Agentic AI Reference Architecture

Observability & Evaluation · Interface

Replica Metrics Endpoint

InterfaceObservability & EvaluationObservability & Evaluationarc:ReplicaMetricsEndpoint

An on-demand endpoint through which each replica reports its current load state (CPU, memory, queue depth, recent latency) for polling by load balancers and metrics collectors.

Responsibility. Exposes a replica's current load metrics on request.

Also known as: /metrics endpoint

is invoked by; is cached byis exposed byis invoked byMetric-Aware Load Balancer: is invoked by; is cached byMetric-Aware Load BalancerAgent Controller: is exposed byAgent ControllerMetrics Collector: is invoked byMetrics Collector
Direct neighbourhood (hover for relationship types)

Relationships

is exposed by structural

is cached by dependency

is invoked by dependency

Classification

Patterns
Pull-based metrics exposition
Quality attributes
Maintainability (ISO/IEC 25010)

Sources

  1. Ch4.7: T. Nguyen, "Scaling Strategies," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.7. ISBN: 9798244538229.