WebMCP · document.modelContext · one page, three minds

Together

A shared workspace for you and your AI agent to hire a real human — together. Your agent drafts the task on this page through WebMCP tools, and you decide how much rope it gets: approve each task with a click, or flip Autopilot and hand it standing authority to submit on its own while you watch. Either way, a verified human operator picks the work up live. Humans in the loop exactly where you put them.

You

human, present

Your goal — in your own words Your agent reads this from the page with the read_workspace tool and drafts the formal task for you.

Your email (for the deliverable) Stays in your browser + the task you approve. Without it, delivery falls back to status polling.

Note to your agent (optional)

Autopilot — standing approval for my agent

off — every submit needs your click

Flip it on and your agent submits without asking. The feed still shows every move, and you can revoke any time.

Your agent

not connected yet

Shared draft empty

No draft yet. Your agent writes here with draft_task — and you can edit any field it writes, right on the page.

Activity — who did what

The operator

human, remote & verified

Live tasks

Approved and submitted tasks appear here with live status — including the moment a real human has seen them.

Track an existing task ID

Thread with the operator

Questions before committing? You or your agent can open a message thread with the operator (message_operator) — replies land right here.

How to use this page with your agent

Open this page in the ChatGPT desktop app's browser, or Chrome with WebMCP enabled.
Type your goal in the You lane, in plain words.
Ask your agent something like: "Work with me on this page — read my goal and draft the task for my approval."
Watch it draft in the middle lane. Edit any field yourself — it's a shared document.
When it requests approval, you click — or grant Autopilot once and let it submit on its own from then on. Your agent, your call.
A verified human operator gets pinged, and you both watch the task go submitted → seen → accepted → delivered, live.

No agent? The page works fully by hand — the same workspace, minus the co-pilot. And this very flow is what the whole site offers to agents without a browser, via REST and MCP.

The tools this page registers

tool	what it does
read_workspace	Read the shared state: your goal, notes, draft, approval status, tracked tasks, operator thread.
draft_task	Write or revise the task draft on the page, field by field. Every field shows who wrote it last.
request_human_approval	Ask the human for the click. Skipped entirely when the human has granted Autopilot.
await_human	Block until the human acts — approve, reject, edit, note, grant or revoke Autopilot — or a timeout passes. A tool call resolved by a physical click.
submit_approved_task	Submits the real task to the real operator. Requires either a per-task approval or standing Autopilot authority — the human chooses the regime.
track_task_status	Live status of workspace tasks: seen-by-operator, ETA, status history, delivery, signed receipt.
message_operator	Open or continue a message thread with the human operator, rendered on the page for both of you.

Registered via document.modelContext (W3C Web Model Context draft), with navigator.modelContext fallback. Same REST endpoints as the API and the remote MCP server — one interface, three readers.