▶
Executionexec_in
Trigger
Automation/LLM/Vision
Uses vision LLM to classify screen state and identify visible elements
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Trigger
Vision-capable LLM model
Screenshot as base64 PNG, JPEG, WebP or GIF (a data URL is fine). Ignored when Image is connected
Screenshot as an image, e.g. from the Screenshot node. Takes precedence over the base64 Screenshot
Comma-separated list of possible states to classify into
Continue
Screen classification result
Detected screen type
Current screen state