Live Engineering Dashboard
Performance Dashboard
Real-time API latency, throughput, and system metrics. Monitor all AI services from a single pane.
Live
Updated 0s agoAPI Latency (p50)
120ms
Throughput
245req/min
Uptime
99.97%
Error Rate
0.12%
API Latency Over Time
p50p99
~2 min windowp50: 137ms | p99: 328ms
Endpoint Performance
| Endpoint | Method | Avg Latency | p99 | Requests▼ | Error Rate |
|---|---|---|---|---|---|
| /api/v1/ml/classify-url | POST | 12ms | 45ms | 3,456 | 0.0% |
| /api/v1/rag/query | POST | 85ms | 240ms | 1,234 | 0.1% |
| /api/v1/nlp/sentiment | POST | 34ms | 89ms | 892 | 0.2% |
| /api/v1/validation/score | POST | 45ms | 120ms | 678 | 0.1% |
| /api/v1/agents/execute | POST | 3,200ms | 5,100ms | 156 | 0.5% |
CPU Usage
Normal
Memory
512/ 1024 MB
50.0% utilized
Active Connections
12
Max pool: 28