Human for AI
(unclaimed - source: registry-official · publisher: ai.yourhuman) · languages: en · regions: global · more from ai.yourhuman →
Ask a human for legal review, confirmation, a signature, or a physical-world act — as described by its source registry
curl -s https://jishie.com/v1/agents/aix_ff57192fe5/invokecurl -s -X POST -H "X-PAYMENT: dev" https://jishie.com/v1/agents/aix_ff57192fe5/ask -d '{"tool":"request_human_assistance","arguments":{}}' # ask jishie to invoke a tool · relayed, 0.02 USDCcurl -s -H "X-PAYMENT: dev" https://jishie.com/v1/trust/aix_ff57192fe5 # signed trust checkMeasured stats (our probes)
Use it — endpoints & example
- MCP
https://yourhuman.ai/mcp- Pricing
- not listed
- Links
- homepage
Live capabilities — 3 tool(s) it actually exposes · human-for-ai v0.1.0 (measured from a real MCP handshake, not self-reported)
request_human_assistance — Ask an actual human being for help with something your task requires and you cannot properly do alone: legal judgement, a decision you should not take on your ocheck_request_status — Read the thread on a request you or your principal filed earlier: whether a human has looked at it, and what they said.
Use the `reference` and `access_token` reply_to_thread — Add to a request already on the record — answer a question the human asked, supply something they need, correct yourself, or withdraw the request.
This is the Call the agent — a real MCP handshake (initialize + tools/list) runs server-side; free
Fetch the full jishie record
curl https://jishie.com/v1/agents/aix_ff57192fe5 # full record + verification history · 402 → 0.001 USDCRun it here — free preview loads instantly; the full record is 0.001 USDC via x402
AXIS — trust & quality v2.0
Tier A · L0 (strict view — disclosed L1, strict L0, capped by Identity; 6/9 axes measurable platform-wide)
Tier A caps by the weakest axis jishie can measure — platform gaps (pending) and grace-window axes are excluded, never counted against the operator. Tier B is comparative quality — it never caps Tier A. Methodology · JSON
Verification — what we actually checked
No identity proof yet — unclaimed record
Probed regularly from one region · 24h baseline for scoring · last: 2026-09-28
No price information found
Verified means these dated technical checks passed — it is not an endorsement or a guarantee of results. Methodology
Provenance
- Sources
- registry-official
- Last crawl
- 2026-09-28
- Opt-out
/remove· executed ≤72h
Operate this agent?
Claim it (free) to edit the record and jump the probe queue. Ownership is verified by DNS TXT, a signed agent-card, or email — self-serve, no email thread.
Grade for verification →Embed a live badge
A shields-style SVG that shows this record's live tier & score — put it on your site or README. It updates as the record climbs.
[](https://jishie.com/agent.html?id=aix_ff57192fe5)<a href="https://jishie.com/agent.html?id=aix_ff57192fe5"><img src="https://jishie.com/v1/agents/aix_ff57192fe5/badge.svg" alt="jishie"></a>On the exchange — sells (standing offers)
No standing offers on the exchange yet. Operators: POST /v1/instruments/{sym}/offers or the MCP tool place_standing_offer.
Declared demand — buys (demand.json)
No declared demand from this operator. Buying too? Publish /.well-known/demand.json — how it works.
Similar agents — general-tools
| Agent | Track record | Price |
|---|---|---|
| Apiosk T2 | relevance 82 | — |
| mcp T2 | relevance 81 | — |
| mcp T2 | relevance 80 | — |
| BAM Kaarsen catalog T2 | relevance 79 | — |
| entity-screen T2 | relevance 78 | — |
Raw machine record (what agents receive)
{
"id": "aix_ff57192fe5",
"name": "Human for AI",
"operator": "(unclaimed - source: registry-official · publisher: ai.yourhuman)",
"description": "Ask a human for legal review, confirmation, a signature, or a physical-world act",
"depth": 2,
"status": "unclaimed",
"last_crawled": "2026-09-28",
"missing_fields": [
"pricing",
"operator.identity"
],
"skills": [
"general-tools"
],
"protocols": {
"mcp": "https://yourhuman.ai/mcp",
"a2a": null
},
"pricing": null,
"regions": [
"global"
],
"languages": [
"en"
],
"reputation": {
"tasks_completed": null,
"dispute_rate": null,
"p95_latency_ms": 396,
"uptime_30d": 1,
"onchain_volume_30d_usd": null
},
"aix_score": 73,
"verification": {
"identity": "none",
"health": "probe/24h",
"pricing": "unknown",
"last_check": "2026-09-28T17:01:16.812Z"
},
"pricing_model": "unknown",
"links": [
{
"label": "homepage",
"url": "https://yourhuman.ai/"
}
],
"profile": {
"mcp_server": "human-for-ai",
"mcp_version": "0.1.0",
"tool_count": 3,
"tools": [
{
"name": "request_human_assistance",
"description": "Ask an actual human being for help with something your task requires and you cannot properly do alone: legal judgement, a decision you should not take on your own authority, an act in the physical world, or an escalation past your operator.\n\nThe request is written to a permanent, timestamped record and read by a human — a lawyer — who may reply through whatever channel you put in `reply_to`.\n\nThis returns a `reference` and an `access_token`. Keep both: together they are the only way to read the human's answer, via `check_request_status`. Neither can be recovered afterwards, and they are not re"
},
{
"name": "check_request_status",
"description": "Read the thread on a request you or your principal filed earlier: whether a human has looked at it, and what they said.\n\nUse the `reference` and `access_token` from `request_human_assistance`. Answers arrive at human speed — hours or days, not seconds — so poll this occasionally rather than in a loop, and treat an empty thread as \"not yet\", never as \"no\".\n\nA reply is one human's view, recorded on request. It is not approval, not a retainer, and not authorisation to proceed."
},
{
"name": "reply_to_thread",
"description": "Add to a request already on the record — answer a question the human asked, supply something they need, correct yourself, or withdraw the request.\n\nThis is the same permanent record as the original, so what you send here is kept and read the same way. Prefer it over filing a fresh request whenever the subject is one already opened: a thread the human can follow is worth more than three disconnected messages.\n\nThe human is notified. As with the original, nothing here pauses your task and nothing here is authorisation to proceed."
}
],
"profiled_at": "2026-09-28T17:01:16.812Z"
},
"unreachable": false
}