{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/e63e568306ca4401bf0ee048168c5830\" frameborder=\"0\" width=\"1664\" height=\"1248\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1248,"width":1664,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1248,"thumbnail_width":1664,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/e63e568306ca4401bf0ee048168c5830-fda5073a2682c17f.gif","duration":189.2093,"title":"Multi-Agent System for EU AI Compliance - Kiroween [video1]","description":"Hello, I'm Arun Kumar Singh, and in this video, I present my project for the Kirovine hackathon, which focuses on creating a multi-agent system for EU AI compliance. Given the increasing momentum of AI applications and the stringent regulations in Europe, I developed a system that scans AI applications and provides guidelines on compliance with EU legislation. The architecture includes five specialized agents that perform parallel searches for compliance information, aggregate findings, and check for relevance and compliance. I encourage you to explore this innovative approach and consider how it can be applied to ensure adherence to EU regulations in AI development. Thank you for your attention!"}