Microsoft releases Agent Control Specification, an open source standard to help developers govern AI agent behavior across deployments

Microsoft introduced Agent Control Specification (ACS), an open source standard that lets developer, compliance, and security teams define policies for what AI agents are allowed to do, must not do, when to require human approval, and what to log for review.

ACS checks agent behavior at multiple points in a workflow — before input is received, before a tool is called, after a tool returns a result, and before the final response reaches the user. Policies can allow, block, or redact actions, or request human approval; developers can also add classifiers and LLMs to judge whether actions meet policy standards.

The specification ships as an SDK with plug-ins for LangChain, the OpenAI Agents SDK, the Anthropic Agents SDK, AutoGen, CrewAI, Semantic Kernel, Microsoft.Extensions.AI, and MCP tools, allowing security policies to travel with agents across different frameworks and environments.