<?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/f3069ff50dbd425b833c50b3f0fe1323&quot; frameborder=&quot;0&quot; width=&quot;1038&quot; height=&quot;778&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>778</height><width>1038</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>778</thumbnail_height><thumbnail_width>1038</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/f3069ff50dbd425b833c50b3f0fe1323-fbd3a05f0731c0e3.gif</thumbnail_url><duration>76.341</duration><title>Using AI to Coach Live Games</title><description>This Loom explains how AI-enabled live analysis can coach players by finding errors they might not notice. It describes a setup where, during a game, a frame is sent every second to the cloud for analysis and the system returns one actionable item if there is any. The goal is to save time and continuously catch mistakes in real time. It also notes the solution works on Metare band glasses with a camera that opens to provide the live feed.</description></oembed>