Microsoft has released an open-source standard called Agent Control Specification (ACS) that gives developers, compliance, and security teams a consistent way to govern AI agent behavior. ACS lets teams define portable policy files specifying what agents may or must not do, when human approval is required, and what actions to log. Policies are enforced at multiple interception points in an agent's workflow — before input, before tool calls, after tool results, and before final responses. Unlike fragmented approaches such as system prompts or custom code checks, ACS provides a unified governance layer that travels with agents across frameworks. It ships as an SDK with plugins for LangChain, OpenAI Agents SDK, Anthropic Agents SDK, AutoGen, CrewAI, Semantic Kernel, and more.
