It's not always code. I sometimes review things like translations that are often done in bulk (thousands of strings in a single batch). There's not much structure to it, it's not like reviewing some weird multi threaded super complicated algorithm, you just need to skim it quickly and make sure that the structure is not broken, and there are no screaming text blocks or unnecessary profanities.

Anyway, it did work properly, now it doesn't. The response shouldn't be "you're holding it wrong".