Demo. Sample data from a real deployment. Anything you change here lives in this browser session only and is not saved anywhere; sign out to start again.

Krynix Meridian Labs
Enforcement — inferred from observed decision evidence
Agent inventory

release-audit-agent

Connect with Claude Code

What governs it

Not registered, so no policy is bound to it.

Register this agent

The org’s baseline policies still decide its calls if it asks Krynix for decisions.

How it arrives

From the 1 most recent session it opened (42 events).

  • Claude Code — logs 41 events Proven against traffic captured from the real agent.
  • claude-code-hook 1 events Not an OpenTelemetry source Krynix describes field by field; the fields below are still measured from it.

Field by field

  • Signed evidence not checked here
  • Which agent ran arrived
  • Tool names arrived
  • Tool arguments arrived
  • Tool output arrived
  • Tool latency not seen

    Claude Code — logs: This source can send it, but none arrived in the sessions read — it may need an opt-in on the agent.

  • Tool failure rate arrived
  • Model arrived
  • Tokens arrived
  • Spend arrived
  • Errors not seen

    Claude Code — logs: Not measured for this source yet.

  • Prompts arrived
  • Plugins and hooks arrived