Shopify

Two reviewers with isolated context that check new code against Shopify's documented architecture, including its UI guidelines, and review it again after fixes until both approve.

Lists each visual difference between implementation and reference, with a severity and where it appears on screen.

Vertical-specific judges, such as electronics or musical instruments, that evaluate each proposed change.

Recognizes when different category and attribute combinations describe the same set of products.

Works out how the reference feature behaves, rebuilds it, runs the checks and answers reviewer feedback.

Captures the new screen and the reference screen in the same state, then hands both to the Gemini reviewer for a design check.

Studies product titles, descriptions and merchant categories to find where the taxonomy differs from how merchants describe products.

Checks the taxonomy itself for hierarchy gaps, naming inconsistencies and better ways to group related concepts.

Reads the reference code and writes test cases for every checkpoint.