Comment by dzonga

I run a small data operation - mostly background jobs processing - with a small layer of CRUD stuff on top could be Django | Rails.

I have found A.I to be good when given guard-rails e.g I can write the initial models & functions by hand - then A.I (smarter autocomplete) completes the rest.

Also good - after the initial setup - if I prompt it I no longer have to spend time reading some library docs I won't likely use

Bad - it can create bad code or go off the rails (hence you've to be a skilled operator i.e skilled engineer before)

Bad - Vibecoding doesn't work when you're dealign with external data whose APIs are mostly undocumented etc (writing types | dataclasses is useful for the smarter autocomplete)