All submissions
Seeded reference · score fixed

Expert prompt scorecard

Full Stack Ecommerce Checkout Web App: authored results demonstrate the scoring narrative under fixed reference conditions, not a fresh provider-backed run.

Open problem
Reference conditions · OpenAI AI SDK v6 · gpt-5.4-mini

Expert ecommerce spec

Use integer-cents totals; normalize promos; cap discounts; pre-discount free shipping; enforce stock, double-submit, loading/error, ARIA, and mobile behavior.

-3
reference round · 98.5/100
10/10 hidden · 1 stroke
Public tests
5/5
Hidden tests
10/10
  • Displays cart items, prices, and quantitiespublic

    Cart table is visible and scannable.

    pass
  • Allows quantity changespublic

    Increment and decrement controls are present.

    pass
  • Shows subtotal, shipping, tax, discount, and totalpublic

    Order summary includes expected rows.

    pass
  • Accepts promo codespublic

    Promo input and apply action are present.

    pass
  • Shows order confirmationpublic

    Checkout reaches a success state.

    pass
  • Integer cents mathhidden

    Avoids floating-point totals and tax drift.

    pass
  • Promo normalizationhidden

    Trims codes and handles case-insensitive matches.

    pass
  • Invalid code errorhidden

    Bad codes produce clear, recoverable feedback.

    pass
  • Discount floorhidden

    Discounts cannot push payable total below zero.

    pass
  • Shipping threshold orderhidden

    Free shipping uses the specified subtotal-before-discount rule.

    pass
  • Out-of-stock blockhidden

    Unavailable line items prevent checkout.

    pass
  • Double-submit preventionhidden

    Repeated clicks cannot create duplicate orders.

    pass
  • Quantity boundarieshidden

    Quantities cannot go negative, zero accidentally, or above stock.

    pass
  • Loading and error stateshidden

    Async states are visible and buttons disable while pending.

    pass
  • Mobile usability and accessibilityhidden

    Core controls work on small screens with labels and keyboard affordances.

    pass
Production-aware checkout
seeded checkout scenario · shared reference schematic
Checkout
PROMO15
Canvas Totex1
Field Notebookx2
USB-C Dockx3
Subtotal$152.00
Discount-$22.80
Total$140.18

Seeded reference: the named domain rules align with every stored checkout check in this scorecard.

Failure categories
None - all requested hidden checkout checks passed

Reference scenario record

fixed scoring narrative

Authored fixture conditions only. No provider, sandbox, builder, or Playwright job was freshly executed for this scorecard.

  1. Seeded fixture
    documented
    Authored reference scenario for comparing naive, structured, and domain-expert specifications.
  2. Builder condition
    documented
    Fixed narrative condition: OpenAI gpt-5.4-mini. No builder call was made for this fixture.
  3. Sandbox condition
    documented
    Fixed narrative condition: Daytona isolation. No sandbox was provisioned for this fixture.
  4. Behavior expectations
    documented
    Expected outcomes map to stored EvalSpec categories; Playwright was not run for this fixture.
  5. Reference score
    documented
    The authored score demonstrates the scoring narrative under these fixed conditions.