Overview
Monitor agent quality, evaluation runs, regressions, latency, and cost.
+12.5% from last month
1,284
Total Evaluation Runs
+3.2% from last month
86.4%
Average Pass Rate
5 unresolved
18
Regressions Detected
-8.1% from last month
2.4s
Average Latency
Evaluation Performance
Pass rate and regression rate across recent evaluation runs.
Evaluation Results
Latest run outcome distribution.
Passed72%
925Failed18%
231Needs Review10%
128Failure Categories
Breakdown of failed evaluation cases.
Incorrect Tool Use34%
Hallucination26%
Incomplete Task18%
Invalid Format13%
Timeout9%
Recent Evaluation Runs
Latest evaluation executions across your agents.
| Run | Agent | Test Suite | Version | Pass Rate | Regressions | Avg Latency | Cost | Status | Started At |
|---|---|---|---|---|---|---|---|---|---|
| #1284 | Customer Support Agent | Support QA Benchmark | v2.4.0 | 91.2% | 2 | 1.8s | $2.84 | Completed | 10 minutes ago |
| #1283 | Sales Assistant | Lead Qualification Set | v1.9.2 | 84.7% | 0 | 2.1s | $3.12 | Running | 24 minutes ago |
| #1282 | Code Review Agent | PR Review Benchmark | v3.1.0 | 78.3% | 5 | 3.4s | $4.56 | Needs Review | 1 hour ago |
| #1281 | Data Extraction Agent | Invoice Parsing Set | v2.0.1 | 62.5% | 8 | 2.9s | $1.98 | Failed | 2 hours ago |
| #1280 | Onboarding Assistant | Getting Started QA | v1.4.0 | 93.8% | 1 | 1.5s | $2.10 | Completed | 3 hours ago |
| #1279 | Research Agent | Knowledge Retrieval Set | v2.7.3 | 88.1% | 2 | 4.2s | $5.74 | Completed | 5 hours ago |