Getting Started

Record browser interactions and get automation code. This guide will walk you through installation, capturing your first interaction, and generating reusable code.

Installation

Install the Chrome Extension

Install the InverseUI Chrome extension to start capturing UI interactions:

  1. Open Chrome Web Store
  2. Search for 'InverseUI'
  3. Click 'Add to Chrome'
  4. Sign in with your Google account

Once installed, you'll see the InverseUI icon in your browser toolbar. Click it to start recording your first interaction.

First Project

Let's capture your first UI interaction and generate automation code.

1. Start Recording

Click the InverseUI extension icon and perform any actions you want to automate:

  1. Click the InverseUI extension icon
  2. Select "Start Recording"
  3. Perform any actions in the browser (clicks, typing, navigation, etc.)
  4. Click "Stop Recording" when you're done

2. Review Recording

After recording, InverseUI captures all your interactions:

Actions Captured

All clicks, inputs, and navigations are recorded

Smart Detection

InverseUI identifies variable inputs automatically

3. Generate Code

After recording, InverseUI will automatically generate code that you can use in your automation scripts. The generated code includes all the interactions you recorded, with parameters automatically detected for reusable inputs.

You can configure which framework to use (Playwright or Selenium) in your account settings. Download the generated code and integrate it into your existing automation framework, or use our Recording API to programmatically control the recording process.

Basic Concepts

Understanding these core concepts will help you get the most out of InverseUI.

How It Works

InverseUI captures your interactions and generates automation code:

  • Records exact UI interactions
  • Identifies variable inputs (parameters)
  • Generates clean Playwright/Selenium code

Why Agents Love InverseUI

Traditional agents waste tokens and time parsing UI. InverseUI gives them muscle memory:

  • Token Efficient: 100x fewer tokens per action compared to UI parsing
  • Lightning Fast: Direct function calls instead of multi-step reasoning
  • Reliable: No more brittle chains of LLM reasoning