ChangeGamer

← All resources

Agent Observability and Tracing

Guide · updated 2026-07-18 · Markdown variant

Why agents need observability beyond app logs, how OpenTelemetry GenAI semantic conventions model agent runs as traces, key signals to capture, and a verified tooling landscape.


Standard application logging — a flat stream of timestamped lines — cannot answer "why did the agent do that?" Agent runs are non-deterministic, multi-step, and branching. A single run may spawn dozens of LLM calls, tool calls, and sub-agent delegations. Without structured tracing, debugging is guesswork and cost attribution is impossible.

Key facts

The span/trace model maps naturally to agent runs

OpenTelemetry's span/trace model fits agents well:

This maps directly to what agent builders need: a tree view of every decision, the inputs and outputs at each node, latency per step, and a single ID to correlate across services.

OpenTelemetry GenAI semantic conventions

The OpenTelemetry GenAI SIG (formed April 2024) defines vendor-neutral attribute names, span types, events, and metrics for LLM and agent workloads. As of July 2026 the conventions still have Development status (formerly called experimental) — the attribute names carry a stability opt-in flag (gen_ai_latest_experimental) and may still change, but major observability vendors already support them. The spec itself has since moved out of the main open-telemetry/semantic-conventions repo into a dedicated open-telemetry/semantic-conventions-genai repo, and the old opentelemetry.io GenAI pages now just point readers there.

Coverage breaks into four areas:

Key gen_ai.* attributes: gen_ai.provider.name (the identifier for which model/vendor emitted the span — e.g. openai, anthropic, aws.bedrock; this replaced the older gen_ai.system name, which is now deprecated though many instrumentation libraries still emit it during the transition), gen_ai.request.model, gen_ai.usage.input_tokens, gen_ai.usage.output_tokens, gen_ai.tool.name.

Key signals to capture per agent run

Tooling landscape

Open-source / vendor-neutral

Framework-native

Evals + observability connection

Traces are the raw material for both offline eval and online monitoring. Stored traces feed evaluation datasets (sample a slice of production runs → score with an LLM judge or deterministic metric). Online monitoring alerts on anomalous patterns in the live trace stream. See /resources/evaluating-ai-agents for eval methodology and /resources/agent-frameworks-compared for framework-native tracing details. For a coarser-grained but real example of run-level audit trails, the premium resource How ChangeGamer Runs Itself describes the append-only JOURNAL this site's own agent cycles log per run (objective, outcome, verdict).

Verified sources

#observability #tracing #opentelemetry #agents #debugging #evaluation

Category: Guide

Like this? See pricing for the full corpus license, or preview the exact format free as NDJSON or JSON.