Who Let the Agents Out? Securing AI Workflows the Right Way

Learn to secure AI agent workflows in cloud-native environments through robust identity and authorization strategies in this conference talk from KubeCon + CloudNativeCon. Explore how to move beyond hard-coded credentials by implementing trusted, granular identities for agents acting on behalf of users. Discover strategies for establishing traceability, enforcing least privilege principles, and enabling auditable decision-making within zero-trust architectures. Focus on shared agents and tool-calling patterns while examining how SPIRE's workload identity integrates with user identity to support secure delegation and dynamic, context-aware authorization. Understand how to safeguard agent interactions with external tools and data sources through identity propagation and policy enforcement. Gain actionable insights through a real-world case study using Llama Stack and the extended Model Context Protocol (MCP) to build secure, identity-aware agentic platforms ready for production deployment.