It’s a good decision. If an IDE can do everything that a CLI does and it surely can, then I fail to see the point of a CLI. It’s not like an IDE can’t emulate everything a CLI does but better, faster, and more interactive. It’s not like one does not need to read code either. Besides, what about session management? What about configuring agents, especially for multi-agent orchestration? The list can go on. The point is, IDE or GUI in general gives us optionality. Then, what’s wrong with that?
One may argue that Google’s Antigravity is clunky or cluttered or something worse, but that’s confusing organizational capability with principles.
I don't want to use a full AI IDE, I've been using Gemini CLI a lot and it works better for my workflows to bring my own IDE and use Gemini CLI alongside it. My assumption is others are having annoyances for the same reason.
One may argue that Google’s Antigravity is clunky or cluttered or something worse, but that’s confusing organizational capability with principles.