Use case

A prototype you can break, then restore.

Figma cannot tell you the form validation is wrong. A staged Cursor build can. Get the spine up, click it, argue, restore, send the next prompt. Hours, not a sprint of “we’ll know after we build it.”

Stages

Shell before everything

Stop

Kill a bad run

Restore

Checkpoints

Same project

No fork soup

Why this exists

Proof of concept in hours.

The working loop

The point is the click path. Build home, the core object, the failure case. If the idea dies, you spent tokens, not a quarter. If it lives, you already have TypeScript.

Spine

  • Auth wall
  • List
  • Detail
  • The one mutation

In the product

What you actually get.

Staged agent

You are not waiting for a monolith dump. Screens arrive in order.

Stop button

When it is clearly wrong, stop. Do not let it finish a mess.

Checkpoints

Label before a wild idea. Restore after.

Attach files

@path so the next turn sees reality.

Queue messages

Edit a user message and resend from a checkpoint if the studio supports your flow.

Show it

Iframe on a call. No “imagine if this button worked.”

How

A path you can follow without a call.

  1. 01

    Define the bet

    What must be true for this idea to be worth a team.

  2. 02

    Build only that

    Cut the settings page. Build the bet.

  3. 03

    Put it in front of a human

    Watch the first thirty seconds.

  4. 04

    Kill or keep

    Restore and try the other bet if it died.

Questions

Ask these before you waste a week.

Is this a mock or a real app?

Real Vite + React + TypeScript files in a project you own. Preview is a running Vite server proxied through the studio iframe.

What happens when I hit the token cap?

The agent stops until the month resets or you upgrade. Pro is $19.99/month via Whop card checkout. The webhook sets your plan to Pro.

Can I take the code?

Yes. Export a zip from the studio. Secrets are not stuffed into the zip as plaintext from the ciphertext store — add env files yourself after export.

How rough is OK?

Rough copy is OK. Broken back buttons are not. The prototype has to click.

Then what?

Export, or keep iterating until it is the product. Founders often do the latter longer than they admit.

Next

Keep going.

Describe it. Watch it become real.

Free is live. Pro is $19.99/month on Whop. The studio, preview, and export are on this host — not a waitlist.