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
Feedback Survey
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
Conversations History
Conversation Flows
Feedback Analytics
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
BotKit SDK Tutorial - Blue Prism

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. Test your Bot
  5. Conversation Testing6 min read

Conversation Testing6 min read

Conversation Testing enables you to simulate end-to-end conversational flows to evaluate the dialog task or perform regression. You can create Test Cases to capture various business scenarios and run them at a later point in time to validate the performance of the bot. 

Test Cases

Test Cases consist of a sequence of Test Steps that capture the conversational flow. Each Test Step is a combination of Step Number, Test Input, Expected Output, Actual Output, and Test Result. 

Step# defines the sequence of execution. 

Test Input represents the user message part of the conversation. 

Expected Output represents the bot message that is anticipated from the bot.

Actual Output represents the response of the bot during test execution. The platform will evaluate the Actual Output against the Expected Output to determine if a test step is passed or not. 

Test Result indicates if the actual output is the same as the expected output. Test Result can be Pass, Failed, or Not Executed.

Test Case Creation 

New Test Cases can be created by recording the conversation while using ‘Talk to Bot’. Follow the following steps to create a new test case. 

Step 1: Launch ‘Talk to Bot’ by clicking on the icon in the bottom right corner of your screen. ‘Talk to Bot’ can be launched from any module on the platform. 

Step 2: Click on ‘Record Conversation’ to start recording the messages that are going to be part of the test case. 

Step 3: Interact with the bot by entering relevant user messages. 

Step 4: To create a new test case, click on ‘Stop Recording’ and then click on ‘Create Test Case’. 

Step 5: In the next screen, add the necessary details such as ‘Test Case Name’, ‘Description’ and ‘Tags’ and click on ‘Add’.

Step 6: Navigate to the Conversation Testing module to execute the added test case or add another test case by following the same steps. 

Tags

Tags help in classifying and organizing test cases. You can choose to add a tag at the time of the creation of a test case or from the ‘General Settings’ under the Test Case properties.

General Settings

 After a test case is created, you can access the ‘General Settings’ from the overflow menu. The General Settings has a few editable and few view-only properties.

You have the option to edit the following properties.

  •       Test Case Name
  •       Test Case Description
  •       Test Case Tags

Additionally, the following properties can be viewed but not edited.

  •       Date & Time of Test Case Creation
  •       Name of the User who created the Test Case
  •       Date & Time of the last update
  •       Name of the user who last updated the test case

Test Case Execution

The following steps will guide you on how to execute a test case and obtain a detailed analytical report based on the execution. 

Step 1: Select the Test Cases that you would like to execute.

Step 2: Click on ‘Run Test Case’ to start the execution. 

Step 3: Next, you are required to choose the Version of the Bot that you want to test. Based on the version selected, please ensure that you have valid authorization tokens for the bot to make the service calls that would be part of the test case. 

Step 4: You can monitor the progress of the execution from the last result column against the test case and the status docker. 

Step 5: Once the test case execution is over, you can click on the test case to view the execution history. 

Step 6: Click on any of the listed test runs to view the details of the test run. 

Test Cases are executed asynchronously i.e. even when multiple test cases are selected, the execution happens sequentially. You have the option to cancel the test execution before the execution is completed. 

Once the test case execution has started, the platform continues to execute the test case even when one or more test steps fail. However, if the test execution is stuck at a test step for more than 60s the platform will timeout and abort the execution. 

Interpreting Test Results

The following details are stored against every test execution. 

  • Date & Time of Execution completion.
  • Version Type to indicate if the test case was run against the In-development or the Published version of the bot. 
  • Execution Result to indicate the result of the execution. A test case is treated as failed if at least one of the test steps is failed. 
  • Execution Time indicates the total time duration of the execution. 
  • Test Step Details represent the total steps that were passed, failed, or not executed. 
  • Execution Error Details are shown only when the platform is unable to complete the test execution either because of the user aborting the test case or the test step timing out due to an error. 

Limitations

The following modules cannot be tested with the current version of conversation testing. 

  • Digital Forms
  • Dynamically generated bot messages where content or context variables are used.

Test Runner Tool

If you would like to set up your own test execution application, then you can download the libraries provided at the Kore.ai Github repository. You can record and download the test cases from the platform, and run these test cases on your application. Note that this tool is an open-source code that you can fork a branch and make changes as per your requirements.

Key Points

  • You can start and stop the recording anytime during your conversation with the bot.
  • The entire conversation is saved as a Test Case.
  • In case you want to split the Test Cases and generate a Test Suite, you can achieve it using “discard all” command during the conversation. The conversation before “discard all” is saved as a test case and the conversation after is another test case. Both the test cases will be saved as a single file as Test Suite. You can split the conversation into as many test cases as per your requirement.
  • The entire conversation is stored in a JSON file which will be available for download once the recording ends.

The Testing Tool will converse with the bot using the user input from the JSON file and compare the bot response with the recorded bot responses.

The results are recorded in a Test Results spreadsheet providing a comprehensive report of the test run, with the developer input, actual and expected results, and the status of the test run (passed or failed). You can use this spreadsheet to report, keep a track of, and re-test the failed test cases.

For more details on the Test Runner refer to the Kore.ai Github.

Menu