Project signals
Evals, CI checks, benchmarks and deploy pipelines for each project, with pass-rate trends, regressions against the previous run, and the evidence behind every verdict.
Projects
4
Signals
21
Evals failing
3
Evals regressed
0
Runs, last 7d
101
Last ingest
1h ago
Needs attention
| polyphony · eval · dracula · ci | gemini-3.5-flash-lite | ✗ 0% | 11h ago | what changed → |
| polyphony · eval · frankenstein · ci | gemini-3.5-flash-lite | ✗ 0% | 11h ago | what changed → |
| polyphony · eval · wuthering · ci | gemini-3.5-flash-lite | ✗ 0% | 10h ago | what changed → |
Projects
polyphony
✗ failingEvals & checks
- eval · cel · ci✓ 100%3d ago
- eval · dracula · ci✗ 0%11h ago
- eval · frankenstein · ci✗ 0%11h ago
- eval · wuthering · ci✗ 0%10h ago
pg_kafka
✓ passingBenchmarks
blog
✓ passingDelivery pipeline
- build · beta—✓ —4d ago
- build · prod—✓ —2h ago
- deploy · beta—✓ —4d ago
- deploy · prod—✓ —2h ago
- verify · beta—✓ —4d ago
- verify · prod—✓ —2h ago
tracer
✓ passingEvals & checks
- api+test · prod✓ 100%2h ago
Delivery pipeline
- deploy · prod—✓ —4d ago
- verify · prod—✓ —4d ago
Recent runs
show delivery pipelineall runs →| When | Project | Signal | Model / source | Pass rate | |
|---|---|---|---|---|---|
| 1h ago | pg_kafka | benchmark · ci | pg_kafka | ✓ 12,299 msgs/s | detail → |
| 2h ago | tracer | api+test · prod | greenlight-verify | ✓ 100% | detail → |
| 8h ago | pg_kafka | benchmark · ci | ae666ab | ✓ 100% | detail → |
| 10h ago | polyphony | eval · wuthering · ci | gemini-3.5-flash-lite | ✗ 0% | detail → |
| 11h ago | polyphony | eval · dracula · ci | gemini-3.5-flash-lite | ✗ 0% | detail → |
| 11h ago | polyphony | eval · frankenstein · ci | gemini-3.5-flash-lite | ✗ 0% | detail → |
| 15h ago | polyphony | eval · frankenstein · ci | claude-opus-5-5 | ✗ 0% ≠ not comparable | detail → |
| 15h ago | polyphony | eval · dracula · ci | claude-opus-5-5 | ✓ 100% ≠ not comparable | detail → |
| 29h ago | tracer | api+test · prod | greenlight-verify | ✓ 100% | detail → |
| 40h ago | polyphony | eval · frankenstein · ci | claude-opus-5-5 | ✓ 100% ≠ not comparable | detail → |
| 40h ago | polyphony | eval · dracula · ci | claude-opus-5-5 | ✓ 100% ≠ not comparable | detail → |
| 44h ago | polyphony | eval · frankenstein · ci | claude-opus-5-5 | ✓ 100% ≠ not comparable | detail → |
Operator
Runs the built-in demo suite on every enabled provider. Needs the ingest token.