# Usage Examples

## Basic Screen Understanding

```
User: "看看屏幕上有什么"
→ Screenshot → AI describes what's on screen → Report to user
```

## Open Application

```
User: "帮我打开Chrome浏览器"
→ Screenshot → AI finds desktop/taskbar → Click Chrome icon → Wait → Verify opened
```

## Web Search

```
User: "帮我百度搜索北京天气"
→ Screenshot → Find browser → Open/type baidu.com → Type "北京天气" → Press Enter → Screenshot result
```

## File Operation

```
User: "把桌面上的report.txt复制到Documents文件夹"
→ Screenshot → Find file → Right click → Copy → Navigate to Documents → Paste
```

## Form Filling

```
User: "帮我在XXX网站注册账号，邮箱用test@example.com"
→ Screenshot → Navigate to site → Fill form fields → Submit
```

## Terminal Operation

```
User: "打开终端执行 df -h"
→ Screenshot → Find terminal → Open → Type "df -h" → Press Enter → Screenshot result
```

## Screenshot Capture

```
User: "截个屏给我看看"
→ Screenshot → Send image to user
```

## Complex Multi-step Task

```
User: "帮我下载这个PDF并保存到Downloads文件夹"
→ Screenshot → Find link → Click → Handle download dialog → Verify in Downloads
```
