NVIDIA OpenShell Reference Architecture 如何在规模化中保障 AI 智能体工作负载的安全与治理
How NVIDIA OpenShell Reference Architecture Secures and Governs AI Agent Workloads at Scale
NVIDIA OpenShell Reference Architecture 通过定义安全边界和治理策略，在规模化中保障 AI 智能体工作负载的安全。该架构支持智能体在执行复杂任务时访问文件、工具和互联网，并能动态协作。架构通过强化访问控制、审计日志和权限管理，降低智能体长时间运行带来的风险。
Autonomous agents can work for hours on complex tasks, accessing files, tools, the internet, and spawning other agents to collaborate with. Executing complex...
Autonomous agents can work for hours on complex tasks, accessing files, tools, the internet, and spawning other agents to collaborate with. Executing complex tasks over long time horizons leads to compounding risk: the agents may download code, build new tools, request additional privileges, and touch more of the underlying infrastructure. The agents’ action paths are determined as they work…
来源: NVIDIA Technical Blog · developer.nvidia.com