Desktop Tools
Bom can see, click, type, and control windows on your desktop — just like you would.
Screenshots
Bom can take a screenshot of your screen at any time. It uses these screenshots to understand what is on your screen and decide what to do next.
- Full screen or a specific area
- Support for multiple monitors
- Smart detection of interface elements (buttons, menus, text fields)
Tip
When Bom takes a screenshot, it can identify clickable elements and number them. This is how it knows where to click.
Mouse and Keyboard
Bom can control your mouse and keyboard to interact with any application:
- Click at any position on the screen
- Type text into any text field
- Press keyboard shortcuts (like copy, paste, save)
- Scroll up and down
- Drag and drop
Window Management
Bom can see all open windows and control them:
- List all open windows
- Bring a specific window to the front
- Minimize, maximize, or close a window
- Get the position and size of any window
Interface Automation
For more precise control, Bom can directly interact with interface elements like buttons, checkboxes, and text fields — without needing to know their exact screen position.
- Find a button by its name and click it
- Read the text in a specific field
- Check or uncheck a checkbox
- Wait for an element to appear before continuing