Tag
The Muse security architecture provides detailed control over when AI agents require human-in-the-loop approval, enhancing safety and usability in automated systems.
The author shares an open-source workspace architecture that structurally prevents AI agents from exfiltrating private data by enforcing human-gated outbound actions and isolating the engine from the data repository.
Perplexity detailed the security architecture of its Computer agent, including Firecracker microVM isolation, scoped connector permissions, and prompt injection defenses.