Why it matters

Without observability, agents are black boxes. When users complain, you can't reproduce or diagnose. With good instrumentation, you can trace exactly what happened.

Advertisement

The architecture

OpenTelemetry: standard for traces + metrics. Every agent step becomes a span; spans nest to show turn structure.

Spans: agent turn (outer), model call (inner), tool call (inner). Tags include model, tool name, token counts, latency.

Observability pillarsTracesspan per stepMetricslatency, tokens, toolsStructured logscontext enrichedCloud Trace, Datadog, Honeycomb all consume OTel; pick your platform
Three observability pillars.
Advertisement

How it works end to end

Metrics: request rate, error rate, p50/p95/p99 latency, token count per turn, tool call count, cost estimate.

Structured logs: JSON logs with correlation IDs. Include session ID, user ID, request ID.

Tracing sensitive data: model inputs/outputs can contain PII. Redact before shipping to observability platform.

Cost tracking: token count × price per token = cost per request. Track for cost accounting.