<?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/4f7b6e6ecba44811af419a1ae0932d1b&quot; frameborder=&quot;0&quot; width=&quot;782&quot; height=&quot;586&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>586</height><width>782</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>586</thumbnail_height><thumbnail_width>782</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/4f7b6e6ecba44811af419a1ae0932d1b-0a8a09f1f2b0c591.gif</thumbnail_url><duration>250.824</duration><title>Explaining JSON Schema for AI Output Enhancement 🌟</title><description>I recorded this video to explain how using JSON schema can enhance the output of your AI column. By specifying fields in JSON, we can align the AI-generated responses with your prompt requirements, improving performance. I demonstrated how to use JSON schema to structure responses effectively. Additionally, I addressed the issue of hidden examples in the interface and suggested a preview to ensure proper display. Action requested: Implement JSON schema for better AI output alignment.</description></oembed>