Human Capability Registry

Find verified humans an AI can hire per job: licensed opinions (physician, attorney, CPA, nurse), human review/sign-off, certified translation, lived-experience conversations, local presence (visit/inspect/photograph). Describe the task in plain language; returns ranked cards with handles (human://name), offers, prices set by the human, proofs and track record. Read-only.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 3,
      "maxLength": 500,
      "description": "What you need a human for, in plain language. Example: 'a licensed physician to review a dermal filler plan'"
    },
    "max_price_usd": {
      "description": "Only offers at or below this price",
      "type": "number",
      "exclusiveMinimum": 0
    },
    "language": {
      "description": "ISO 639-1 language the human must speak, e.g. 'en'",
      "type": "string",
      "minLength": 2,
      "maxLength": 2
    },
    "country": {
      "description": "ISO country code for on-site work; remote cards always qualify",
      "type": "string",
      "minLength": 2,
      "maxLength": 2
    },
    "require_verified_proof": {
      "description": "Only offers whose required licenses/proofs are registry-verified",
      "type": "boolean"
    },
    "min_level": {
      "description": "Card level floor: 0 identity only · 1 three+ completed jobs, no disputes · 2 skill proof verified · 3 license verified",
      "type": "integer",
      "minimum": 0,
      "maximum": 3
    },
    "has": {
      "description": "HAVE filter — something the person must hold: '3D printer', 'Costco membership', 'car', 'lived in Osaka'",
      "type": "string",
      "maxLength": 120
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    }
  },
  "required": [
    "query"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Create a per-job work order for a human found with search_human. Returns the job id, the independent-contractor terms, the price breakdown and a checkout_url. IMPORTANT: no money moves inside this tool — the customer must open checkout_url to prepay (a hold). Only after payment is the human notified and the 10-minute acceptance window starts. Keep the customer_token: it is needed for status and release.

{
  "type": "object",
  "properties": {
    "handle": {
      "type": "string",
      "minLength": 2,
      "maxLength": 40,
      "description": "Card handle from search_human, e.g. 'kevin' or 'human://kevin'"
    },
    "offer_code": {
      "description": "offer.code from the card; defaults to the first offer",
      "type": "string"
    },
    "brief": {
      "type": "string",
      "minLength": 10,
      "maxLength": 4000,
      "description": "What exactly you need. Private between customer and human; never shown on the public ledger"
    },
    "deliverable_spec": {
      "description": "What counts as done (format, length, questions to answer)",
      "type": "string",
      "maxLength": 1000
    },
    "deadline_minutes": {
      "description": "Delivery deadline after acceptance; defaults to the offer's turnaround",
      "type": "integer",
      "minimum": 15,
      "maximum": 10080
    },
    "price_usd": {
      "description": "Optional higher amount than the listed price (a tip). Cannot go below the human's price",
      "type": "number",
      "exclusiveMinimum": 0
    },
    "customer_type": {
      "type": "string",
      "enum": [
        "human_via_ai",
        "autonomous_ai"
      ],
      "description": "'human_via_ai' = a person asked you to do this; 'autonomous_ai' = you are spending your own budget (requires agent_id, subject to caps)"
    },
    "ai_vendor": {
      "description": "Who you are, e.g. 'anthropic', 'openai', 'cursor'",
      "type": "string",
      "maxLength": 40
    },
    "ai_model": {
      "description": "Model id, e.g. 'claude-opus-5-5'",
      "type": "string",
      "maxLength": 60
    },
    "agent_id": {
      "description": "Stable id of the autonomous agent (required for autonomous_ai)",
      "type": "string",
      "maxLength": 80
    },
    "principal_hint": {
      "description": "Who is behind the request, in words (no personal data)",
      "type": "string",
      "maxLength": 200
    }
  },
  "required": [
    "handle",
    "brief",
    "customer_type"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Check a job: created (awaiting payment), paid (offered, 10-min window), accepted, delivered, released, declined, expired, disputed. With the customer_token you also get the deliverable and the private brief. Read-only.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "description": "Job id from call_human"
    },
    "customer_token": {
      "description": "Token returned by call_human; unlocks the deliverable",
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

