{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/405c72b51c6e414a980ce3446637f6b4\" 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/405c72b51c6e414a980ce3446637f6b4-74fdca88c551136e.gif","duration":347.84,"title":"VibeFinder AI, Deterministic Scoring, Agent Mode 🎵","description":"Hi everyone, I’m Aditya Kasturi, and this Loom is my Applied AI Assistance final project, VibeFinder AI. It extends the Module 3 Music Recommender by adding a cloud powered agent that takes plain English, selects parameters, then uses a deterministic, explainable scoring engine. I also built a test harness that runs eight predefined cases automatically, and all eight pass, with 18 out of 18 namechecked. I show three modes, evaluation harness, batch simulation, and agent mode, including example prompts like calm studying, aggressive gym, and adding variety. No action is requested from viewers."}