<?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/a6096a5c0ac14224a3782d738bbf6e2c&quot; frameborder=&quot;0&quot; width=&quot;1108&quot; height=&quot;831&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>831</height><width>1108</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>831</thumbnail_height><thumbnail_width>1108</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/a6096a5c0ac14224a3782d738bbf6e2c-0023eca03a16f6fd.gif</thumbnail_url><duration>156.0768</duration><title>Enhancing Code Understanding with AI-Powered Comments 🚀</title><description>In this video, we introduce Scope, a tool designed to help developers effectively comment their code bases using LLM routing with Martian. We generate comments at various abstraction levels, from line-by-line to file-level, making it easier to understand code quickly. Our approach optimizes cursor context management, significantly reducing token usage by up to 95%, which enhances overall efficiency. I encourage you to explore the demo and see how our file summaries can improve your coding experience. Please let us know your thoughts and any questions you might have!</description></oembed>