SecurityConference50min
Taming Agentic AI: Running rogue agents safely on Kubernetes
This talk presents Agent Sandbox, a Kubernetes-native framework for securely running autonomous AI agents and untrusted code. It explains how the system combines the safety of virtual machines with the efficiency of containers using CRDs and gVisor isolation, enabling scalable and secure deployment of non-deterministic workloads.
talk.summaryAiDisclaimer
Abdellfetah SGHIOUARGoogle Cloud
talkDetail.whenAndWhere
Thursday, June 18, 10:10-11:00
Room 4A
talks.roomOccupancytalks.noOccupancyInfo
As AI agents increasingly evolve from simple chatbots to autonomous systems capable of generating and executing code and manipulating data, they introduce significant security and operational challenges. This talk explores Agent Sandbox, a Kubernetes-native solution designed to safely and efficiently run non-deterministic and untrusted workloads.
We will discuss how Agent Sandbox bridges the gap between the safety of virtual machines and the speed of containers. You will learn how it utilizes a dedicated CRD to manage templates and allow Agents to run generated code in an isolated container, leveraging gVisor to provide a user-space kernel runtime.
Join us to discover how to scale your AI agents confidently, knowing that even if they go rogue, your cluster remains secure.
We will discuss how Agent Sandbox bridges the gap between the safety of virtual machines and the speed of containers. You will learn how it utilizes a dedicated CRD to manage templates and allow Agents to run generated code in an isolated container, leveraging gVisor to provide a user-space kernel runtime.
Join us to discover how to scale your AI agents confidently, knowing that even if they go rogue, your cluster remains secure.
Abdellfetah SGHIOUAR
Senior Developer at Google Cloud. Co-host of the Kubernetes Podcast by Google and CNCF Ambassador. My focus areas include High-Scalable distributed systems on Kubernetes, Service Mesh, and Serverless. With a background in datacenter scale architecture, operations, and consulting. I spend most of my time working on optimizing GenAI Apps for large-scale operations using Cloud Native Technologies and producing content targeting developers and ops professionals.