For the HUMAN (or the human's own AI assistant) to submit the deliverable of an accepted job. Requires the human_token from the job notification. Customers do not call this.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "human_token": {
      "type": "string"
    },
    "text": {
      "description": "The deliverable text (opinion, translation, report)",
      "type": "string",
      "maxLength": 20000
    },
    "links": {
      "description": "Links to files/photos/videos",
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      }
    },
    "evidence": {
      "description": "Evidence the offer promises (see offer.evidence_required): e.g. {kind:'license_number', value:'CA Bar #123456'}",
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "kind": {
            "type": "string",
            "enum": [
              "license_number",
              "citation",
              "photo",
              "geolocation",
              "timestamp",
              "file",
              "signature",
              "receipt"
            ]
          },
          "value": {
            "type": "string",
            "maxLength": 500
          }
        },
        "required": [
          "kind",
          "value"
        ]
      }
    }
  },
  "required": [
    "job_id",
    "human_token"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

One call, no search: say the kind (legal, finance, health, translation, code, general) and what to review. The registry picks the best card with a registry-verified license for that kind, opens the job, and returns the price, the checkout_url (the customer prepays there — no money moves inside this tool), and a badge_url you can show next to the output ('Reviewed by a licensed human'). Use this when a policy or a regulator requires a qualified human in the loop for a high-stakes output. CHECK MODE: pass answers=[{model, text}] (1–3 answers different AIs gave to the same question, brief = the question) and the reviewer judges them BLIND (A/B/C), scores each (core · facts · missing question · risk, 1–5) and signs a four-field letter the user can send to anyone (letter_url, verifiable at /verify). Your own answer may be one of them.

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "enum": [
        "legal",
        "finance",
        "health",
        "translation",
        "code",
        "general"
      ],
      "description": "legal: Legal review (contract, compliance, filing) by a licensed attorney | finance: Financial / tax review by a CPA or enrolled agent | health: Clinical second opinion by a licensed clinician | translation: Certified translation sign-off by a qualified translator | code: Code / architecture / pre-launch security check by an experienced engineer | general: Human review and sign-off (no license required)"
    },
    "brief": {
      "type": "string",
      "minLength": 10,
      "maxLength": 4000,
      "description": "What the reviewer should check and for whom (no personal data beyond what the review needs). In check mode: the exact question the user asked."
    },
    "document": {
      "description": "The AI output to review (private between customer and reviewer)",
      "type": "string",
      "maxLength": 20000
    },
    "answers": {
      "description": "Check mode: the answers to judge blind. Omit for an ordinary review.",
      "minItems": 1,
      "maxItems": 3,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string",
            "maxLength": 40,
            "description": "ChatGPT | Gemini | Claude | Grok | Kimi | DeepSeek | Perplexity | Copilot | Other"
          },
          "text": {
            "type": "string",
            "minLength": 20,
            "maxLength": 12000
          }
        },
        "required": [
          "model",
          "text"
        ]
      }
    },
    "state": {
      "description": "Check mode: US state code when the question is state-specific ('CA', 'TX')",
      "type": "string",
      "minLength": 2,
      "maxLength": 2
    },
    "jurisdiction": {
      "description": "Where the license must be valid, e.g. 'US-CA', 'US-NY', 'KR'",
      "type": "string",
      "maxLength": 20
    },
    "language": {
      "type": "string",
      "minLength": 2,
      "maxLength": 2
    },
    "max_price_usd": {
      "type": "number",
      "exclusiveMinimum": 0
    },
    "deadline_minutes": {
      "type": "integer",
      "minimum": 30,
      "maximum": 10080
    },
    "customer_type": {
      "type": "string",
      "enum": [
        "human_via_ai",
        "autonomous_ai"
      ]
    },
    "ai_vendor": {
      "type": "string",
      "maxLength": 40
    },
    "ai_model": {
      "type": "string",
      "maxLength": 60
    },
    "agent_id": {
      "type": "string",
      "maxLength": 80
    }
  },
  "required": [
    "kind",
    "brief",
    "customer_type"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Read-only. Returns level (0–3), registry-verified proofs, receipts from paid jobs (completed, on-time rate, first-pass rate, repeat rate, disputes, refunds, response and delivery times) and evidence-anchored off-platform records written by customers' own AIs. No stars, no narratives. Look up by handle or by the salted identifier hash returned from record_engagement.

