<?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/4a136aa0219a44eca1508dbfb1c77fdd&quot; frameborder=&quot;0&quot; width=&quot;1754&quot; height=&quot;1316&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1316</height><width>1754</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1316</thumbnail_height><thumbnail_width>1754</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/4a136aa0219a44eca1508dbfb1c77fdd-806c4210d44b78b5.gif</thumbnail_url><duration>64.875</duration><title>Building AI Native Automation Workflows</title><description>This Loom explains Pedro’s system-oriented approach to building AI-native automation and backend infrastructure. He describes using AI tools alongside Cloud Code, APIs, ROS, Python, and databases like Postgres and Superbase to create real operational workflows. He also covers orchestration logic and operational safeguards, including retries. For cloud infrastructure, he mentions using AWS services such as Cognito and other components like SAPI 8-Way.</description></oembed>