<?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/251217a66f034cd283f086480e50bfc3&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/251217a66f034cd283f086480e50bfc3-00001.gif</thumbnail_url><duration>264.129</duration><title>LevelUp LLM Tutor</title><description>In this video, I explain how our hypothetical learning platform, Level Up, gathers user context without explicitly asking for it. We use a series of challenges to calibrate the user&apos;s skill level and then use an algorithm to generate prompts for an AI assistant. The assistant guides the user through the onboarding process, collecting valuable data on their understanding and providing hints and feedback. The goal is to create a customized learning plan for each user. No action is requested from the viewers, but it&apos;s important to understand the process behind context gathering in a personalized learning platform.</description></oembed>