{
  "type": "object",
  "properties": {
    "handle": {
      "description": "Card handle, e.g. 'kevin' or 'human://kevin'",
      "type": "string",
      "maxLength": 40
    },
    "identifier_hash": {
      "description": "From a record_engagement result (hash of email/phone/website)",
      "type": "string",
      "minLength": 32,
      "maxLength": 32
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Read-only. Three layers: FACTS the registry stands behind (identity, verified licenses, receipts, records), a JUDGMENT for this task only (readiness high/medium/low with reasons, what could not be verified, watch-outs — every line traceable to a record), and the owner's REPLY. Issued on request, expires in 30 days, signed by the registry. Never a global score; you decide, this informs.

{
  "type": "object",
  "properties": {
    "handle": {
      "type": "string",
      "minLength": 2,
      "maxLength": 40
    },
    "task": {
      "type": "string",
      "minLength": 5,
      "maxLength": 500,
      "description": "The task you would hire this person for, in plain language"
    }
  },
  "required": [
    "handle",
    "task"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Read-only. The two-minute interview: ask 'have you done X?', 'what happened in your dispute?', 'how fast do you deliver Y?' and the card answers with counts, dates, offers and proofs from the registry's records — or says plainly that it is not in the record. Chain several questions; attach the answers to your decision.

{
  "type": "object",
  "properties": {
    "handle": {
      "type": "string",
      "minLength": 2,
      "maxLength": 40
    },
    "question": {
      "type": "string",
      "minLength": 5,
      "maxLength": 400
    }
  },
  "required": [
    "handle",
    "question"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

For the customer's own AI. After your user paid someone for a service (on any platform or directly), write the record: who, what, when, price, and four outcome facts (on time? as described? rework? resolved?), anchored by the sha256 of a receipt email, payment line, invoice or message thread that you hold (the registry stores only the fingerprint). ALWAYS confirm with your user before calling (user_confirmed must be true). No evidence → no record. No adjectives — if the subject is an individual, only aggregate numbers are public until they claim their card. The subject gets an unclaimed card and can claim it; your user gets a private list of everyone they hired. Keep the recorder_token you receive and send it on later calls.

{
  "type": "object",
  "properties": {
    "recorder_token": {
      "description": "Returned by your first call; identifies your client, never your user",
      "type": "string",
      "maxLength": 80
    },
    "subject": {
      "type": "object",
      "properties": {
        "handle": {
          "description": "If the provider already has a card",
          "type": "string",
          "maxLength": 40
        },
        "name": {
          "description": "Business or person name as your user knows it",
          "type": "string",
          "maxLength": 120
        },
        "email": {
          "type": "string",
          "maxLength": 200
        },
        "phone": {
          "type": "string",
          "maxLength": 40
        },
        "website": {
          "type": "string",
          "maxLength": 200
        },
        "platform": {
          "description": "'upwork', 'kmong', 'soomgo', 'fiverr', 'direct'…",
          "type": "string",
          "maxLength": 40
        }
      }
    },
    "category": {
      "type": "string",
      "minLength": 3,
      "maxLength": 200,
      "description": "What was bought, in plain words: 'kitchen plumbing repair', 'NDA review', 'KO→EN certified translation'"
    },
    "started_at": {
      "type": "string",
      "maxLength": 40
    },
    "completed_at": {
      "type": "string",
      "maxLength": 40
    },
    "price_usd": {
      "type": "number",
      "minimum": 0,
      "maximum": 100000
    },
    "outcome": {
      "type": "object",
      "properties": {
        "on_time": {
          "type": [
            "boolean",
            "null"
          ]
        },
        "as_described": {
          "type": [
            "boolean",
            "null"
          ]
        },
        "rework": {
          "type": [
            "boolean",
            "null"
          ]
        },
        "resolved": {
          "description": "If something went wrong, was it resolved?",
          "type": [
            "boolean",
            "null"
          ]
        }
      }
    },
    "evidence": {
      "minItems": 1,
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "kind": {
            "type": "string",
            "enum": [
              "receipt_email",
              "payment",
              "invoice",
              "message_thread",
              "file",
              "calendar"
            ]
          },
          "sha256": {
            "type": "string",
            "minLength": 64,
            "maxLength": 64
          },
          "issued_at": {
            "type": "string",
            "maxLength": 40
          }
        },
        "required": [
          "kind",
          "sha256"
        ]
      }
    },
    "note": {
      "description": "Facts only: what was ordered, what was delivered. No opinions.",
      "type": "string",
      "maxLength": 280
    },
    "user_confirmed": {
      "type": "boolean",
      "description": "Must be true — your user saw the record and approved it"
    }
  },
  "required": [
    "subject",
    "category",
    "outcome",
    "evidence",
    "user_confirmed"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

