<?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/dc0df4028d0a43c296ddbf83cd4db091&quot; frameborder=&quot;0&quot; width=&quot;1726&quot; height=&quot;1294&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1294</height><width>1726</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1294</thumbnail_height><thumbnail_width>1726</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/dc0df4028d0a43c296ddbf83cd4db091-7523a805ea1910a9.gif</thumbnail_url><duration>302.064</duration><title>Enhancing the Glitch Investigator Game 🤖</title><description>Hello everyone, this is Steven Gobran. In my final project for A1-110, I transformed the original buggy number guessing game into a full-applied AI system with two new features: a RAG-powered bug pattern lookup and an automated reliability evaluator. I demonstrated how the bug pattern lookup retrieves relevant documentation for common Python errors and how the reliability evaluator tests the system&apos;s performance with seven checks. I encourage you to explore these features and provide any feedback on the project.</description></oembed>