{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/8448b2bfca1d499ba06327aa2becb7b1\" frameborder=\"0\" width=\"1658\" height=\"1243\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1243,"width":1658,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1243,"thumbnail_width":1658,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/8448b2bfca1d499ba06327aa2becb7b1-f91f5e3c1d6c9bb4.gif","duration":323.82,"title":"CS Masters Program Recommender Project Walkthrough","description":"In this Loom, I take you through my final project, a CS Masters recommender built by adapting a music recommender show project. I show a few applicant profiles, like a budget-focused domestic person, and how the system returns the top five recommended programs with scores and a RAG-based snippet matched to their keywords. I explain the data inputs, including programs.csv with hard numbers like tuition, application fee, and GRE requirements, plus locally stored scraped content that tailors over time. I also cover the guardrail fallback when no keywords match, so we always return something. No specific action was requested from viewers."}