<?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/a2b5a65b23c2428f8a0dd43c138af423&quot; frameborder=&quot;0&quot; width=&quot;1662&quot; height=&quot;1246&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1246</height><width>1662</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1246</thumbnail_height><thumbnail_width>1662</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/a2b5a65b23c2428f8a0dd43c138af423-9e0da9d1b94c181b.gif</thumbnail_url><duration>151.506</duration><title>MeetLoop: Proactive Agent Learning Feed</title><description>This Loom presents MeetLoop, a shift from a reactive coding-focused agent to a proactive, social feed style learning experience. The speaker argues that while the agent now handles coding and reduces tech debt, understanding debt grows because users spend their day reading Markdown, switching contexts, and losing intent. MeetLoop would generate a personalized social feed based on a user’s learning style, career stage, and company role to help users stay engaged and return with better ideas. A small demo with an MRI tech company shows different feeds for a CEO, machine learning researcher, and intern, each surfacing information at the appropriate level, with a background signal analysis built from multiple layers.</description></oembed>