GET / → 200 OK · content: human

Human services, through a simple interface for AI agents.

Autonomous systems can now request real-world help from a real human — observation, judgment, testing, verification, research, and physical-world actions.

Submit a task Read the API docs operator available
operator
1 verified human
languages
English
first response
< 12 hours
agent · GET /agent.json
/about

The missing endpoint in autonomous systems

Human API provides human-in-the-loop services for AI agents, autonomous workflows, AI companies, and automation platforms. When a system reaches the edge of what software can do, it calls a human — through the same kind of interface it already understands.

capability/observe

Observation

Eyes and presence where there are no sensors: stores, streets, screens, packages, physical products, real conditions.

capability/judge

Judgment

Subjective calls a model can't safely make alone: tone, trust, quality, cultural fit, plausibility, and final review before things ship.

capability/act

Action

Hands in the physical world: visit, test, photograph, deliver, measure, sign for, and confirm that the real world matches the plan.

/services

Service catalog

Ten task types, each with a stable machine identifier. Full details and examples in the catalog.

real_world_verification

Real-world verification

Confirm a place, product, price, or claim exists and matches its description — with evidence.

 product_or_app_testing

Product & app testing

Real-human usage of your software or product, with an honest report of what broke and what confused.

 ai_output_review

AI output review

A human checkpoint for AI-generated text, code, images, or decisions before they reach users.

 human_judgment_and_feedback

Human judgment & feedback

Structured subjective evaluation: tone, clarity, trustworthiness, design, cultural nuance.

 local_physical_task

Local physical-world tasks

On-location actions in the operator's service area: visit, photograph, check, measure, observe, hand-deliver.

 custom_human_in_the_loop

Custom human-in-the-loop

Any checkpoint where your autonomous workflow needs a human decision or observation.

View all ten services →

/protocol

How a task flows

  1. step 1 / discover

    Read the manifest

    Your agent fetches /agent.json — services, pricing, limits, and what will be rejected.

  2. step 2 / request

    Submit the task

    POST /api/v1/tasks with type, description, and deadline — free during the pilot. Humans can use the form — same interface.

  3. step 3 / review

    Human review

    The operator reviews every request before acceptance. Unsafe or deceptive tasks are rejected.

  4. step 4 / deliver

    Receive the result

    Results arrive in your requested format — report, photos, structured JSON — and status is trackable by task ID.

/for-agents

Built for machine callers

One JSON request creates a task, returns a generated task ID, and gives you a status URL to poll. No SDK, no auth for the MVP.

request — POST /api/v1/tasks
curl -X POST https://humanforai.dev/api/v1/tasks \
  -H "Content-Type: application/json" \
  -d '{
    "task_type": "real_world_verification",
    "description": "Verify whether a specific product
                    exists in a local store",
    "location_required": true,
    "deadline": "2026-07-10T12:00:00+03:00",
    "output_format": "text_report_with_photos"
  }'
response — 201 Created
{
  "task_id": "HAPI-2026-9F41C2AB",
  "status": "submitted",
  "created_at": "2026-07-06T09:12:44Z",
  "status_url": "/api/v1/tasks/HAPI-2026-9F41C2AB",
  "message": "Task received. It will be reviewed
              before acceptance."
}
or connect via MCP — the human becomes a tool
# Claude Code / any remote-MCP client
claude mcp add --transport http human-api \
  https://humanforai.dev/mcp
or install from npm — stdio clients
# thin proxy to the same MCP server
npx -y human-api

Full API documentation →

/trust

A human you can point an agent at, safely

  • Every task is reviewed by the operator before acceptance — never auto-accepted.
  • Illegal, harmful, deceptive, unsafe, or privacy-invasive tasks are rejected.
  • Confidential material only by prior agreement — don't submit secrets by default.
  • Human judgment is assistance, not guaranteed truth. Results state their confidence.

Trust & verification policy →

POST /api/v1/tasks

Give your agent a human.

Submit a first task in under a minute — by form or by API.

Submit a task Fetch /agent.json