Now in closed beta.Book a demo to get started.
Use cases

Add the alert that would have paged sooner

Incident follow-through|The work pauses once the plan is written. Somebody reads the approach and approves it before any code exists, and the run continues from there.

An alert on the signal that moved first, back-tested against the incident window.

The ticket

Add the alert that would have paged before the incident became visible to users.

Acceptance criteria

  • The rule fires when replayed against the incident window
  • It does not fire against a comparable healthy window
  • It links to a runbook that exists
  • The routing destination is a person or rotation, not an unwatched channel

What lands as proof

The rule replayed against both the incident window and a healthy one, showing it fires for the first and not the second.

Why teams defer it

  • An alert that fires too often gets muted within a week, so tuning it is the actual work.
  • Back-testing needs retained metrics at the right resolution, and the retention window may already have passed.

Questions

What does the agent actually change?
The ticket is scoped to one outcome: add the alert that would have paged before the incident became visible to users. Work that serves that outcome is in scope, and anything outside it is left for a separate ticket, so the pull request stays reviewable.
How do I know the work is done?
The pull request carries the evidence, not only the diff. Here that means rule and runbook in the same pull request, so a reviewer can confirm the result without reproducing the work locally.
How much oversight does this need?
The run stops once the plan is written. Somebody reads the approach and approves it before any code exists, which is the cheapest moment to redirect the work.

Ready to put the fleet to work?

Contact us for a demo with an expert.