{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/866aa8e790c84e018fc9b9302c032d2e\" 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/866aa8e790c84e018fc9b9302c032d2e-362ad6bd14f95a82.gif","duration":300.55,"title":"AI 110 Music Recommender Project Updates 🎵","description":"Hi, I am Jennifer, and this is my AI 110 final project extension of my Module 3 Music Recommender AI. I added more agents, enhanced regs, and used three documents to produce richer explanations, while also adding a confidence score and tracing the reasoning steps. With default settings, target energy was 0.7 and I initially preferred no acoustic music, showing the top five recommendations. Sunshine City was the top pick, and confidence was checked against a threshold of 0.5, with no RAG showing shorter explanations. I tried a formal explanation style with RAG but it started repeating generic definitions, and I was not able to fully resolve that."}