Outcomes
Whether the run finished, stopped, or needs review.
Every governed run leaves a readable record. Atlas keeps it, so you can inspect what happened instead of trusting an agent's "done".
Whether the run finished, stopped, or needs review.
Whether the configured verifier actually passed.
Which of the 13 failure classes appeared, and when.
How many attempts the run took before it settled.
Whether the run receipt checks out cryptographically — reported separately from task verification.
Spend where it was recorded. Unknown cost is shown as unknown, never as $0.