{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/8f898e43abdd4910a03368aa92be7d1f\" frameborder=\"0\" width=\"1660\" height=\"1245\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1245,"width":1660,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1245,"thumbnail_width":1660,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/8f898e43abdd4910a03368aa92be7d1f-0b6d5ff57ef04e67.gif","duration":300.313,"title":"Part 1 - Problem Space, Moodboarding via Paper x Claude","description":"I walked through how I used paper and Claude Code to redesign slow day AI loading states for the AI parsing stage. First, I screenshot the problem space states into a frame called problem space, then sent the notes and screenshots to Claude Code to analyze issues. Second, I moodboarded two directions, minimal to maximalist, plus a more Dynamic Island style, with rules to not copy inspirations one to one. Then I asked Claude to compile directions, and I went back into paper to test the early screen drafts. I did not request any viewer action."}