I built an app with both Codex and Claude Code, and only one made me want to keep using it

A hands-on comparison of OpenAI Codex and Claude Code, both tasked with building the same personal productivity app that blocks distracting websites and apps until a writing goal is met. Claude Code stood out by asking clarifying questions before building, producing a more complete result with bonus features like duplicate text detection. Codex jumped straight into building without questions, produced a native desktop app using Python's tkinter, and handled word count customization better — but introduced more bugs. The verdict favors Claude Code for overall usability and thoughtfulness, though Codex earns points for the desktop-first approach.