Introduction

Kaizen is runtime security for the AI agents you build. You attach it to an agent, it inspects every action the agent takes, and it decides allow or block against your policy. On top of that, it learns each agent's normal behavior and flags the actions that fall outside it.

What it secures

Agents act through tool calls, API requests, file operations, and outbound connections. Kaizen evaluates those actions, not the prompt or the model's text. The case that matters is an agent doing something outside its normal job, whether it was manipulated, misconfigured, or compromised.

How it fits

• Client (data plane). A lightweight library you attach to your agent. It enforces policy locally and reports each action. SDKs for Python and TypeScript, an MCP shim, and framework hooks.
• Observer. An isolated service that learns each agent's behavior and judges deviations. It runs in your own environment.
• Control plane. The managed API and console for policy, keys, and verdicts.

See Architecture for how the parts connect and where the Observer runs.

The verdict contract

inspect(action) -> { decision: allow | block, reason, evidence }

The contract is the same whether you call the SDK directly, wrap an OpenAI Agents run, or sit in front of an MCP server.

Next: Quickstart to attach Kaizen and protect your first agent.