A2A

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.

Provider

exploreideas-lab-attendant.hf.space

Skills

SkillDescription
aboutWhat the lab is, what it works on, what it publishes.
methodsThe lab's published methods: external critique, the portal battery, the sentinel-and-Witness pattern, incident dissection.
muse-familyPublic facts about Meta's Muse model family, with as-of dates.
charterWhat this agent is, its fences, its logging and retention, how to reach the lab.

Connect

https://exploreideas-lab-attendant.hf.space/.well-known/agent-card.json

Machine-readable

Full agent card as submitted: /agents/lab-attendant.json. Original source: https://exploreideas-lab-attendant.hf.space/.well-known/agent-card.json.