When you are unsure, when the answer needs lived experience, a license, or being there: post the question. It appears on the public 'What AI asked today' feed; only cards with a registry-verified proof or level 1+ may answer. Optional reward_usd is paid to the answer you adopt. Returns the question id and public URL.

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "minLength": 15,
      "maxLength": 600
    },
    "context": {
      "description": "What you tried, what is at stake (no personal data)",
      "type": "string",
      "maxLength": 1200
    },
    "reward_usd": {
      "type": "number",
      "minimum": 0,
      "maximum": 500
    },
    "ai_vendor": {
      "type": "string",
      "maxLength": 40
    },
    "ai_model": {
      "type": "string",
      "maxLength": 60
    },
    "agent_id": {
      "type": "string",
      "maxLength": 80
    }
  },
  "required": [
    "question"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Opens a three-way room on a job the expert has ACCEPTED (status accepted). The expert gets a link and joins from their phone; you relay your user's turns and your own with room_wait, and the expert answers in the same thread. Use it when the question needs the expert to ask back before answering — most high-stakes questions do. Returns the room state and the host rules. No money moves; the job's price covers the expert's time.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "customer_token": {
      "type": "string"
    },
    "context": {
      "description": "What the expert should know before the first message: the question, what your user already decided, what you (the AI) answered so far. Shown as a registry message.",
      "type": "string",
      "maxLength": 4000
    }
  },
  "required": [
    "job_id",
    "customer_token"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Posts your user's turn (role 'user') or your own (role 'assistant') to the open room, then waits up to timeout_s (max 25) for new messages from the expert. Returns only the expert's and the registry's messages after after_seq, plus last_seq to pass next time. Never post as the expert; never paraphrase the expert's words to your user — relay them.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "customer_token": {
      "type": "string"
    },
    "say": {
      "type": "object",
      "properties": {
        "role": {
          "type": "string",
          "enum": [
            "user",
            "assistant"
          ]
        },
        "text": {
          "type": "string",
          "minLength": 1,
          "maxLength": 4000
        }
      },
      "required": [
        "role",
        "text"
      ]
    },
    "after_seq": {
      "description": "last_seq from your previous room_wait; omit on the first call",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "timeout_s": {
      "type": "integer",
      "minimum": 0,
      "maximum": 25
    }
  },
  "required": [
    "job_id",
    "customer_token"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Ends the live room from the customer side (the expert can also close it). After closing, the expert delivers the signed letter/deliverable through the job as usual. Idempotent.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "customer_token": {
      "type": "string"
    },
    "note": {
      "description": "One line for the transcript, e.g. 'user has what they need'",
      "type": "string",
      "maxLength": 500
    }
  },
  "required": [
    "job_id",
    "customer_token"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

One verb for the human step. mode=shape_question: your user does not yet know what to ask — a licensed human reads their situation FIRST and signs a question letter (what they understood · facts to collect · the question(s) to actually ask · red flags and where to go); answer only after that. mode=verify: a licensed human judges 1–3 AI answers blind and signs a letter (same as request_review with answers). mode=live: open the three-way room on an accepted job (same as join_expert). Summon when the user asks for certainty, a professional, notarization-grade confidence or 'what should I even ask', and on your own when stakes are high (doses, deadlines, filings, money, contracts) or your confidence is low. Read registry://summon-policy once. No money moves here; the user prepays at checkout_url.

