---
title: "Computer Use"
description: "Computer Use skill for Vellum — control your Mac directly with screen observation, clicking, typing, and AppleScript."
canonical_url: "https://www.vellum.ai/docs/skills-reference/computer-use"
md_url: "https://www.vellum.ai/md/docs/skills-reference/computer-use"
related:
  - "/docs/skills-reference"
  - "/docs/skills-reference/acp"
  - "/docs/skills-reference/amazon"
  - "/docs/skills-reference/app-builder"
  - "/docs/skills-reference/browser"
  - "/docs/skills-reference/chatgpt-import"
  - "/docs/skills-reference/contacts"
  - "/docs/skills-reference/document"
---

# Computer Use

## What it does

Controls your Mac directly — observes the screen via accessibility APIs and screenshots, clicks, types, scrolls, drags, opens apps, and runs AppleScript. Your assistant's hands and eyes on your desktop.

## Setup required

None (built into the macOS app). Requires macOS system permissions.

## Permissions

- Accessibility (mouse/keyboard control)
- Screen Recording (seeing screen content)
- Each action is prompted individually for approval

## Common prompts

| You say...                                | What happens                  |
| ----------------------------------------- | ----------------------------- |
| “Open Safari and go to my bank's website” | Opens app and navigates       |
| “Click the Submit button”                 | Clicks a specific UI element  |
| “Fill out this form with my info”         | Types into form fields        |
| “Take a screenshot of what's on screen”   | Captures current screen state |
| “Switch to Slack and check my DMs”        | Navigates between apps        |
| “Scroll down to the pricing section”      | Scrolls within an app         |

## Configuration

- No configuration needed
- Step limit of 50 actions per session
- Each action requires approval unless you create trust rules via the Allow button

## Tips & gotchas

- **Accessibility tree + screenshots.** The assistant reads the accessibility tree (same API screen readers use) AND takes screenshots for a complete picture.
- **Element-based clicking.** It prefers clicking by element name rather than coordinates for reliability.
- **Session caps.** Sessions are capped at 50 steps with loop detection.
- **macOS only.** Computer use is macOS only — not available on other channels.
- **Screen visibility.** Be mindful of what's visible on screen — screenshots are sent to the AI model.