The AI can control any browser session in your space, navigating to URLs, clicking elements, typing text, taking screenshots, and reading page content. The same interface works across Kazzle Browser, cloud browser sessions, and Chrome or Brave via the extension.Documentation Index
Fetch the complete documentation index at: https://docs.kazzle.com/llms.txt
Use this file to discover all available pages before exploring further.
How it works
- The AI opens (or reuses) a browser session
- It navigates to the target URL
- It reads the page content or takes a screenshot
- It clicks, types, scrolls, or waits as needed
- Results flow back into the thread
What the AI can do
| Action | Description |
|---|---|
| Navigate | Go to any URL |
| Read content | Get page text (preferred, cheap and fast) |
| Screenshot | Capture the visible page (use sparingly, expensive) |
| Click | Click by text label, selector, or coordinates |
| Type | Type into the focused element |
| Scroll | Scroll up or down |
| Wait | Pause for page changes (max 10 seconds) |
| Read elements | Extract interactive elements for structured navigation |
Handoff between you and the AI
Sessions are shared. The AI can target a tab you opened, and you can pick up where the AI left off.- You open a tab. The AI can see it and interact with it.
- The AI opens a session. You can watch via the live view URL or open the same tab.
- Extension sessions. Your Chrome window is the AI session. The AI navigates the same browser you see.
Which browser the AI uses
When the AI opens a browser session, the best available option is picked automatically:- Chrome or Brave (your real browser) - preferred when connected
- Cloud browser - when no local browser is connected
- Kazzle Browser - fallback