{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/eea15a45c105455594b479dc7508d0a1\" frameborder=\"0\" width=\"1440\" height=\"1080\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1080,"width":1440,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1080,"thumbnail_width":1440,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/eea15a45c105455594b479dc7508d0a1-19b7e1d3b474745c.gif","duration":302.481,"title":"Introducing Agent Guard: A Real-Time Proxy for Responsible AI Compliance 🚀","description":"In this video, I introduce the concept of Agent Guard, a real-time proxy designed to intercept AI tool calls and evaluate them against eight responsible AI dimensions and regulatory compliance frameworks, including the India DPDPA and EU AI Act. As AI agents evolve from simple chatbots to autonomous systems making critical decisions, it's essential to ensure their actions are safe and compliant. I demonstrate how Agent Guard can block unsafe actions, such as biased hiring decisions or unauthorized data processing, before they execute. I encourage you to consider how this solution can enhance the responsible deployment of AI in our systems. Thank you for your attention!"}