# How to let an agent operate a desktop app when a task needs real clicks with orca

Repo: [stablyai/orca](https://github.com/stablyai/orca) | Difficulty: Advanced | Time: 1 hour | Basis: From the README

Use Computer Use so an agent can interact with visible desktop UI during a workflow.

**Who it is for:** Developer whose task requires poking at a native or visual app that has no API

**The problem:** Some checks, like confirming a desktop app renders correctly, cannot be done from a terminal alone.

**The outcome:** The agent operates the visible UI as part of the workflow and reports what it saw.

## Steps

1. Read the Computer Use docs linked from the README.
2. Enable the feature for the agent you want to use.
3. Give the agent a narrow task on a specific app.
4. Watch its actions and stop it if it goes off track.

## Prompt to paste into your agent

```text
Using stablyai/orca's Computer Use feature, have an agent open <app name> and perform <specific check>. Verify by reading back what the agent reports it clicked and saw.
```

## Caveat

Computer Use lets an agent control visible apps on your machine, so run it only on non-sensitive sessions and watch what it clicks.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/stablyai-orca/let-agents-operate-desktop-apps/