This is a public, interactive preview. Every project, run, score, and payment below is sample data. Nothing is saved or sent to a server.
Projects
Evaluation health across your agent workspace.
Runs
Every evaluation run, newest first.
| Project | Label | Pass rate | Gates | Cases | Started | Actions |
|---|
No runs match
Try a different project or gate filter.
Scorers
Performance and regressions across stored evaluation runs.
Scorer health
Lowest pass rates appear first so regressions are easy to spot.
| Scorer | Pass rate | Mean score | Results | Failed | Errors |
|---|
Recent problems
Failed and errored results that deserve attention.
Economics
Agent payment activity captured inside evaluated traces.
Spend by project
Successful settlements recorded in sample eval traces.
| Project | Settled USD | Settled | Failed | Budget status |
|---|
Recent payments
Inspect x402 settlements, failures, networks, and recipients.
| Status | Project / run | USD | Network | Recipient | When |
|---|