The quality, regression, and release-control mesh for the PlatPhorm ecosystem.
Discover targets from the network graph, MCP Hub, Claws, Spec, Trace, BrowserOps, AgentUI, Sandbox, Docs, and Webhook Lab. Turn capabilities into deterministic, model-graded, browser, replay, and workflow evaluations.
Eval Suites
Active evaluation suites across the network
Recent Runs
Latest evaluation run results
| Suite | Status | Score | Duration | Timestamp |
|---|---|---|---|---|
| MCP Tool Validation | passed | 94% | 2m 34s | Today, 14:23 |
| Spec Contract Compliance | passed | 88% | 1m 12s | Today, 10:15 |
| Trace Integration Tests | failed | 76% | 4m 56s | Yesterday, 22:45 |
| Browser Journey Tests | running | — | — | Now |
Network Coverage
Eval coverage across 8 services in the PlatPhorm network
Network Integrations
Connected services powering the evaluation mesh
71 tools, 12 resources, 9 prompts
150+ federated tools across 84 sites
OpenAPI, AsyncAPI, JSON Schema validation
Causal lineage and time travel debugging
Methodology publishing and examples
Isolated MCP testing playground
Real browser journey execution
Event replay and delivery testing
Ready to evaluate your services?
Start by syncing from the network graph, then create eval suites, run them against your targets, and gate releases with confidence.