Skip to content

Federated Observability

Multi-region metrics aggregation and performance monitoring

Regional Performance Metrics
Real-time latency and throughput across all regions
Latency Percentiles Explained

P50 (Median)

50% of requests complete faster than this time. Represents typical user experience.

P95

95% of requests complete faster than this. Key SLA metric for performance.

P99 (Tail Latency)

99% of requests complete faster. Identifies outliers and worst-case scenarios.

LyDian OS — AI Economy Operating System