DocsPage Interactionbrowser_ai_click

browser_ai_click

Browser Ai Click

Click an element described in natural language using AI vision. The AI analyzes the page screenshot to find and click the element matching your description. Example: 'the blue submit button'.

Usage Example

123456789101112
import asyncio
from owl_browser import OwlBrowser, RemoteConfig
# Async usage
async with OwlBrowser(config) as browser:
context = await browser.create_context()
context_id = context["context_id"]
await browser.ai_click(
context_id=context_id,
description="value"
)

Parameters

Required

context_idstringrequired

The unique identifier of the browser context (e.g., 'ctx_000001')

descriptionstringrequired

Natural language description of the element to click (e.g., 'search button', 'the login link at the top')

Response

Returns a JSON object with the operation result.

{
  "success": true,
  "result": <value>
}