# How they use your computer

*Assign them work*

Your AI agent operates your browser and desktop apps the way a human would. Navigate web apps, fill forms, click buttons, move files, and complete multi-step workflows across any application. Install the lightweight companion app and your employee gains access to your entire machine.

Not every tool has an API. Automation lets your AI employee operate your browser and computer the way a human would.

The desktop companion app bridges your employee to your local machine. Available for macOS, Windows, and Linux.

Every action goes through the approval gateway. Your employee explains what it wants to do and waits for your permission.

## At a Glance

- **Any** Browser or desktop app
- **3** Platforms supported
- **Gated** Approval before action

## Use Cases

### Automate repetitive browser tasks

Your AI employee navigates websites, fills forms, clicks through workflows, and extracts data just like a human would, but faster and without breaks.

### Control desktop apps to get work done

Let your employee operate desktop software directly: open files, run programs, copy data between apps, and complete multi-step workflows without API access required.

### Monitor and interact with web dashboards

Your employee checks a dashboard, reads the current state, takes action based on what it sees, and reports back. No API needed if the data lives in a UI.

### Handle multi-step processes end to end

Chain browser and desktop actions into a full workflow: log in, pull a report, process the data, and upload results. One task, fully automated from start to finish.

## Features in this Category

- **[Control Any Browser](/en/features/automation/browser-automation)** — Your employee navigates web apps, fills forms, clicks buttons, and completes workflows that have no API.
- **[Control Any Desktop App](/en/features/automation/desktop-automation)** — Your employee operates desktop apps, moves files, and runs multi-app workflows from a real computer.