{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/d5392168bb61436aa1fe0314bf97d7c0\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/d5392168bb61436aa1fe0314bf97d7c0-b7c5f2d1734b94c3.gif","duration":336.075,"title":"SuperSickMusicFinder9000 Full App Demo 🎵","description":"Hi, I’m presenting my Applied AI final project, SuperSickMusicFinder9000, which upgrades my original music recommender into a full AI system. I built it from core files in the repo, and it runs end to end to recommend songs based on inputs like mood, genre, and activity, with a confidence percentage. I demoed happy workout Pop, sad studying hip hop, and energetic partying EDM, showing the matches and how confidence changes. I also included a guardrail for missing or weak inputs and reliability testing that the system passes. No action is specifically requested from viewers."}