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

Watch live, terminate if needed

Runs stream while the agent works — and a misbehaving one stops at a button.

WhereTracing

Introduced Apr 1, 2026

run · @finance-analyst · running · 2m 14sTerminate run
message received0.0s
llm call · context ▸ 14 items2.4s
tool · postgres_query312ms
tool · create_chartrunning…

How it works

Watch tool calls land.

Runs stream while the agent works — you see it in real time, not in a post-mortem.

The kill switch is on the same screen.

A misbehaving run stops at a button, not at the end of a support ticket.

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.