<?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/2c80949975ed45858563732a70645d0d&quot; frameborder=&quot;0&quot; width=&quot;2228&quot; height=&quot;1671&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1671</height><width>2228</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1671</thumbnail_height><thumbnail_width>2228</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/2c80949975ed45858563732a70645d0d-7a2e6aedc817bdeb.gif</thumbnail_url><duration>251.346</duration><title>Optimizing Your Workflow with the Right Model Selection 🛠️</title><description>Hey Sandy, I apologize for the delay in getting back to you. I reviewed the issues you&apos;re facing with the workflow setup, and I noticed that the model is currently set to GPT-40mini, which isn&apos;t suitable for the complex task of finding available time. I recommend switching to the 03 model for better performance, especially for scheduling tasks. If you could make that change and send me the task URL, I&apos;d be happy to take another look. I&apos;ve had good experiences using the 03 model for scheduling with clients globally, so I think it will help you too.</description></oembed>