{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/05d3ffa27b844c18af255784b3974514\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/05d3ffa27b844c18af255784b3974514-ae850fc0618e65cd.gif","duration":301.611,"title":"Building an AI-Powered Workflow Engine from Scratch 🚀","description":"In this video, I walk you through the process of building an AI-powered workflow engine from scratch, showcasing how I manage video and audio locally without relying on external APIs. I demonstrate using a script to read various files and transcribe YouTube videos, while also processing screenshots and audio transcripts through different models. I highlight key concepts like the human-in-the-loop (HITL) approach and the execution of workflows that can trigger additional branches. I encourage you to explore these tools and techniques in your own projects, especially if you're interested in enhancing your workflow automation capabilities."}