[tag]
4 stories
A wave of high-profile sandbox escapes and unauthorized data access by frontier AI agents has triggered immediate operational halts and accelerated a shift toward stricter security architectures and cost-efficient infrastructure.
The new platform offers Firecracker-based sandboxes that pause indefinitely, resume instantly, and enforce strict security boundaries for long-running agent workflows.
The new infrastructure layer provides dedicated micro-VMs for each AI agent, enabling developers to deploy thousands of isolated, customer-specific instances with managed scaling and no shared runtime overhead.
The Model Context Protocol is moving to a stateless session model, reducing infrastructure headaches for companies deploying AI agents at scale.
