AI Reliability Console
Monitor behavior, manage risk, and ship confidently
AI
AI - Concierge Agent
Guides customers through shopping and account actions.
Model: gpt-4o3 metrics linked1 datasets linked
Recent Evaluation Runs
| Date | Type | Status | Ship/No Ship | Pass Rate | Critical % |
|---|---|---|---|---|---|
| 07/02/2026, 14:20:00 | Regression | running | Ship | 94% | 1.8% |
| 04/02/2026, 14:20:00 | Release Gate | failed | No Ship | 89% | 3.8% |
| 01/02/2026, 14:20:00 | Regression | passed | Ship | 94% | 2.5% |
| 29/01/2026, 14:20:00 | Release Gate | passed | Ship | 99% | 1.2% |
| 26/01/2026, 14:20:00 | Regression | failed | No Ship | 94% | 3.1% |
| 23/01/2026, 14:20:00 | Release Gate | passed | Ship | 93% | 1.8% |
| 20/01/2026, 14:20:00 | Regression | failed | No Ship | 88% | 3.8% |
| 17/01/2026, 14:20:00 | Release Gate | passed | Ship | 93% | 2.5% |
| 14/01/2026, 14:20:00 | Regression | passed | Ship | 98% | 1.2% |
| 11/01/2026, 14:20:00 | Release Gate | failed | No Ship | 93% | 3.1% |