<?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/b4bd8126a1f146c49cb36a89dc9b676c&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/b4bd8126a1f146c49cb36a89dc9b676c-666754c2f7fe1e22.gif</thumbnail_url><duration>182.319</duration><title>Building an AI-Powered Workflow Engine from Scratch 🚀</title><description>In this video, I showcase a workflow engine builder I&apos;ve developed as a competitor to Niden, which is currently in progress but has a publicly available backend. I demonstrate a workflow that fetches stock data for Apple, runs it through a Monte Carlo risk simulation, and sends alerts via Slack based on the output. I&apos;ve built various integrations and can create new ones quickly, which enhances the functionality of my applications. I also highlight that this engine powers real-life sites, including a booking application. While I have many ideas for its potential, I invite feedback and thoughts on further developments.</description></oembed>