Building secure agents with Azure AI Foundry and Microsoft Security | BRK145

Microsoft's presentation discusses building secure and trustworthy AI agents using Azure AI Foundry and Microsoft Security. They highlight the growing use of AI agents in workplaces and the associated trust gap due to concerns about system malfunctions and misuses. To close this trust gap, they demonstrate collaboration between developers, security professionals, and compliance officers. Various tools and guardrails are introduced to ensure AI agents stay on task, are secure, and adhere to data policies. The importance of continuous monitoring and evaluation is emphasized, and integrations with security tools are showcased to enhance the overall trustworthiness of AI systems.