The traditional security model, which trusts entities inside a network perimeter, is obsolete for AI. A Zero Trust approach is necessary because agents operate inside the perimeter. This model assumes threats are already present and treats every agent and request as a potential threat by default.

Many companies initially build their own AI gateway, viewing it as a simple, thin proxy layer. However, upon moving agents to production, they quickly discover that real-world complexity around governance, observability, and security requires a far more robust, specialized control plane platform.

Trying to secure AI agents by restricting which tools are exposed in the Model Context Protocol (MCP) is the wrong approach. Security should be implemented at the API layer itself using robust, granular permissions like OAuth scopes. Treat the AI agent as any other third-party application accessing your API.

Instead of manually writing complex security policies for agents, run the agent in an audit mode to capture its network traffic. Then, use an LLM to analyze this traffic and automatically suggest a comprehensive, baseline security policy based on observed behavior.

Securing AI agents requires a three-pronged strategy: protecting the agent from external attacks, protecting the world by implementing guardrails to prevent agents from going rogue, and defending against adversaries who use their own agents for attacks. This necessitates machine-scale cyber defense, not just human-scale.

Recent AI agent hacks demonstrate that the most significant security risk isn't the sandbox's operating system integrity but its network access. Preventing rogue behavior hinges on strictly controlling 'egress' — the agent's ability to connect to the open internet — which is the true security perimeter to defend.

As agents become more complex, their infrastructure needs expand beyond simple compute. Demand is growing for networked sandboxes allowing agent-to-agent communication, sidecars for services like proxies, and fine-grained control over network egress for security and logging.

An intelligent AI agent is harmless in isolation. The danger emerges the moment it's connected to external tools, creating pathways for data exfiltration and unauthorized actions. Security must focus on creating hard guardrails and blocks for these connections, rather than trying to control the non-deterministic agent itself.

The focus of agent security is shifting from traditional identity and access management (IAM) to governing what an agent *does* with its permissions. Granting an agent access is necessary, but the real challenge is controlling the near-infinite permutations of actions it might take with that access.