The TestDriver interactive CLI allows you to create, refine, and execute tests dynamically using natural language commands. Here’s how to get started.

​
Prepare your environment

Before we get started, let’s set up your machine to collaborate with TestDriver.

​
Displays

TestDriver isn’t like any framework you’ve used before. TestDriver makes decisions based on what it can see on your display!
TestDriver only knows about what it can see on your primary display!
When you enter commands into TestDriver, the current window will minimize and the focus-window command will bring Chrome or other applications to the foreground. For now, set up your environment with a browser window and your terminal side by side like so:

Left or right, it doesn't matter!

​
Application state

The application you want to test should be visible before you run the testdriverai command. For our example, make a new incognito window in Chrome and load our test webpage: 
https://testdriverai.github.io/example-react-todo/
Make sure to reset your application state before running every test!

​
Launch interactive mode

Run the following command to launch the TestDriver interactive mode: 
testdriverai
You’ll see a prompt (>) where you can enter commands.

​
Write tests using natural language

Simply describe what you want to test in plain English. For example: 
> click sign up
TestDriver will analyze your screen, interpret your instruction, and generate a test script to achieve the goal. It can see your UI, control the mouse and keyboard, and automate complex workflows—all through simple commands. 
thinking...

To accomplish the goal of clicking "Sign Up," we need to
focus on the Google Chrome application and then click on
the "Sign Up" button.

Here are the steps:

1. Focus the Google Chrome application.
2. Click on the "Sign Up" button.

commands:
  - command: focus-application
    name: Google Chrome
  - command: hover-text
    text: Sign Up
    description: button in the header
    action: click

command='focus-application' name='Google Chrome'
command='hover-text' text='Sign Up' description='button in the header' action='click'

​
4. Refine your test

If something doesn’t work as intended:
  • Use /undo to remove the last step: 
    > /undo
Modify your prompt or add new steps to refine the test.

​
5. Save your test

Once you’re satisfied with the test, save it to a YAML file: 
> /save
This generates a reusable YAML file (for example, testdriver.yaml) with all the steps.
TestDriver v5 uses the .yaml file extension for all test files. This is a breaking change from v4 which uses the .yml extension!