<?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/1cb3ff4c0b8b4d1c863566ae8df67fb4&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/1cb3ff4c0b8b4d1c863566ae8df67fb4-e01bfa97816505ea.gif</thumbnail_url><duration>583.467</duration><title>AI NLF Draft Simulator Architecture Walkthrough 🚀</title><description>Hi guys, I am Anu, and in this Loom I walk you through my NLF MOOC job simulator draft app architecture and a quick demo. I run it locally, show 7 teams and 30 prospects from two JSON files, and when I draft Travis Hunter the AI auto picks the next player, updates the pick log, and continues until the draft is complete. The backend is FastAPI with three endpoints and a builder AI pick function that sends needs, available players, and current picks to a Grok LLM. If Grok fails, the backend falls back to the highest ranked need position. No action was requested from viewers.</description></oembed>