▶
ExecutionTrigger
Automation/LLM/Planning
Uses LLM to plan a sequence of automation actions to achieve a goal
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Trigger
Vision-capable LLM model
Current screenshot as base64 PNG, JPEG, WebP or GIF (a data URL is fine). Ignored when Image is connected
Current screenshot as an image, e.g. from the Screenshot node. Takes precedence over the base64 Screenshot
Screen frame of the screenshot, from the capture node. Coordinates are desktop input coordinates (ready for the mouse nodes) when Frame is connected, otherwise pixels of the original screenshot
General proposes actions for any surface. Browser creates a plan for Execute Browser Action Plan.
DOM or accessibility snapshot containing selectors for browser actions
What the automation should accomplish
JSON array of available action types and their parameters
Any constraints or preferences for the plan
Continue
Complete action plan
List of planned actions. In General plans parameters.x/parameters.y are a screen position in desktop input coordinates (ready for the mouse nodes) when Frame is connected, otherwise pixels of the original screenshot
The first action to execute