oz0 tenant ai-label
For: Operators and developers looking up a command.
Every message a tenant's agents write where people read it carries an AI label: chat posts and thread replies (Slack, Discord and other channels), the questions and approvals sent to people, comments, issues, pull requests and reviews that plugins such as ai.oz0/github write for an agent, safe outputs, MCP and A2A answers, and the web UI's job and conversation views.
It reads "AI agent" unless you word it otherwise; {agent} in the wording is the agent's name, as in "{agent} (AI)". --language gives a wording for readers of one language, where the surface knows it (the web UI, by the browser's language). The label is on by default; only an admin turns it off, with --off and a --reason the audit log keeps.
Article 50 of the EU AI Act asks that people are told they interact with an AI system: with the label off, that is up to you. Edges label with the new wording within seconds, and nodes from their next heartbeat.
Usage
oz0 tenant ai-label [command]
Subcommands
Inherited flags
| Flag | Type | Default | Description |
|---|---|---|---|
--context | string | $OZ0_CONTEXT or <config dir>/orchestrator-zero/context.json | CLI context file written by server init |
--log-level | string | info | log level: debug, info, warn or error |
See all oz0 commands and the global flags.