<?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/fdd32ce470304e318ede3c9c89e97e80&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/fdd32ce470304e318ede3c9c89e97e80-12d457e69459ebe2.gif</thumbnail_url><duration>70.799</duration><title>Stretch Search for Learning in Context</title><description>This Loom presents Stretch Search, a hackathon project that helps people learn from coding agent concepts. The speaker explains that instead of only showing a single result, Stretch Search searches and builds a learning map so users can understand coding agents from different perspectives. They describe using it on topics like what a hoodie is, and having it explain concepts such as “number five” or the first ten. The Loom also notes that users can reference previous searches for an in context understanding to keep up with new terms on the page.</description></oembed>