Observability for AI agents
Monitor, meter, and report on every AI agent in your org
Trenchcoat gives engineering teams complete visibility into AI agent usage, token spend, and session activity — starting with Claude Code.
No credit card required
Session timeline
Replay any session turn by turn — every tool call, error, and stop reason, with time spent per phase.
Cache-aware cost
Real cost per session and per agent, priced from live model rates with cache reads and writes counted.
Agent tracing
Trace the full spawn tree a session launches — model, tool count, cost, and latency for every subagent.
Evals
Tag sessions and record eval scores through the API to track agent quality over time.
Skill analytics
See which skills your agents reach for, and how often, across every session.
Team access
Share dashboards, manage API keys, and control who sees what.
Coming soon
More ways to plug in
Trenchcoat is expanding beyond Claude Code.
OpenAI Agents SDK
Instrument agents built on the OpenAI Agents SDK and stream their telemetry into Trenchcoat.
GitHub Copilot
A Copilot Extension that reports agent activity from your GitHub workflow into Trenchcoat.
Get started
Get visibility into your AI agents in minutes
Connect the Trenchcoat plugin, events start flowing immediately
Start for free