Merging countries into one feed is how a correct feed goes wrong for two-thirds of it

Conditional attribute rules -- apparel, shipping, tax -- and the currency check are all country-scoped; running one feed across several target countries applies the wrong rule set to most of the rows.

This is one of the things Product Feed & Merchant Center Compliance already handles. Get your products into Google Shopping and keep them from being rejected.

Buy for $1292 of 3 clean-room builds passed · full refund if it fails on your machine

Is this you?

A single feed covering several target countries has to pick one targetCountry and one currency to validate against, which means every conditional rule that's actually country-specific -- required apparel attributes, whether shipping or tax attributes are needed, which currency is correct -- gets checked against the wrong country's requirements for every row that isn't the one the feed happened to be configured for.

Why this one is easy to get wrong

A single feed file feels like the natural unit of "the product catalogue," and adding a second country reads like a data problem (more rows, different prices) rather than an architectural one -- nothing about the CatalogItem shape signals that FeedContext's country and currency fields are meant to be one-per-run, not one-for-the-whole-catalogue.

What you get instead

FeedContext carries targetCountry and currency as per-feed facts, and every conditional rule -- apparel attributes, shipping/tax requirements, the currency check itself -- reads from that one context rather than inferring a country per item. Running a second country is a second FeedContext through the identical pipeline, which is what makes three countries a config change rather than a fork of the codebase.

Source: ARCHITECTURE.md 'The catalogue seam' — checkable in the pack you receive

How you actually use this

You don’t install a library or wire up an SDK. Your own coding agent builds the code in your project, and you keep it — no runtime dependency on us.

Step 1
Download and unzip
You get a folder: the docs that tell an agent what to build, a starting skeleton, and the test suite that decides when it's done.
Step 2
Open it in Claude Code or Cursor
Point your coding agent at the folder. Nothing to install, no account with us, no API key.
Step 3
Paste one prompt
The pack contains the exact prompt. Paste it as your first message and leave it alone — it works through the build itself, choosing a cheaper or stronger model per task.
Step 4
Run ./verify.sh
One command. It prints a pass or fail for every check. Green means the build is done — the same script we ran to produce the receipt on this page.

Typical build: about 44 minutes of your agent working, mostly unattended. Then you integrate the working module into your app the way you would any code you’d written yourself.

Why you can believe this

2 of 3 runs passed

We ran this pack from an empty folder 3 times and published exactly what happened — every check, the model, the token cost, the wall time. Not a testimonial, and not our opinion: the same verify.sh you run yourself. Read the full receipt →

Buy for $129 14-day refund if verify.sh fails →