All the time. In fact, a change that touches > 2 files has to be justified by 5 why's and presented to me before execution. That, and many other safeguards in global instruction files.
Has anyone ever actually challenged a decision made by Claude Code or Codex while coding?
Like, the AI suggests a way to do something and you just go:
“No, I think there’s a better way.”
Curious how often people actually push back on their AI coding tools.
