3 September 2026

Capsule Security releases AI safety system to stop rogue autonomous agents

• Capsule Security, a startup founded in 2025, built a detection system using Nvidia's Nemotron models to monitor what autonomous AI agents do before they act, allowing real-time approval or blocking.
• The system sits outside an agent's workflow and judges whether each action matches the task assigned, catching problems at the step they occur rather than after damage is done.
• On an academic benchmark of 9,429 real agent incidents, Capsule's system reached 98% accuracy and responded in as little as 71 milliseconds, outperforming comparable systems from OpenAI, Anthropic and Google.
• The larger detection model was optimized to run on a single graphics processing unit, cutting memory requirements by close to half without losing accuracy.
• Customers including financial institutions and technology companies already process billions of tokens through the system, according to Capsule's April public launch with seven million dollars in seed funding.

Reported by SiliconANGLE