{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/83585c694bf34fe892707218b68bb2cb\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/83585c694bf34fe892707218b68bb2cb-323039862ab9bbb9.gif","duration":150.113,"title":"Enhancing Security for Azure OpenAI in Defense Operations","description":"In this video, I introduce Bearstack AI, which is focused on creating a security layer that facilitates the adoption of Azure OpenAI within the Department of Defense. I highlight the critical issue of data spillage, particularly with sensitive information like grid coordinates and PII. Our BearStackAPI, running on Azure Functions, intercepts file uploads at the ingestion layer to ensure compliance by masking sensitive data before it reaches Azure OpenAI. We are excited to prepare this architecture for deployment in the Tradewinds marketplace, aiming to deliver secure Microsoft AI solutions to the tactical edge. I encourage you to consider how this technology can enhance security in your operations."}