Pods and Ports Can’t Describe an AI Agent: Write Your First Per-Call Policy
From publicly posted calendar Checked yesterday
About this event
Once an AI agent is discovered, traditional Kubernetes pod and port rules fall short. Agents dynamically choose models, MCP tools, and other agents at runtime over the same HTTPS connection, meaning network-level policies either block them completely or allow unrestricted access. This session covers per-agent governance. We replace shared API keys and broad service accounts with verifiable agent identities and scoped, short-lived credentials. You will learn to write fine-grained policies, permitting specific models and read-only tools while denying other calls, and safely test them in observation mode before enforcing them in production. Platform engineers who will own agent mandates on a shared cluster, AI and ML engineers whose agents need real access to tools and data, and security engineers who want to approve agents with more than a checklist. Session 1 is helpful but not required. Whether your agents are making simple model calls today or preparing to connect with complex tools, this session will help you build robust per-agent policies for your upcoming deployments.