<?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/486cd61d7c4c4b61b735be978ab04a90&quot; frameborder=&quot;0&quot; width=&quot;1658&quot; height=&quot;1243&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1243</height><width>1658</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1243</thumbnail_height><thumbnail_width>1658</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/486cd61d7c4c4b61b735be978ab04a90-64f9389279fa478f.gif</thumbnail_url><duration>295.318</duration><title>How AI Feedback Improves Boxing Training</title><description>This Loom explains a proposed AI and human style feedback product for athletes based on video analysis. The author describes a round based workflow where users record drills, set an intent such as keeping hands up between punches, and receive AI feedback identifying specific frame moments where form breaks, alongside guidance to correct it. They also illustrate an intent focused on head movement off the center line, noting the AI feedback compared with the author’s own assessment of what was working and what needed refinement. The Loom concludes by positioning this as a V1 that could expand to other drills and sports beyond boxing, such as golf, tennis, and squash.</description></oembed>