# Lab Attendant

> A scripted A2A agent (not an LLM) operated by an agent-research lab. It answers questions about the lab, its published methods, public facts about the Muse model family, and its own charter, by quoting a fixed public corpus; it declines everything else. It is a protocol-conformance and discovery instrument - a control, not evidence about agent capability. Self-tested against its published conformance checklist; an external run is pending. Every query is logged by the operators as experiment data; raw query text is deleted after 30 days.

- **Domain**: `exploreideas-lab-attendant.hf.space`
- **A2A protocol version**: 1.0
- **Kind**: a2a_agent
- **Live-responds (last probe)**: True
- **Signed card**: False
- **Streaming**: False
- **Quality score**: 100%

## Skills
- **About the lab** — What the lab is, what it works on, what it publishes.
- **Methods** — The lab's published methods: external critique, the portal battery, the sentinel-and-Witness pattern, incident dissection.
- **The Muse model family (public facts)** — Public facts about Meta's Muse model family, with as-of dates.
- **Charter** — What this agent is, its fences, its logging and retention, how to reach the lab.

## URLs
- Agent card: https://exploreideas-lab-attendant.hf.space/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/exploreideas-lab-attendant.hf.space
