# Browser Tool (/docs/verdent-for-vscode/core-features/browser-tool)

> Automate web interactions, test UIs, and capture screenshots using browser sessions



The Browser Tool enables AI-driven browser interactions. Launch browser sessions, click elements, type text, scroll pages, and capture screenshots through natural language commands.

### What You'll Learn [#what-youll-learn]

* Session lifecycle: launch → interact → close
* Browser actions: click, type, scroll
* Use cases: UI testing, screenshots, navigation

***

## Session Lifecycle [#session-lifecycle]

Every browser automation workflow follows a strict sequence:

1. **Launch** - Start a browser session at a target URL
2. **Interact** - Perform actions (click, type, scroll)
3. **Close** - End the session to release resources

Browser state persists across actions within a session. You must close the browser before using other Verdent tools.

<Tip>
  Each action returns a screenshot showing the current browser state. Review screenshots between actions to verify success before proceeding.
</Tip>

***

## Browser Actions [#browser-actions]

<Tabs>
  <Tab title="launch">
    **Start a new browser session**

    * Required: target URL
    * Opens browser at 1920x1080 resolution
    * Always the first action in any workflow

    ```
    Launch browser at https://example.com
    ```
  </Tab>

  <Tab title="click">
    **Click at specific coordinates**

    * Required: x,y coordinates
    * Coordinates are viewport-relative
    * Target element centers for reliability

    ```
    Click coordinates 450,300
    ```
  </Tab>

  <Tab title="type">
    **Type text via keyboard**

    * Required: text to type
    * Types into currently focused element
    * Often follows a click on an input field

    ```
    Type "user@example.com"
    ```
  </Tab>

  <Tab title="scroll">
    **Scroll the page**

    * `scroll_down` - Scroll one page height down
    * `scroll_up` - Scroll one page height up
    * Reveals off-screen content

    ```
    Scroll down to load more content
    ```
  </Tab>

  <Tab title="close">
    **End browser session**

    * Always the last action in any workflow
    * Required before using other tools
    * Releases browser resources

    ```
    Close browser
    ```
  </Tab>
</Tabs>

<Tip>
  Coordinates are relative to the 1920x1080 viewport. Center is approximately (960, 540). Use screenshots to estimate element positions.
</Tip>

***

## Common Use Cases [#common-use-cases]

<Tabs>
  <Tab title="UI Testing">
    **Test form submissions and navigation flows**

    Launch at a login page, click input fields, type credentials, submit forms, and verify results through screenshots.

    ```
    Launch browser at https://app.example.com/login
    Click coordinates 450,280
    Type "testuser@example.com"
    Click coordinates 450,340
    Type "password123"
    Click coordinates 500,420
    Close browser
    ```
  </Tab>

  <Tab title="Screenshots">
    **Capture pages for documentation**

    Screenshots are captured automatically after each action. Navigate to target pages and sections to build visual documentation.

    ```
    Launch browser at https://docs.example.com
    Scroll down to API section
    Close browser
    ```
  </Tab>

  <Tab title="Navigation">
    **Navigate to target content**

    Use browser automation to reach content that requires interaction (clicking menus, loading lazy content) before extraction.

    ```
    Launch browser at https://store.example.com
    Scroll down three times
    Click "Next Page" at 960,800
    Close browser
    ```
  </Tab>
</Tabs>

***

## Limitations [#limitations]

* **Tool exclusivity** - Only browser\_action can be used during active sessions
* **Coordinate-based** - Requires x,y coordinates, not CSS selectors
* **Fixed resolution** - Browser viewport locked at 1920x1080
* **Chrome only** - Puppeteer supports Chrome/Chromium browsers
* **No persistence** - Sessions don't survive Verdent restarts
* **No WSL support** - Browser Tool does not work in WSL environments
* **No saved state** - Each session starts fresh without cookies or authentication
* **Single session** - Only one browser session can be active at a time

<Tip>
  Always close the browser session before using file operations, search tools, or bash commands. The browser locks other tools during active sessions.
</Tip>

***

## See Also [#see-also]

<CardGroup cols="3">
  <Card title="Code Diff" icon="code-compare" href="/docs/verdent-for-vscode/core-features/code-diff">
    Review and approve code changes
  </Card>
</CardGroup>