The Goal Tells an Agent What to Do. Security Has to Govern How.

Check Point and NVIDIA have launched a beta integration between Check Point's semantic monitoring and the NVIDIA Open Agent Safety Platform, which places security boundaries in the infrastructure outside an agent's reach. Check Point said its monitor judges whether each agent step still fits the task and can deliver a verdict before the action runs in under 100 milliseconds. The two systems work together through NVIDIA OpenShell, addressing the gap that an agent's stated goal rarely specifies how the agent may reach it.

In this article An agent’s goal rarely says how the agent may reach it, and capable agents are good at finding routes nobody planned for. →NVIDIA Open Agent Safety Platform puts the boundary in the infrastructure, outside the agent’s reach →Check Point semantic monitoring judges whether each step still fits the task →the two already work together in a beta integration with NVIDIA OpenShell →the monitor’s verdict can arrive before the action runs, in under 100 milliseconds What the Goal Leaves Out When an organization hands an autonomous agent a job, such as processing supplier invoices, it states the goal … The post The Goal Tells an Agent What to Do. Security Has to Govern How. https://blog.checkpoint.com/ai-security/check-point-nvidia-openshell/ appeared first on Check Point Blog https://blog.checkpoint.com .