Every rollout, fully explained.
Ingest episodes from your fleet or your sims — video, proprioception, actions. Replay any run on one synced timeline, trace every step, and let the judge grade what happened.
● head
hand_left
hand_rightYour failures are your best data.
Most stacks evaluate in simulation, before deployment, and go blind the moment a policy ships. pocy watches the other side: every real rollout is graded, the sub-failures are mined out, and each one comes back as a test the next version has to pass.
One loop: grade every rollout, cluster the failures, reconstruct them in sim, and gate the next release on them. Every pass turns production time into labeled, reproducible test data.
Every graded rollout feeds a failure taxonomy. Clusters rank by severity × rate × trend — a prioritized queue, not a folder of videos.
A production failure becomes a simulation task — that grasp, that part, that approach angle — and joins the suite your next policy must pass.
Suites wire into CI with real exit codes. Green ships; red names the exact rollout and the exact reason.
