Skip to main content

Documentation Index

Fetch the complete documentation index at: https://momentic.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

When a run fails, Momentic analyzes screenshots, page state, step descriptions, and error traces to surface the likely root cause, so you can triage without replaying the run.

​
What it considers

  • Screenshots before and after each step to spot overlays, misalignment, or unexpected UI changes
  • Page state and URL at the moment of failure
  • Step descriptions and actions to understand intent
  • Element targeting details to catch hidden or disabled elements
  • Error message and stack

​
Where you see it

The run viewer surfaces failure analysis under the AI failure analysis tab:
  • Error summary
  • Root cause analysis + suggested fix
  • Error details (message, stack)
  • Summary of previous steps
Failure analysis
The CLI also prints a root cause summary, classified error type, and a fallback description when RCA isn’t available.

​
Manual classification override

The AI’s classification is a starting point. From the AI failure analysis tab you can override the category and add a reason — useful when the AI miscategorizes a failure or when you want to attribute a run to a category your team tracks. Manual overrides are visually distinct from AI classifications in the run viewer, and the run keeps both: the AI’s original category is archived as the previous classification when you save your override. The override flows through the same write path as the AI classifier, so it shows up in dashboard filters and metrics.

​
Configuration

Set ai.aiFailureAnalysis in momentic.config.yaml:
momentic.config.yaml
ai:
  aiFailureAnalysis: true