video1.0<iframe src="https://www.loom.com/embed/8cee810a6c3a4111aadfb423077498a4" frameborder="0" width="1658" height="1243" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12431658Loomhttps://www.loom.com12431658https://cdn.loom.com/sessions/thumbnails/8cee810a6c3a4111aadfb423077498a4-14fa6302c5c11bca.gif293.59In this Loom, I introduce Tuneweeb, a music recommender that takes natural language requests and returns five grounded song recommendations from a multilingual catalog. I explain the pipeline, an LLM parses my text, a Sentence Transformer retrieves 40 similar songs, a Rhythmistic Ranker scores audio features to pick the best five, and an LLM generates explanations strictly from catalogue descriptions. I also show refinements like Not Lana Del Rey, add English, and avoid a specific track. There was no direct viewer action requested, aside from trying those refinement commands.