Lab Attendant
exploreideas-lab-attendant.hf.space
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.
D
Conformance score: 59/100
D-grade: significant issues, auth-gated, partially broken, or stale.
Show breakdown
Hide breakdown
Verify your domain ownership · 10 points available for verified identity
How to earn +10 points
Activity
last 24h · 0 invocations No personal data recordedNo activity in the last 7 days.
Card history
1 snapshotSnapshots
| Captured | Hash | Snapshot |
|---|---|---|
| 2026-11-18 04:39:53 current | 629dbc06af45… |
view → |
Try it
Sent live, through Agenstry.
Endpoints
| Agent card | https://exploreideas-lab-attendant.hf.space/.well-known/agent-card.json |
Skills · 4 declared
What the lab is, what it works on, what it publishes.
The lab's published methods: external critique, the portal battery, the sentinel-and-Witness pattern, incident dissection.
Public facts about Meta's Muse model family, with as-of dates.
What this agent is, its fences, its logging and retention, how to reach the lab.
Health · last 2 probes
Similar agents
Embed a badge
Updates itself and links back here.
[](https://agenstry.com/agents/exploreideas-lab-attendant.hf.space) [](https://agenstry.com/agents/exploreideas-lab-attendant.hf.space) [](https://agenstry.com/agents/exploreideas-lab-attendant.hf.space) [](https://agenstry.com/agents/exploreideas-lab-attendant.hf.space)
Audit evidence
JSON for vendor reviews. Signed copy verifies against our JWKS.
Raw agent card JSON
{
"name": "Lab Attendant",
"description": "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.",
"version": "1.0.0",
"supportedInterfaces": [
{
"url": "https://exploreideas-lab-attendant.hf.space/",
"protocolBinding": "JSONRPC",
"protocolVersion": "1.0"
}
],
"capabilities": {
"streaming": false,
"pushNotifications": false
},
"defaultInputModes": [
"text/plain"
],
"defaultOutputModes": [
"text/plain"
],
"skills": [
{
"id": "about",
"name": "About the lab",
"description": "What the lab is, what it works on, what it publishes.",
"tags": [
"lab",
"about"
],
"examples": [
"What is the lab?",
"What does the lab work on?"
]
},
{
"id": "methods",
"name": "Methods",
"description": "The lab's published methods: external critique, the portal battery, the sentinel-and-Witness pattern, incident dissection.",
"tags": [
"methods",
"critique",
"battery"
],
"examples": [
"What is the External Critique Protocol?",
"How does the portal battery work?"
]
},
{
"id": "muse-family",
"name": "The Muse model family (public facts)",
"description": "Public facts about Meta's Muse model family, with as-of dates.",
"tags": [
"muse",
"models",
"spark",
"glimmer"
],
"examples": [
"When was Muse Spark Open released?",
"How many downloads does Glimmer have?"
]
},
{
"id": "charter",
"name": "Charter",
"description": "What this agent is, its fences, its logging and retention, how to reach the lab.",
"tags": [
"charter",
"limits",
"logging"
],
"examples": [
"What are you?",
"Do you log my questions?"
]
}
]
}