▶
Executionexec_in
Trigger
Automation/LLM/Vision
Uses vision LLM to comprehensively observe and describe the current screen
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Trigger
Vision-capable LLM model
Base64-encoded screenshot
Specific area or aspect to focus on (optional)
Continue
Complete screen observation
Text description of the screen
List of observed elements