video1.0<iframe src="https://www.loom.com/embed/71361b8d05b74aff8339060190a76a19" frameborder="0" width="1662" height="1246" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12461662Loomhttps://www.loom.com12461662https://cdn.loom.com/sessions/thumbnails/71361b8d05b74aff8339060190a76a19-4d2e76ccfb68a998.gif363.542In this video, I demonstrate Vigil, a risk assessment engine designed for evaluating agent deployments in production environments. We’re addressing the gap in traditional insurance coverage for autonomous agents, like our financial advisor chatbot, which can execute trades up to 10 grand with human oversight for larger transactions. I walk through our system's workflow, highlighting how we assess legal and technical risks, ultimately arriving at a risk score of 8.5 out of 10 for our chatbot. I encourage you to consider how this framework can be applied to your own projects, especially as we navigate the complexities of compliance and risk management in software development.