Assistant Certify · beta preview
During the beta this page lists the steps you enter a record for. Enter the run IDs and dates from your own training runs and paste an Assistant Audit report. We do not check what you enter here, and nothing on this page is a certificate, a pass or a score. The criteria for certification are still being set, and they include an outside review of our tests, which is not complete.
A run on a scenario it never trained on
The same habit re-checked at least a day later
Outside review not complete.
Capability check · September 29, 2026
Simulated practice runs, selected checks on pasted conversation logs, and a self-entered beta checklist. No certificates or public quality scores are issued.
Internal measurement separates deterministic simulation, local model-backed runs and paid model-backed runs. Before/after improvement, held-out transfer and later retention need their own evidence; more runs do not establish them.
Read the measurement status · Try the selected-check audit · Review the beta checklist