<?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/b93e78c4113048c08675945a9a961c88&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/b93e78c4113048c08675945a9a961c88-eb2434fc2a8c2b27.gif</thumbnail_url><duration>120.128</duration><title>Introducing Lobsmash: The AI Paddle Coach for Personalized Training and Feedback</title><description>In this video, I discuss the development of an AI Paddle Coach called Lobsmash, which utilizes Gemini on the back end to analyze user-uploaded paddle clips and provide personalized training modules. The coach also facilitates group chats for partners to collaborate and share gameplay footage for feedback. Currently, I have set up a WhatsApp webhook for communication and am using Super Bass as the backend, although I didn&apos;t have time to implement a level of laps. My future goal is to evolve this into a robot that can play paddle with users and give real-time coaching. I welcome any feedback or suggestions as I continue to build this project.</description></oembed>