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
Edit Configuration
Recent Evaluation Runs
DateTypeStatusShip/No ShipPass RateCritical %
07/02/2026, 14:20:00RegressionrunningShip94%1.8%
04/02/2026, 14:20:00Release GatefailedNo Ship89%3.8%
01/02/2026, 14:20:00RegressionpassedShip94%2.5%
29/01/2026, 14:20:00Release GatepassedShip99%1.2%
26/01/2026, 14:20:00RegressionfailedNo Ship94%3.1%
23/01/2026, 14:20:00Release GatepassedShip93%1.8%
20/01/2026, 14:20:00RegressionfailedNo Ship88%3.8%
17/01/2026, 14:20:00Release GatepassedShip93%2.5%
14/01/2026, 14:20:00RegressionpassedShip98%1.2%
11/01/2026, 14:20:00Release GatefailedNo Ship93%3.1%