<?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/e9e8c40c46844edfb5721ea9ed6cf04c&quot; frameborder=&quot;0&quot; width=&quot;1664&quot; height=&quot;1248&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1248</height><width>1664</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1248</thumbnail_height><thumbnail_width>1664</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/e9e8c40c46844edfb5721ea9ed6cf04c-5236421e109c8efe.gif</thumbnail_url><duration>193.928</duration><title>Airtable Field Agent demo</title><description>In this video, I discuss the process of using AI to fill out a field agent&apos;s information by searching for a person&apos;s name and retrieving their personal homepage URL. I encountered some disappointing outputs on the first attempt, which is not uncommon with Airtable. To improve the results, I decided to switch to a better model, specifically GPT-5, and then tried using Flash, which worked successfully. I encourage you to explore these AI tools and techniques in your own projects for better efficiency.</description></oembed>