# Agent tracing

**Source:** https://promtable.com/glossary/agent-tracing

> Agent tracing captures the full execution graph of an agent run — every step, every tool call, every model output — so engineers can debug, audit, and improve the agent over time.

---
Agent tracing captures the full execution graph of an agent run — every step, every tool call, every model output — so engineers can debug, audit, and improve the agent over time.

Production agents in 2026 are impossible to debug without tracing. Each agent run emits a structured trace: planner step, tool calls + arguments + results, model outputs at each step, latency per stage, total token spend, final outcome. Tools that ship tracing: Langfuse, Braintrust, Phoenix (Arize), LangSmith, OpenLLMetry. Best practice: trace 100% of production runs but sample for evals; pin prompt version IDs to traces; alert when failure rate or token budget spikes. Tracing turns agents from black boxes into observable systems.

## When to use

- Any production agent.
- Multi-step LLM pipelines.

## Common mistakes

- Tracing only failures — you need success samples to know what good looks like.
- No version pinning in traces — can't attribute regressions to prompt changes.

## Related terms

- [evals](https://promtable.com/glossary/evals)
- [prompt-versioning](https://promtable.com/glossary/prompt-versioning)
- [agent](https://promtable.com/glossary/agent)
- [agent-loop](https://promtable.com/glossary/agent-loop)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/agent-tracing
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/agent-tracing".
Contact: info@vibecodingturkey.com.