Project signals
Real verification history for LLM evals, agent runs, API checks, and project pipelines like pg_kafka — pass rate, regressions, and comparisons.
Pass rate over time (30d)
Latest run per tool
| Tool | Model | Env | Pass rate | Result | When |
|---|---|---|---|---|---|
| blog | greenlight | prod | — | pass | 2026-08-25 13:47 |
| pg_kafka | ae666ab | ci | 100% | pass | 2026-08-25 14:12 |
| polyphony | gemini-2.5-flash | ci-frankenstein | 50% | fail | 2026-08-24 07:43 |
| tracer | unknown | prod | 71% | fail | 2026-08-25 12:50 |
Recent runs
| When | Tool | Model | Env | Pass rate | Cost | |
|---|---|---|---|---|---|---|
| 2026-08-25 14:12 | pg_kafka | ae666ab | ci | 100% | — | detail → |
| 2026-08-25 13:47 | blog | greenlight | prod | — | — | detail → |
| 2026-08-25 13:47 | blog | greenlight | prod | — | — | detail → |
| 2026-08-25 13:47 | blog | greenlight | prod | — | — | detail → |
| 2026-08-25 12:50 | tracer | unknown | prod | 71% | — | detail → |
| 2026-08-24 14:10 | pg_kafka | ae666ab | ci | 100% | — | detail → |
| 2026-08-24 13:49 | blog | greenlight | prod | — | — | detail → |
| 2026-08-24 13:49 | blog | greenlight | prod | — | — | detail → |
| 2026-08-24 13:49 | blog | greenlight | prod | — | — | detail → |
| 2026-08-24 12:53 | tracer | unknown | prod | 71% ↓ regression 86% → 71% | — | detail → |
| 2026-08-24 07:43 | polyphony | gemini-2.5-flash | ci-frankenstein | 50% | — | detail → |
| 2026-08-24 07:37 | polyphony | gemini-2.5-flash | ci-dracula | 33% ↓ regression 60% → 33% | — | detail → |