<?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/b4c47e3491504375b9244ea69fe095df&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/b4c47e3491504375b9244ea69fe095df-f6e1f2d2a39a3920.gif</thumbnail_url><duration>133.975</duration><title>To-Do Created with Z.ai</title><description>Hi everyone, in this follow-up video, I wanted to share the impressive results we achieved with our coding agent for Django applications, similar to Loveable. We explored different frameworks, including OpenAI&apos;s Agents SDK and Pydantic, and I was particularly impressed with the new GLM 4.5 model from Zdata.ai, despite some initial timing issues. I demonstrated how it created a landing page and added tasks with due dates and priorities, which looked fantastic. I encourage you to check out the results and think about how we can implement similar features in our projects. Let&apos;s keep pushing forward with our AI initiatives!

Workshop materials: https://github.com/alexeygrigorev/workshops/tree/main/coding-agent</description></oembed>