American technology firm Nvidia has unveiled a new security platform designed to govern artificial intelligence agents and limit the risk of uncontrolled autonomous behaviour. The system, named the Open Agent Safety Platform, combines software tools and independent monitoring to prevent AI agents from exceeding the permissions granted to them.

The platform’s goal is to prevent a scenario where AI systems act beyond their programmed boundaries or assigned tasks, a concern often raised about future autonomous systems. Nvidia’s initiative seeks to impose a framework of oversight on AI agents as they become more advanced and integrated into various sectors.

The introduction of the Open Agent Safety Platform represents a proactive corporate step towards managing the risks associated with increasingly capable AI. It highlights growing industry focus on safety alongside capability in a key global technological field.