<?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/8d613aa434cf4a829e93160d01df35ae&quot; frameborder=&quot;0&quot; width=&quot;1108&quot; height=&quot;831&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>831</height><width>1108</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>831</thumbnail_height><thumbnail_width>1108</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/8d613aa434cf4a829e93160d01df35ae-ec30a1d5e6d100b1.gif</thumbnail_url><duration>206.2514</duration><title>Designing an End-to-End Multi-Agent AI Workflow with Symphony 🤖</title><description>Today, I guide you through creating a multi-agent AI workflow using Symphony. We explore available tools like perplexity and image-to-text, and how to add new ones. I show how to design workflows, run functions, and access private tools securely. No content access, just efficient workflow design and execution. Let&apos;s dive in!</description></oembed>