▶
Executionexec_in
Trigger
Automation/LLM/Healing
Uses LLM to diagnose automation failures and suggest/apply healing actions
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Trigger
LLM model (vision-capable preferred)
Base64-encoded screenshot at time of failure
The error message from the failed action
Type of action that failed (click, type, wait, find, etc.)
The target of the failed action (selector, coordinates, text)
Additional context about what the automation was trying to do
Current page HTML (for selector-based failures)
Continue (Healed)
Could not heal
Full healing result
Failure diagnosis
Healed value (new selector, coordinates, etc.)