How ready are your agents for a bad day? Get your score

Recorded by default

Every run records itself — no SDK, no collector, nothing to instrument.

WhereTracing

Introduced Mar 8, 2026 · updated Apr 17, 2026

AgentStatusTook
@finance-analystfinished15.04s
@contract-reviewrunning42s…
@supportfinished3.1s
@data-engineerfailed1.8s

How it works

Nothing to instrument.

The platform runs your agents, so it records them — model calls, tool executions, summarizations, and timing, for every agent from the first day.

Tool calls keep everything.

Input, output, stdout and stderr — the same detail you would have had running the command yourself.

From message to run in one click.

Any message an agent sent links to the run that produced it.

See it on your own cluster.

Thirty minutes, your infrastructure, your stack. Or skip the call — it is one Helm release onto a cluster you already run.