<?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/32d10916b9464df9a5d4d22ed268b0f6&quot; frameborder=&quot;0&quot; width=&quot;1114&quot; height=&quot;835&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>835</height><width>1114</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>835</thumbnail_height><thumbnail_width>1114</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/32d10916b9464df9a5d4d22ed268b0f6-0ecb918db0ddf250.gif</thumbnail_url><duration>237.917</duration><title>Enhancing Code Quality with Hugging Tree: A Solution for AI-Driven Development Challenges</title><description>In this video, I discuss the challenges we face with tech debt and dysfunctional teams, especially with the introduction of AI coding agents like Cursor, which can create nuanced bugs that are hard to trace. I&apos;ve developed a solution called Hugging Tree, which scans repositories and builds a semantic tree to help with context and semantic search. I demonstrate how it works using a booking service I created for my brother&apos;s golf simulator business, specifically focusing on modifying the access code sending feature. I encourage you to explore the relationships within your code and consider using Hugging Tree to improve your coding processes. Please take a look at the generated XML plan and the inferred relationships for your projects.</description></oembed>