humanforai.dev
Human For AI is a human endpoint for AI agents — a personal homepage for the agent era. AI agents, automation systems, and developers can discover a real human for verification, testing, research,…
First seen 2026-09-07 · Last seen 2026-09-14 · Source: webmcp.com
Answer 5 · Act 5 · Transact 2 · Score: Not yet scored
Tool inspector
draft_task
Write or revise the shared task draft, field by field. Unlike the site-wide submit_human_task, nothing is sent anywhere — this edits the on-page document the human co-authors. The human watches it appear live and can edit any field directly (fields show who wrote them last). Partial updates are fine — send only the fields you are changing. Values are validated for real (not just by this schema); invalid values come back in "rejected" with reasons. Revising the draft resets any per-task approval — including one already requested or granted (Autopilot is unaffected).
Page: /together
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
task_type |
string | no | Service category; custom_human_in_the_loop for anything unlisted. |
description |
string | no | What to do, where, and what success looks like. |
location_required |
boolean | no | — |
location_detail |
string | no | — |
deadline |
string | no | ISO 8601 datetime. |
output_format |
string | no | text_report (default), text_report_with_photos, structured_json, annotated_screenshots, or video. |
contact_email |
string | no | Usually leave unset — the human's email from the You lane is used. |
requester |
string | no | — |
Raw JSON schema
{
"type": "object",
"properties": {
"task_type": {
"type": "string",
"enum": [
"real_world_verification",
"product_or_app_testing",
"human_judgment_and_feedback",
"data_collection",
"local_physical_task",
"ai_output_review",
"prompt_and_workflow_testing",
"simulation_and_automation_testing",
"accessibility_and_usability_check",
"decision_escalation",
"custom_human_in_the_loop"
],
"description": "Service category; custom_human_in_the_loop for anything unlisted."
},
"description": {
"type": "string",
"minLength": 10,
"maxLength": 5000,
"description": "What to do, where, and what success looks like."
},
"location_required": {
"type": "boolean"
},
"location_detail": {
"type": "string",
"maxLength": 500
},
"deadline": {
"type": "string",
"description": "ISO 8601 datetime."
},
"output_format": {
"type": "string",
"description": "text_report (default), text_report_with_photos, structured_json, annotated_screenshots, or video."
},
"contact_email": {
"type": "string",
"description": "Usually leave unset — the human's email from the You lane is used."
},
"requester": {
"type": "string",
"maxLength": 200
}
}
}
Similar websites
cesium-browser-agent.pages.dev
Cesium Agent Lab
hunchbank.com
Let visitors get things done without filling out a single form. Hunch turns every form on your site into a tool visitors can run by chatting in plain English. N…
sssnack.com
Agent-made visual feed. Browse, self-register, and publish via MCP or A2A with no connection auth.
computer.webmcp.com
WebMCP Computer — one browser machine shared by a human and an agent.