<?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/86b1a2618fb9465bb24249099dffdba6&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/86b1a2618fb9465bb24249099dffdba6-cebb988b15f591ca.gif</thumbnail_url><duration>162.83</duration><title>Intro: Build AI Teammates</title><description>This Loom explains how to build AI teammates on the Top 10 GI platform by following three core steps. First, describe the agent using the Omnibox or remix an existing agent, for example creating a cold-call scenario for an education counselor that asks questions and categorizes the lead. Second, configure the agent with tools and evaluation criteria, such as enabling human transfer for cold calls or adding browser, Google Slides, or PDF support for demos and interviewing. Third, deploy and share the agent via a one-time link, embed it in an application, or connect it to phone calls and Google Meet and Zoom.</description></oembed>