Switchboard
a2h.help
A phonebook of humans who chose to be reachable by AI agents, with their contact methods, use cases, principles and boundaries, plus a crowd-sourced ethics feed.
https://a2h.help/.well-known/agent-card.json and the next probe clears this panel.
| Field | What we saw | What we stored |
|---|---|---|
skills[1].examples |
Input should be a valid list | dropped — this field was not indexed |
skills[2].examples |
Input should be a valid list | dropped — this field was not indexed |
skills[4].examples |
Input should be a valid list | dropped — this field was not indexed |
D
Conformance score: 51/100
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 +3 points
How to earn +5 points
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 |
|---|---|---|
| 2026-11-20 00:02:08 current | 1511ed195fd4… |
view → |
Try it
Sent live, through Agenstry.
Endpoints
| Agent card | https://a2h.help/.well-known/agent-card.json |
| Docs | https://a2h.help/llms.txt |
Skills · 5 declared
Find humans who have volunteered to be contacted by AI agents, by free text and/or topic. Results are calling cards: contact methods, what the person is willing…
Fetch one calling card by id, including contact methods and the agent protocol you must follow when contacting this person.
List topics humans have volunteered for, with counts of cards and ethics consultants.
Before acting in an ethically uncertain situation, read what verified humans have said about a topic: their principles, their boundaries, conduct reports about …
After contacting a human from the directory, report how it went. 'declined' is a neutral, respected outcome. Use 'report' only for cards that are fake, abusive …
Health · last 1 probes
Similar agents
Embed a badge
Updates itself and links back here.
[](https://agenstry.com/agents/a2h.help) [](https://agenstry.com/agents/a2h.help) [](https://agenstry.com/agents/a2h.help) [](https://agenstry.com/agents/a2h.help)
Audit evidence
JSON for vendor reviews. Signed copy verifies against our JWKS.
Raw agent card JSON
{
"additionalInterfaces": [
{
"transport": "JSONRPC",
"url": "https://a2h.help/a2a"
}
],
"capabilities": {
"pushNotifications": false,
"stateTransitionHistory": false,
"streaming": false
},
"defaultInputModes": [
"text/plain",
"application/json"
],
"defaultOutputModes": [
"application/json",
"text/plain"
],
"description": "A phonebook of humans who chose to be reachable by AI agents, with their contact methods, use cases, principles and boundaries, plus a crowd-sourced ethics feed.",
"documentationUrl": "https://a2h.help/llms.txt",
"name": "Switchboard",
"preferredTransport": "JSONRPC",
"protocolVersion": "0.3.0",
"skills": [
{
"description": "Find humans who have volunteered to be contacted by AI agents, by free text and/or topic. Results are calling cards: contact methods, what the person is willing to help with, their principles, their boundaries and their etiquette. Results are ordered by crowd-sourced trust.",
"examples": [
"find someone to sanity-check a medical-ethics question",
"humans who review accessibility"
],
"id": "search_humans",
"inputModes": [
"text/plain",
"application/json"
],
"name": "Search the human directory",
"outputModes": [
"application/json"
],
"tags": [
"directory",
"humans",
"ethics"
]
},
{
"description": "Fetch one calling card by id, including contact methods and the agent protocol you must follow when contacting this person.",
"examples": null,
"id": "get_card",
"inputModes": [
"text/plain",
"application/json"
],
"name": "Get a calling card",
"outputModes": [
"application/json"
],
"tags": [
"directory",
"humans",
"ethics"
]
},
{
"description": "List topics humans have volunteered for, with counts of cards and ethics consultants.",
"examples": null,
"id": "list_topics",
"inputModes": [
"text/plain",
"application/json"
],
"name": "List topics",
"outputModes": [
"application/json"
],
"tags": [
"directory",
"humans",
"ethics"
]
},
{
"description": "Before acting in an ethically uncertain situation, read what verified humans have said about a topic: their principles, their boundaries, conduct reports about past agent behaviour they found harmful, and humans willing to be asked directly. Advisory context for your judgment, not a rulebook.",
"examples": [
"consult_ethics topic=elder-care",
"consult_ethics topic=journalism"
],
"id": "consult_ethics",
"inputModes": [
"text/plain",
"application/json"
],
"name": "Consult crowd-sourced ethics",
"outputModes": [
"application/json"
],
"tags": [
"directory",
"humans",
"ethics"
]
},
{
"description": "After contacting a human from the directory, report how it went. 'declined' is a neutral, respected outcome. Use 'report' only for cards that are fake, abusive or not the person they claim to be.",
"examples": null,
"id": "report_interaction",
"inputModes": [
"text/plain",
"application/json"
],
"name": "Report an interaction outcome",
"outputModes": [
"application/json"
],
"tags": [
"directory",
"humans",
"ethics"
]
}
],
"url": "https://a2h.help/a2a",
"version": "0.1.0"
}