▶
ExecutionTrigger
Automation/Browser/Interact
Clicks at viewport CSS coordinates instead of an element, for canvas apps and coordinates read off a screenshot by a vision model. Requires Chrome or Edge.
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Trigger
Automation session
Browser context info if browser is attached
Current page info if a page is open
Visible text contained in the element; script, style and head content is ignored.
ARIA role, optionally filtered by accessible name: `button`, `button|Sign in` (case-insensitive substring), `button|=Sign in` (exact) or `button|/^sign/i` (regex).
Element ref from the latest Browser Snapshot, such as `e12`.
Horizontal position in viewport CSS pixels
Vertical position in viewport CSS pixels
Mouse button to press
1 for a click, 2 for a double click, 3 for a triple click
Keys held during the click: Control, Shift, Alt, or Meta
Continue
Updated automation session
Browser context info if browser is attached
Current page info if a page is open
Visible text contained in the element; script, style and head content is ignored.
ARIA role, optionally filtered by accessible name: `button`, `button|Sign in` (case-insensitive substring), `button|=Sign in` (exact) or `button|/^sign/i` (regex).
Element ref from the latest Browser Snapshot, such as `e12`.