Skip to main content

Unit Tests

  • Updated

Index:

  1. Introduction
  2. How to access Unit Tests
  3. Managing Unit Tests
  4. Create test
  5. Other features
  6. Setting up a unit test
  7. Variables
  8. Definitions 
  9. Running and analyzing tests

     

Introduction

The Unit Test feature allows you to validate the accuracy of your conversational flow responses, whether deterministic or AI-based. This tool is essential to ensure that expected behaviors are correct before deploying to production, making it easier to maintain and continuously improve your Smart Contact.

How to Access Unit Tests

You can open Unit Tests in two ways:

Home Screen:

In the upper right corner, click the icon.
From the menu, select Tests and Logs.

Side Menu:

On the left side menu, click Unit Tests.

Managing Unit Tests

The unit test management screen is the starting point to view, create, and run tests for your bot or AI agent.

Create Test

Click the Create test button in the upper right corner, or if no tests have been created yet, click the centered Create new test button. You can fill in all test parameters manually or import a settings file by clicking:

Import settings: Upload a file in Blip's format with pre-configured tests.

Other Features

Search: Search field to find specific tests by name.
Test list: Displays all created unit tests with the following details:
Test name: Name assigned to the test.
Interactions: Total number of configured interactions.
Last run: Date and time of the last test execution.
Last status: Result of the last test run, which can be:
Waiting to run: Test created but not yet executed.
Success: All interactions passed successfully (e.g., "Success 18/18").
Metric failure: Some interactions failed (e.g., "Metric failure 25/57").
Start error: Test could not be executed due to an error (e.g., "Start error 2/3").
Interrupted: Test was stopped during execution.
Delete tests: Remove one or more tests.
Run tests: Execute one or more selected tests.


Setting Up a Unit Test

When creating or editing a test, you will access three configuration tabs: Definitions, Variables, and Interactions.

Interactions

This tab is where you define the sequence of questions and answers to validate your bot or AI agent's behavior.

Order: The execution order of interactions (you can reorder by dragging grid icons).
Description: The input text to be sent to the bot.
Result: The status after running the test:
Waiting to run
Success
Start error
Metric failure
Interrupted


Configuring an Interaction:
Click on an interaction to expand and configure it in detail.

Input type:
Text: The text sent to the bot (e.g., "What are your working hours?").
Image
Response match:
Exact: Bot’s response must match exactly.
Similar: Bot’s response must be similar to the expected answer.
Similarity level: Define the required match percentage.
Expected responses:
Text: Add the expected text response (e.g., "Our store is open from 8 AM to 6 PM").
Image: Add an expected image response.
Last received response: Displays the bot's actual response during the last test for comparison.

Variables

In this tab, manage the context variables used in the test flow. Add, edit, or remove the variables your bot or agent may need to start the flow correctly.

Type: context or contact
Name: Variable name (e.g., numbercpf)
Value: Value of the variable (e.g., 129.452.875-06)
New variable: Add a new variable

Definitions

In this tab, define the timeout for test execution.

Response timeout: Use the slider to set the max response time per interaction. If the bot takes longer than the defined time, the interaction is considered a failure.

Running and Analyzing Tests

Click Save after configuring the test.
In the test list, select the test and click Run tests.
View the status and click the test to analyze results.
Interactions marked as Metric failure or Start error indicate areas that need fixing.

 


 For more information, visit the discussion on the subject at our community or videos on our channel. 😃

Related articles