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.
Ask the AI about this article →
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Visko raised $10 million in pre-seed funding from Llama Ventures and opened public access to its first foundat…
AI company Runway has unveiled Solaris, the first model in a new category it calls "Interface World Models." I…
Google's AI search gave advice to call emergency services for users alone with an African, Indian, or Pakistan…
John Deere introduced JD, a conversational AI tool that lets farmers ask open-ended questions about their hist…
Nvidia CEO Jensen Huang said on Fox Business that AI is creating 'hundreds of thousands' of jobs, including in…
Israeli startup DataAgent Ltd
