<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/b485e5d04b4246a4847a765f8f39883d&quot; frameborder=&quot;0&quot; width=&quot;1110&quot; height=&quot;832&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>832</height><width>1110</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>832</thumbnail_height><thumbnail_width>1110</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b485e5d04b4246a4847a765f8f39883d-54573bf01e610756.gif</thumbnail_url><duration>300.114</duration><title>MixtapeID: The AI-Powered Music Recognition Tool for DJs</title><description>Hey everyone, it&apos;s Elius here, and I want to share my weekend project called Misty by D, which I built using Claude and Cursor without writing any code. This tool solves the problem of having to take out my phone to Shazam songs during DJ sets; instead, I can record the entire set and it processes the music to identify all the songs for me. It works by fingerprinting chunks of the audio using three different APIs to optimize accuracy and cost. The entire project took about seven hours to complete, and I’ve even created documentation for it in Cursor. If you&apos;re interested in trying it out or have any feedback, I&apos;d love to hear from you!</description></oembed>