History
- Apr 17, 2026Every message an agent sends now links to the run that produced it.
How ready are your agents for a bad day? Get your scoreHow ready are your AI agents for a bad day? Get your security readiness score in 2 minutes.
Get my score →Every run records itself — no SDK, no collector, nothing to instrument.
Introduced Mar 8, 2026 · updated Apr 17, 2026
The platform runs your agents, so it records them — model calls, tool executions, summarizations, and timing, for every agent from the first day.
Input, output, stdout and stderr — the same detail you would have had running the command yourself.
Any message an agent sent links to the run that produced it.
Thirty minutes, your infrastructure, your stack. Or skip the call — it is one Helm release onto a cluster you already run.