<?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/cdb3c53da06944b2a599e75943848a3e&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/cdb3c53da06944b2a599e75943848a3e-a3e320429f18b14d.gif</thumbnail_url><duration>178.88</duration><title>Hoops AI for Real-Time Player Insights</title><description>This Loom introduces Hoops AI, a performance insights app for NBA players that analyzes health data alongside competitive records. It walks through the coach console where players log in, view their intake and profile history with graphs, and review past game tracking. It then covers the live session, where coaches enter in-game indicators and metrics such as three-point percentage, along with notes like a player wincing during jumps, and select specific indicators for the AI model to analyze. The AI calls Claude for a quick summary, with more detailed insights available, and accuracy is supported by RAG using the player’s past history as the source of truth.</description></oembed>