<?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/9371cac6bc614cfc82e0f2728df5147a&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/9371cac6bc614cfc82e0f2728df5147a-bb2347f65464960c.gif</thumbnail_url><duration>104.725</duration><title>Launch Proof Testing With BrainBase Agents</title><description>This Loom explains a launch proof built with BrainBase to simulate real crowd usage during website launch rather than using automated traffic. It uses multiple BrainBase agents: a tester lead agent for system tests like overflow, a critic agent for visual UI styling scoring, and a chaos agent that simulates erratic behaviors from different personas before the page loads. The Janitor agent scales testing across multiple regions and ensures all instances shut down, with plans to connect to Flash for broader regional testing. The Loom concludes by showing how the evaluation report looks, including an error.</description></oembed>