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. Channel Enablement
  5. Adding the Amazon Alexa Channel

Adding the Amazon Alexa Channel

To add Amazon Alexa as a channel to your Kore.ai assistant, you must extract supported Dialog Tasks of this VA from the Configurations tab and add to your Amazon Alexa’s Skills. Additionally, you must configure your VA’s Webhook URL as your Alexa Skill Set’s Service Endpoint for the XO Platform to receive messages. To enable the Alexa channel, you must have or register for an Amazon Developer account.

Important Notes

Alexa as a channel must be enabled for VAs that are specifically built to work on voice-based channels. Review the following constraints before enabling Alexa as a channel:

  1. Enterprise assistants that require the user’s authorization to communicate with it are not supported.
  2. If your dialog tasks require the user’s authorization to communicate with external systems, then the Platform will push a card with URL information to the Alexa app.
  3. Intents and entities of only Published Dialog Tasks can be exported to Amazon Alexa. Ensure that your intents and entities adhere to the naming guidelines of Amazon Alexa.
  4. Not all entity types available in the Kore.ai Platform are currently available in Alexa. Verify that your tasks contain Alexa-supported entities for optimal user experience.
  5. Ensure that your dialog tasks contain one or more utterances.
  6. If you want to display responses as templates on supported devices like Echo Show, you must define channel-specific responses/prompts.
  7. Ensure that your dialog tasks contain the Message node as the last node only. Alexa marks a task as completed if a VA message is displayed without expecting any input from the user.
  8. Webhook Nodes work asynchronously and are currently not supported.
  9. Amazon Alexa executes one task at a time and hence the Hold & Resume functionality is not supported.

Setup Overview

To add the Amazon Alexa channel, you must:

  1. Add a New Skill – To enable the Alexa channel to your Kore.ai assistant, create a new Alexa skill in the Amazon developer console.
  2. Configure the Interaction Model – Alexa skill can be built in one of the following ways:
    1. Dialog Migration to extract the dialog tasks from Kore.ai and import them into Amazon Alexa’s Skills. This will entail re-import for reflecting ongoing changes in the dialog definition. Intent detection and execution are primarily controlled by Alexa.
    2. Redirection to create a single intent in your skill with one SearchQuery slot that accepts user inputs and redirects them to your Kore.ai VA. Intent detection and execution are primarily controlled by the Kore.ai VA.
  3. Enable Account Linking – To access end user’s authentication details to make API calls to external services. This step is optional.
  4. Enable Webhook Integration – To integrate Amazon Alexa with your Kore.ai VA, enable webhook integration by copying the Webhook URL provided on the Configurations tab of the Amazon Alexa Channel page in the XO Platform and select HTTPS as Service Endpoint type.
  5. Enable Channel – After completing the integration setup, enable the channel.
  6. Test Integration – Once the channel is enabled, to validate a successful integration, test any intent utterance using the Test tab of your Alexa Skill and check its responses for the given test utterances.
  7. Distribution, Privacy & Compliance, and Certification – You must publish your Alexa Skill on Alexa App and provide details for Privacy and Compliance to enable Skills Beta Testing that allows you to invite your co-developers to test your app. You must also submit your Skill to Amazon for certification to enable your skill to become visible on Alexa Skills on Amazon App Store after it is certified.

Step 1: Add a New Skill

  1. Log into your Amazon Developer Portal and click the Alexa tab. Choose Skills from Your Alexa Console and Create a New Skill
  2. In the Create a New Alexa Skill section, enter the required information in the respective fields.
    1. Choose if you want to Sync Locale and select Custom as a model to add to your skill.  
    2. Under Choose a method to host your skill’s backend resources, please select Provision your own.

  3. Click Create Skill at the top right of the page.

Step 2: Configure the Interaction Model 

  1. Now, from under the Interaction Model section, select JSON Editor.
  2. In the Code Editor, define the intents and entities to associate with your newly created skill. For this, follow the steps below in the XO Platform:  
    1. Select the assistant you want to work with.
    2. Go to Deploy > Channels > Amazon Alexa > Configurations.
    3. From under Alexa Skill Definition JSON, download the VA’s tasks as a JSON file to be uploaded into Alexa Skills JSON Editor.

    4. Upload the JSON file to the Alexa Code Editor, review and ensure that there are no errors, click Save Model, then Build Model.

      Note: It takes 2-5 mins for the Model to build. Any changes implemented to the built model must be followed by rebuilding the model.

Step 3: Enable Account Linking (Optional)

You can enable the Account Linking feature in your Alexa Skill if your assistant expects end users’ authorization for making API calls to external services. 

  1. Within your skill’s Build tab, go to Tools.
  2. Click on Account Linking and set up the integration as per the instructions available from Amazon, and as per your requirements. Alexa requests users to provide the required authorization details for linking the accounts. During skill execution, Alexa shares the user access tokens with Kore.ai assistants, which are then used to make API calls defined in Service nodes. 

Step 4: Enable the Webhook Integration

  1. Go to the Endpoint section.
  2. Select HTTPS as the Service Endpoint Type. Copy the Webhook URL provided in the Configurations tab of the Amazon Alexa channel page in the XO Platform and enter it in the Default textbox.
  3. In the SSL Certificate dropdown, select the option My development endpoint is a sub-domain of a domain that has a wildcard certificate from a certificate authority.
  4. Click Save Endpoint.

Step 5: Enable the Channel

Before you can start testing your assistant on Alexa, you must complete the channel setup. Go to the Configurations tab of the Amazon Alexa channel page, review the details and select Yes; click Save to enable Amazon Alexa Channel.

Step 6: Test the Integration

Once done, you can use the Test tab of your Alexa Skill to test your utterances against the integration. In the Test tab, go to the Service Simulator section and provide any intent utterance and click Ask <skill-name> to test the utterance. If you get a successful response then the integration is considered a success.

Step 7: Distribution

Now, go to the Distribution tab and provide all the required details for publishing your Alexa Skill on the Alexa App and Save the details.

Privacy & Compliance

Next, go to the Privacy & Compliance tab and provide all the required details requested and click Save

After completing these steps, the Skills Beta Testing option is enabled and this allows you to invite your co-developers to test your app.

When you are ready to submit your Skill to Amazon, Submit for Certification. Your skill will be visible on Alexa Skills on Amazon App Store after it is certified.

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