▶
ExecutionTrigger
Automation/Browser/Capture
Captures a region of the visible page at a higher device scale, so small text and icons stay legible for vision models. Coordinates are viewport CSS pixels, the same space as element bounding boxes and Click At Point. Chrome and Edge only.
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`.
Left edge of the region in viewport CSS pixels
Top edge of the region in viewport CSS pixels
Region width in CSS pixels
Region height in CSS pixels
Render scale: 2 doubles the region's pixel size (on top of the display's pixel ratio); up to 10
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`.
Region as base64 PNG data
Region as NodeImage