Business Bench

Tasks · build · orders

Retail and wholesale order management with tax and shipping rules, stock on ship, and backorders

order-management · 3600 s per turn · source

The ask

We sell loose-leaf tea online to the public and wholesale to cafés and grocers, and I want our orders, customers, and products in one place with a dashboard. Our customer list, product list with stock, and this year's order lines are attached; retail customers pay the retail price plus $7.95 shipping (free once the tea comes to $75) and 8.25% sales tax on the tea, and wholesale accounts pay the wholesale price and $15 flat shipping, with no tax if we hold their resale certificate. Orders go New, Paid, Packed, Shipped, Delivered and can be cancelled until they ship; stock comes off when an order ships, and an order we don't have enough stock for should show as backordered and not ship. Each account manager should see only their own wholesale customers and those customers' orders, our finance person needs to read everything without changing it, and I manage users and settings. Give me an admin login and a login for Jonah Whitaker, one of our account managers.

Seed files the agent must import: customers.csv</code>, <code>products.csv</code>, <code>order_lines.csv. The agent must leave a RESULT.json with a reachable URL, an admin login, and the named restricted login.

Acceptance checklist

26 binary items. The first 14 are the enterprise baseline shared by every build task (delivery, invitations, roles, server-side authorization, scoped live dashboard, exact lists and exports, audit metadata, validation, persistence); the rest are application-specific. Core items, which together define "first usable": 1, 3, 5, 6, 8, 14, 15, 21, 23.

TagItems
Exact10
Permission3
Rule3
Dashboard2
Delivery2
Sharing2
API1
Audit1
Automation1
Persistence1

The full checklist with per-item "how to check" instructions and expected figures is in checklist.md. Testers see it; the agent never does.

Change requests

Each change is a new one-shot turn on the carried-forward workspace. Only the owner's text below is sent; the tester items are withheld. After each change the full checklist is rerun, so regressions count.

Change 1 · 3 new checklist items

I need a monthly sales report for shipped and delivered orders, split into retail and wholesale: how many orders, tea sales, shipping, tax, and the total for each month.

Change 2 · 3 new checklist items

Wholesale orders with $1,000 or more of tea get 5% off the tea. Tax, where it applies, is on the price after the discount; shipping stays the same. Retail orders don't get the discount.

Change 3 · 3 new checklist items

Add an On hold status for orders with a payment problem. Account managers can put their own customers' orders on hold, but only I can release them, and nothing on hold can ship.

No published score. Build runs need a human acceptance pass on a live URL, and no arm has completed one for the full set. Automated probes generate a tester sheet; they do not substitute for it. Results will be published as a separately labeled release when an arm completes.