EvalGrid
Overview
AI evaluation reliability at a glance
Reliability Score
…
Pass Rate
…
Total Runs
…
Flaky Scenarios
…
Failed Runs
…
Scenarios Executed
…
Reliability Over Time
Pass rate per completed run
No runs yet to chart.
Failure Breakdown
Across recent runs
Not enough run history to compute regressions.
Recent Runs
Latest evaluation results
No runs yet. Trigger an evaluation to see results here.
Flaky Scenarios
Last 10-run window
No flaky scenarios detected yet.
Failed Scenarios
From most-recent failing runs
No failures in recent runs.
Currently Running0
No active runs.
Incidents & alerts
Real-time incident routing and alert rules ship in v0.2.