<?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/1b55d963cd8c4ea695edcb139efd9af7&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/1b55d963cd8c4ea695edcb139efd9af7-ab52ac10e00d3bdb.gif</thumbnail_url><duration>1279.048</duration><title>ODK-AI: Populating the upper level</title><description>In this video, I walk you through the process of populating a GitHub issue using an AI tool from ODK. I demonstrate how to authenticate and configure the tool to break down issues into smaller elements and create individual tasks. I also highlight some challenges I faced with the AI&apos;s output and the importance of providing precise instructions. Please take a moment to review the generated issues and ensure they meet our standards.</description></oembed>