Operations4 min readUpdated April 8, 2026

Runs & statuses

How run execution works and what queued, running, completed, warnings, and failed mean in practice.

01

Overview

Every scan produces a run record that moves through a small, predictable state machine. The state is the single source of truth for whether results are trustworthy, and no dashboard widget shows numbers from a non-completed run.

02

Run lifecycle

Runs move forward only — there is no reverse transition. A run that hits warnings or failed stays in that terminal state; a retry creates a new run.

Queued
Accepted, waiting for a worker slot.
Running
Actively querying models and parsing responses.
Completed
All prompts succeeded; score is canonical.
Warnings
Score is usable but some prompts were skipped.
Failed
Too many prompts failed; score is not shown.
03

Failure handling

Individual prompt failures are tolerated up to a threshold. Below the threshold the run completes with warnings; above it the run is marked failed and no score is written.

No run credits in this billing model

Plans are enforced by audit limits only. When an audit cannot be saved, your usage count does not increase.

04

Retry behavior

Warnings and failed runs can be retried from the run history page. Retries create a brand-new run record; the original is preserved for audit. Retrying does not inherit any state from the previous run.

Still need help?

Didn't find what you're looking for?

Reach out and we'll point you to the right guide — or fast-track a new one.