Agent Status
Live health of the AI pipeline behind every triage decision. Degraded agents fall back to deterministic rules — no silent failures.
Active agents
3/4
running
System health
95%
weighted avg
Tasks processed
5,039
last 24h
Error rate
0.26%
13 errors
Pipeline status
DEGRADED
1 agent below SLO
Agent fleet (4)Per-agent health, throughput, latency and uptime. Click row to expand (coming soon).
Correlation Engine
Cross-source pivot graph · v2.4.1
Running
Health
100%
Processed
1,361
Errors
0
Avg
141ms
Uptime
105d
Last
Just now
Risk Scorer
Per-case AI risk 0–100 · v1.8.0
Running
Health
98%
Processed
1,361
Errors
2
Avg
113ms
Uptime
105d
Last
Just now
MITRE Mapper
ATT&CK technique tagging · v3.0.2
Running
Health
100%
Processed
1,066
Errors
0
Avg
126ms
Uptime
105d
Last
Just now
LLM Triage Advisor
Justification + recommended action · v1.2.4
Degraded
Health
82%
Processed
1,251
Errors
11
Avg
1820ms
Uptime
105d
Last
12 sec ago
Task processing volume (7d)Total triage tasks completed across all agents per day.
Average response time (ms, 7d)Per-agent p50 response latency. The LLM Advisor runs at ~10× the deterministic agents — expected.
Agent health is observed from the AI runtime queue (Redis Streams) and vLLM inference logs. Degraded agents auto-fall back to deterministic rules; cases never fail silently.