agent gateway
3 stories filed under agent gateway on Beyond Market Intelligence. The newest of them: “Google's new service runs AI agents in isolated microVMs with secure checkpointing”, “A defense-in-depth architecture for autonomous AI agents”, and “Secure AI agents require zero trust, starting now”. Google's Agent Compute Engine runs AI agents in isolated microVMs with checkpointing, letting you suspend and resume execution environments without exposing credentials. Autonomous agents that can reason and act on their own introduce a category of risk that application-level controls were never built to contain. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every agent gateway story on Beyond Market Intelligence, newest first.

Google's new service runs AI agents in isolated microVMs with secure checkpointing
Google's Agent Compute Engine runs AI agents in isolated microVMs with checkpointing, letting you suspend and resume execution environments without exposing credentials. The design keeps API keys and OAuth tokens outside the sandbox, using an external Agent Gateway to authenticate and inject secrets. That's a thoughtful approach to a persistent problem. For a deeper look at agentic security risks, our coverage of "AI coding tool Claude Code exposed 2,282 secrets in public repositories" explores what happens when those protections aren't in place.

A defense-in-depth architecture for autonomous AI agents
Autonomous agents that can reason and act on their own introduce a category of risk that application-level controls were never built to contain. Treating that risk as a single problem produces incomplete architectures, says Oscar Wahlberg, senior director of product management at Nutanix. The guardrails catching a malicious prompt won't stop a hallucinating agent from deleting databases or leaking sensitive data. A defense-in-depth architecture spanning infrastructure, network, and control plane layers is what actually scales into production.

Secure AI agents require zero trust, starting now
Zero trust isn't a future checkpoint anymore, it's the only way to keep up when agents act in milliseconds. Ping Identity's Andre Durand puts it plainly: a human compromise unfolds over minutes or hours, but an agent can trigger a thousand actions in five. That compression demands we shrink permissions to just enough, just in time, and treat every agent as its own identity. The window to build this architecture is narrow. Move now, or retrofit later at far greater cost.