<?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/a93ac8491a134422a21e14624059f9da&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/a93ac8491a134422a21e14624059f9da-1704546583327.gif</thumbnail_url><duration>245.46666666666667</duration><title>Optimize a RAG Application for Answering Questions on Nike&apos;s 10k Filings</title><description>Hey, it&apos;s Joel, one of the co-founders of Pre AI. In this video, I&apos;ll show you how to optimize a rack application that answers questions on Nike&apos;s 10k filings. You can follow along at darksappr.ai. We&apos;ll go through a tutorial and then analyze why the application gave the wrong answer. We&apos;ll use trace logs and evaluation metrics to identify and fix the issue. No action is required from you, but feel free to ask questions or provide feedback.</description></oembed>