After providing authorization, users have to re-initiate the task.
  • Web form-based responses are not supported for Action, Information, and Alert tasks. and enable fulfillment using a webhook integration.

Step 1: Create a Google Actions Project

  1. Log in to Actions on Google Console, click Go To Actions Console.
  2. Click Add/import project. Provide all the details in the required fields and click Create Project.
  3. After your project is created, you are redirected to the project’s Get Started page.
  4. On this page, you must select a category for your project. Select the project category as Custom and click Next.
  5. After your category is selected, you must select a project template. Scroll down to the bottom of the page and select Click here to build your Action using DialogFlow, this will redirect you to the project’s overview page.
  6. Click the Modify languages in Settings option to update the languages in which your actions are displayed.
  7. Go back by clicking on the Overview tab on top of the page.
  8. Now click Decide how your Action is invoked under the Quick Setup. This opens up the Develop tab.
  9. Now proceed to the Invocation option on the left pane. Provide a name that users use to invoke your actions.
  10. Click Save on the top-left of the page. You may review other options available.

Step 2: Define Actions

  1. Next, you must define Actions. Actions are the tasks that you intend your project to fulfill. Click Actions on the left pane and click Add Your First Action. A new window with options to either build a custom intent or to choose built-in intents is displayed. Choose an appropriate option as per your requirement.
  2. Actions on Google will redirect you to the Dialogflow application for defining the action definition. If you are new to Dialogflow, you are requested to register on Dialogflow. Once your Dialogflow account is set up, you are redirected to the Console of Dialogflow to create a new Agent. Click Create to complete the creation of a new agent.
  3. Once your agent is created, click Intents on the left pane. Dialogflow will add two intents by default viz. Default Fallback Intent and Default Welcome Intent.
    1. Default Fallback Intent is used to respond to any user input that does not match any of the other intents defined in the intent.
    2. Default Welcome Intent is used to respond to the user on the first input. If no other intent is created in Dialogflow, these two intents will be used to address all user inputs.
  4. As you expect your Kore.ai assistant to fulfill all your user requests, you must turn on Webhook Calls for both these intents. Once enabled, Dialogflow will route all user requests reaching any of these two intents to your Kore.ai assistant.
  5. Select Default Fallback Intent to open the intent details and go to the end of the page. Under the Fulfillment section, turn on the toggle to Enable webhook call for this intent option. Click Save to update your changes.
  6. Go back to the Intents on the left pane, select Default Welcome Intent to open the intent details, and go to the end of the page. Under the Fulfillment section, turn on the toggle to Enable webhook call for this intent option.
  7. Click Save to update your changes.

Step 3: Enable Fulfillment

  1. Next, Enable Fulfillment. To configure the webhook integration between your Dialogflow agent and Kore.ai assistant, click the Fulfillment option on the left pane and enable the Webhook toggle switch.
    • Open the assistantin the Kore.ai XO Platform and access the Channel Enablement option and select the Google Assistant channel.
    • Go to the Configurations tab and copy the Webhook URL provided there and update it in the URL field in the Fulfillment section of Dialogflow.
    • From the Configurations tab of the Google Assistant channel page on the builder, copy the Access Token. This token must be added as a header key in the Dialogflow Fulfillment screen.
    • Under the Webhook option of the Fulfillment section, add the key as Access-token and update the copied access token as the value for this key.
  2. Go to the end of the page and click Save.

Step 4: Test using Simulator

  1. Your configurations to enable the channel are all set up now. Actions on Google provides a built-in simulator to test your assistant. For this, you must first enable few additional options of your Google account’s Activity Controls as per the details provided here.
    1. After you have configured these controls, in the Dialogflow console, click Integrations on the left pane and then click the Google Assistant. A popup window with Google Assistant’s integration settings is displayed. Review the required settings and then click Test at the bottom of the window.
    2. This redirects you back to the Google Action Console and opens up the test tab. Now, you can start testing your assistant using Google’s in-built emulator.
  2. Once you have configured the integration and tested your assistant, you must deploy your bot for making it available to potential users. Proceed to the Deploy on the top and furnish all the required information and submit for release by clicking Save on the top-right of the page. Your action will be available on Google Assistant Explore only after your release submission is approved.
  3. Proceed to the Configurations tab on the Google Assistant channel page to continue with the channel setup process.

Step 5: Enable the channel

  1. In the XO Platform, select the assistant you want to add the channel to.
  2. Go to Deploy > Channels > Google Assistant.
  3. Go to the Configuration tab, select Yes and Save your change to enable the channel.

After the channel is enabled and all configurations are verified, you can optionally publish the assistant to make it available for end-users, with the new channel. Learn more about Publishing your Virtual Assistant.

To learn more about working with Channels within the Kore.ai XO Platform, please see Channel Enablement.

Menu