▶
Executionexec_in
Trigger
Automation/LLM/Vision
Uses a vision LLM to locate UI elements based on natural language description
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Trigger
Vision-capable LLM model
Base64-encoded screenshot of the screen
Natural language description of the element to find (e.g., 'the blue submit button')
Optional context about the application or page
Continue
Element not found
Element location details