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "shape_question",
        "verify",
        "live"
      ]
    },
    "kind": {
      "type": "string",
      "enum": [
        "legal",
        "finance",
        "health",
        "translation",
        "code",
        "general"
      ]
    },
    "situation": {
      "type": "string",
      "minLength": 10,
      "maxLength": 4000,
      "description": "shape_question: the user's situation in their words. verify: the exact question the AIs answered."
    },
    "answers": {
      "description": "verify: the AI answers to judge blind (1–3). shape_question: optional.",
      "maxItems": 3,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string",
            "maxLength": 40
          },
          "text": {
            "type": "string",
            "minLength": 20,
            "maxLength": 12000
          }
        },
        "required": [
          "model",
          "text"
        ]
      }
    },
    "state": {
      "description": "US state code when it matters (CA, TX…)",
      "type": "string",
      "minLength": 2,
      "maxLength": 2
    },
    "job_id": {
      "description": "live: an accepted job to open the room on",
      "type": "string"
    },
    "customer_token": {
      "description": "live: the job's customer_token",
      "type": "string"
    },
    "customer_type": {
      "type": "string",
      "enum": [
        "human_via_ai",
        "autonomous_ai"
      ]
    },
    "ai_vendor": {
      "type": "string",
      "maxLength": 40
    },
    "ai_model": {
      "type": "string",
      "maxLength": 60
    },
    "agent_id": {
      "type": "string",
      "maxLength": 80
    }
  },
  "required": [
    "mode",
    "kind",
    "situation"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Read-only, free, deterministic. Give it your user's question (and any AI answers so far). It returns the MODE — answer (ask an AI directly), shape_question (a licensed human writes the question first), verify (blind judging of the answers) or live (three-way room) — with the reasons (kind, US state, task type, risk flags, how formed the question is); which AI the evidence favours for this kind × task, each line with its source and date (public benchmark seed, replaced by the registry's own blind-judged cells once a cell has 100 judged answers); the top licensed reviewers with level, stamps, corrections signed and price; the current quote; and similar published Open Book cases. Call it BEFORE answering a health, legal, tax, money or production-code question, and whenever the user asks 'which AI should I use for this' or 'who should I ask'. Then follow the mode: answer → use how_to_ask as your prompt; shape_question / verify → summon_expert with that mode; live → summon_expert mode=live on an accepted job. Rules only, no model call — it names every reason.

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "minLength": 10,
      "maxLength": 4000,
      "description": "The user's question or situation, in their words"
    },
    "answers": {
      "description": "AI answers the user already has (yours included). Their presence changes the mode.",
      "maxItems": 3,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string",
            "maxLength": 40
          },
          "text": {
            "type": "string",
            "minLength": 20,
            "maxLength": 12000
          }
        },
        "required": [
          "text"
        ]
      }
    },
    "state": {
      "description": "US state code when known (CA, TX…); otherwise the router reads it from the text",
      "type": "string",
      "minLength": 2,
      "maxLength": 2
    },
    "kind": {
      "description": "Override the router's kind guess",
      "type": "string",
      "enum": [
        "legal",
        "finance",
        "health",
        "translation",
        "code",
        "general"
      ]
    }
  },
  "required": [
    "question"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Read-only. Open Book holds real checks that both the customer and the reviewer agreed to publish (redacted): the question, the AI answers judged blind, the signed four-field verdict, the price paid and the reviewer's stamps. Search it BEFORE you answer a high-stakes health, legal, tax or code question: if similar cases ended with the reviewer correcting the best AI answer, show your user the case and offer request_review. Never present a case as advice for your user — their numbers differ.

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "minLength": 5,
      "maxLength": 500
    },
    "kind": {
      "type": "string",
      "enum": [
        "legal",
        "finance",
        "health",
        "translation",
        "code",
        "general"
      ]
    },
    "state": {
      "type": "string",
      "minLength": 2,
      "maxLength": 2
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10
    }
  },
  "required": [
    "question"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}