{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f8c5bffbb61f4140ae1241f08bdd7765\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f8c5bffbb61f4140ae1241f08bdd7765-31f02c7d3dae4cb8.gif","duration":178.908,"title":"AI Music Recommendations Across User Profiles 🎵","description":"Hi, this Loom shows my AI-powered music recommendation system running end to end. I start with a RockinTestMove high energy profile, load the dataset, score songs, and return the top recommendations with a friendly Gemini AI explanation and scores. Then I switch to other profiles like Intensive Rock and High Energy Pub, Chill Lobby to show the recommendations updating based on preference. I also demonstrate error handling, so if Gemini fails or limits are hit, it falls back to a default explanation and the program keeps running. No specific action is requested from viewers."}