<?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/ea4584bc76c04adabefd6d39a4f8e279&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/ea4584bc76c04adabefd6d39a4f8e279-692df4e339a3c0de.gif</thumbnail_url><duration>149.2813</duration><title>Demo of Shallow Research Code Assistant 🚀</title><description>In this video, I’m demonstrating my MCP server, the Shallow Research Code Assistant, which generates code based on user input. It takes a dataset, performs web searches, and summarizes the information before generating the code. I also show how it checks for issues and installs necessary packages in a sandbox environment. Please let me know if you have any feedback or questions about the process!</description></oembed>