How do you know when an AI generated feature is actually ready?
by•
I have started noticing a pattern with AI coding tools: the first version of a feature looks finished long before it actually is.
Month I asked an AI assistant to add CSV export to a small internal tool. The happy path worked perfectly the UI looked clean. The generated tests passed.
Then someone uploaded a CSV with a column and a few unusual characters. The export technically completed,. The resulting file was unusable.
What changed for me was stopping at "the feature works". Asking, "What inputs would make this fail?"
How do you decide which edge cases are worth testing, before calling an AI generated feature production ?
12 views
Replies
This is a good reminder that AI can speed up coding but you still need to test the actual result manually
Mine was an all() over a generator in a validator script. It silently stops at the first failure, so I thought 125 files passed when only one line ever ran. Looked exhaustive, was not. Since then my rule for AI generated checks specifically is to feed it something I already know will fail, twice in a row, before trusting a clean pass on anything real.