{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/db15276f52a34da1960218a76ecf40d5\" frameborder=\"0\" width=\"1658\" height=\"1243\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1243,"width":1658,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1243,"thumbnail_width":1658,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/db15276f52a34da1960218a76ecf40d5-fce9107d23762b16.gif","duration":104.491,"title":"Ensuring AI Safety with SafetyGuard: A Comprehensive Evaluation Platform","description":"In this video, I discuss the critical need for safety evaluations in AI deployments, as many companies are currently operating without a systematic check for vulnerabilities. I introduce SafetyGuard, our automated AI safety evaluation platform, which analyzes code bases and provides comprehensive reports on risk, security, cost, and performance within minutes. I showcase how it works using a GitHub repo URL, highlighting its ability to pinpoint issues in the code and suggest fixes. With this intelligence, we can confidently deploy AI applications while ensuring their security. I encourage you to consider how SafetyGuard can enhance your AI safety protocols."}