<?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/8e5991da3693421c97c276f0ae180ed9&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/8e5991da3693421c97c276f0ae180ed9-63ef9bfd8673a04c.gif</thumbnail_url><duration>94.824</duration><title>Structured LLM System Demo | Adam Hall</title><description>In this video, I share a system I built called Decision Group, which is an AI-driven platform designed to produce consistent and reliable JSON outputs. Using prompt engineering and schema validation, I can generate hundreds of pages of content efficiently. My focus has been on creating a lightweight agent workflow with structured reasoning and orchestration. I am excited about the potential to apply this approach to job-related tasks, particularly around agent workflows. I encourage you to consider how we can leverage this technology in our projects.</description></oembed>