page.perform() method executes single, granular actions on a web page. It’s optimized for speed and reliability, using the accessibility tree instead of screenshots.
Overview
Basic Usage
Common Actions
Click Elements
Fill or Type Inputs
Form Interactions
Scrolling
Hover
Keyboard Actions
When to Use perform() vs ai()
Use page.perform()
- Single, specific actions
- When you know exactly what action is needed
- Fast, reliable execution
- Lower token cost
Use page.ai()
- Complex multi-step workflows
- When visual context is needed
- Tasks requiring decision making
- When next action depends on page state
Example: Combining Both
Return Value
page.perform() returns a TaskOutput object:
Checking Success
Error Handling
Tips for Writing Effective Instructions
Be specific about the target element
Be specific about the target element
Good: “click the blue ‘Sign Up’ button at the bottom of the form”Bad: “click the button”
Include context when elements look similar
Include context when elements look similar
Good: “fill the email input in the login form with user@example.com”Bad: “fill email”
Use visible text for identification
Use visible text for identification
Good: “click the link that says ‘Learn More’”Bad: “click the third link”
Specify the action clearly
Specify the action clearly
Good: “type ‘search query’ into the search box”Bad: “search for something”
CDP Actions
HyperAgent uses Chrome DevTools Protocol (CDP) for precise element interactions by default. This provides:- Exact coordinate-based clicks
- Deep iframe support
- Auto-filtering of ad frames
Next Steps
page.ai()
Complex multi-step automation
page.extract()
Extract structured data
Action Caching
Record and replay automations