Overview

Operational overview

Overview

Connect, test, understand, reproduce, and export evidence from actual evaluation calls.

Run evaluation
Completed runs
0
0 total recorded
Observed pass rate
—
No scored cases
Inference errors
0
Excluded from the pass rate
p95 latency
—
0 successful attempts

Recent evaluations

View results

No evaluation runs yet

Select a verified connection and at least one suite to run your first bounded test.

Configure a run