Nvidia Adds Hardware Monitoring Design to AI Agent Safety Platform
Nvidia adds a Sentry hardware monitoring design to its AI agent safety platform. See what OpenShell offers now and what IT teams still need to verify. The post Nvidia Adds Hardware Monitoring Design to AI Agent Safety Platform appeared first on TechRepublic .
Nvidia is enhancing its AI agent safety platform with a new hardware monitoring design called Sentry. The company's layered approach to AI agent safety includes OpenShell software, which sets access boundaries, and Sentry, which monitors agents running on separate hardware. Sentry, a reference design, is not yet available for purchase or general release.
OpenShell, which is now widely available, runs agents in sandboxes and allows operators to define file, network, tool, process, and credential permissions. Sentry, built on Nvidia BlueField-4 data processing units, monitors agent activity, quarantines agents within milliseconds if they cross software boundaries, and records agent actions for investigation.
IT teams should assess whether Sentry's hardware monitoring layer integrates with their existing Vera Rubin infrastructure for agentic workloads.
Written by urgent.news from TechRepublic's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
