<?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/cdd4ad04b51f44cb94e89dbc13a36968&quot; frameborder=&quot;0&quot; width=&quot;1366&quot; height=&quot;1024&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1024</height><width>1366</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1024</thumbnail_height><thumbnail_width>1366</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/cdd4ad04b51f44cb94e89dbc13a36968-59329c4700fd8189.gif</thumbnail_url><duration>1197.824</duration><title>ArchGuard AI: Agentic Architecture Assistant (Team Beta)</title><description>Let me quickly walk you through this project structure. At the core is the SRC folder organized by responsibility, with Specialist agents like Agents Architect, Security, and Performance extending shared Base and Factory behavior. Their outputs are combined in Synthesizer.py into a final consolidated report, with ConfigSettings centralizing constants and MemoryManager handling session persistence. Under Tools and UI, we have GitHub REST connectors, UIComponents, and App as the entry point, plus helpers like Export and LLMFactory. Outside SRC, Outputs stores Markdown, JSON, and Docx artifacts, and there are unit, E2E, and Streamlit UI tests. No action was specifically requested from viewers.</description></oembed>