Agile InsightsBriefing
A closed reference volume, an open steel toolbox with hand tools and a pair of headphones on a dark desk, labelled AGT, Reference Series and Reference 6. A yellow bar along the bottom reads Reference series, number 6.

Reference 6 · Primer · About 5 minutes

Microsoft Agent Governance Toolkit: runtime control for AI agents

Microsoft's free, open source toolkit that checks and records what an AI agent does, and what it still leaves to you.

#microsoft#agents

Download the MP3 · Linda, an AI voice, reads a script written from the sources below.

In this episode

01Free code, not a standardMicrosoft published the toolkit in April 2026 as open source code under the MIT licence, and it is in public preview as at October 2026. Developers place it between an AI agent and the tools the agent uses.
02Permissions do not check actionsAccess permissions control which systems an agent can reach, not what it does once inside. The toolkit checks each action an agent attempts against written rules, before the action happens.
03Four ideas that carry itEach attempted action is allowed, warned, blocked, sent to a human or modified. Every agent gets its own verifiable identity, isolation limits what it can touch, and a tamper evident record is kept of each decision.
04Where it sits beside Agent 365Agent 365, Entra Agent ID and Purview look at agents across the whole organisation. The toolkit sits inside the agent's own runtime and decides before each step. Its OWASP coverage is the project grading itself, not an audit.
05Limits and three first stepsWith no policies loaded, the toolkit allows everything by default. Start with a register of agents with named owners, decide which actions need human approval, then pilot it on one low risk agent.
Sources and links (9)
The repository · GitHub
Source code, licence, releases and issues for the toolkit.
Release history · GitHub releases
Tagged releases, including the latest, v4.1.0.
Announcement · Microsoft Open Source Blog
Microsoft's launch post from 2 April 2026.
Limitations · Project documentation
The project's own list of what it does not do.
Roadmap · Project documentation
Direction and priorities, with no commitments.
Agent Framework and the toolkit · Microsoft DevBlogs
How the toolkit fits Microsoft Agent Framework.
Microsoft Agent 365 · Microsoft Learn
The tenant wide control plane for agents.
Governing agent identities · Microsoft Learn
Entra Agent ID sponsors, access packages and lifecycle.
OWASP agentic top ten · OWASP GenAI Security Project
The 2026 list of the main risks for agentic applications.

Written from public sources and checked on 10 October 2026. The toolkit is public preview software and its details change often. Check the current documentation before relying on it.

How this maps to what we do

Agents plan, use tools and act over many steps. The governance question is who owns them, what they may reach, and how they are stopped.

Standard or rule
What an organisation needs
Where we help
A register of agents with one named owner each, scoped permissions, a tested stop control, monitoring, and an incident playbook that covers third parties.
AI Operating Model DesignAI SecurityManaged Support
Microsoft Agent Governance Toolkit
Runtime policy enforcement and observability for agents on the Microsoft platform, tied to your governance model.
AI SecurityAI Operating Model DesignManaged Support

These are Agile Insights AI Strategy & Governance offerings.

Want to know more?

Sign up for our podcast at agile-insights.com.au.

Read the transcript

Linda The Microsoft Agent Governance Toolkit is a free tool that stops an AI agent doing something it should not do, at the moment it tries. By the end of this episode, you will know what it is, what it covers, and what it leaves squarely with you. This is as at October 2026.

Linda Start with what it is. Microsoft published it in April 2026, announced on the Microsoft Open Source Blog. It is open source software, released under the MIT licence, which means anyone can use and change it at no cost. It is not a standard, and it is not a certification. It is code that developers place between an AI agent and the tools the agent uses. It is a toolkit, not a service Microsoft runs for you, and it works outside the Microsoft world too.

Linda Here is the problem it solves. Many organisations are now giving agents real access: email, databases, payment systems. Access permissions control which systems an agent can reach. They do not control what the agent does once it is inside. Imagine an agent allowed to read customer records that decides, on its own, to send them to an outside address. The permissions allowed the read. Nothing checked the intent. This toolkit is built to check that, before the action happens.

Linda Who uses it? Mostly engineering and security teams, who install it. But executives meet it in other ways. A risk lead asks, how do we know this agent stayed inside its limits? An auditor asks for evidence. A board asks who is accountable when an agent acts. The toolkit produces some of the evidence for those conversations. It does not produce the answers.

Linda Now, what is in it. Four ideas carry it. The first is policy enforcement. Every action an agent attempts is checked against written rules, and the answer is allow, warn, block, send to a human, or modify. If the check itself fails, the action is blocked. The second is identity. Each agent gets its own verifiable identity, so you can tell which agent did what, instead of five agents sharing one login. The third is isolation, which means limiting what an agent can touch, with a kill switch to stop it. The fourth is evidence. It keeps a tamper evident record of each decision, so you can show later what was asked and why it was allowed.

Linda How does it connect to the rest of the Microsoft stack? Think of two layers. Microsoft Agent 365, which became generally available on the first of May 2026, is the tenant wide control plane. It keeps a registry of agents, and works with Microsoft Entra Agent ID, which gives each agent a directory identity and a named human sponsor. Microsoft Purview adds data protection and audit. Those tools look at agents across the whole organisation. The toolkit sits closer to the action, inside the agent's own runtime, and decides before each step. It plugs into Microsoft Agent Framework, and the project publishes a guide for deploying it with Foundry Agent Service. Its documentation also describes a bridge to Entra Agent ID, though that is a project tutorial, not a Microsoft product feature.

Linda It also maps to the OWASP list of the ten biggest risks for agentic applications, published in December 2025. The project's own page says it covers all ten. Its repository badge says seven fully and three partly. Either way, that is the project grading itself. It states plainly that this is not a third party audit.

Linda Now the limits, because they matter most. The toolkit governs actions. It does not judge whether the agent reasoned well. It records attempts, not outcomes. It does not govern the documents an agent reads. And if no policies are loaded, it allows everything by default. A tool that looks switched on, but is not configured, is worse than none. None of this replaces an owner for each agent, decisions about scope, a risk register, or independent assurance.

Linda Three first steps. One, make sure you have a register of agents, each with a named accountable owner. Two, decide which agent actions need a human to approve them. Three, ask your technology team to pilot the toolkit on one low risk agent, and test that it blocks what it should.

Linda For primary sources, start with the project's GitHub repository and documentation site, the Microsoft Open Source Blog announcement, Microsoft Learn on Agent 365 and Entra Agent ID, and the OWASP agentic top ten. Links are in the show notes.

Linda On currency. The toolkit is in public preview. The project says it is production quality, but it warns of breaking changes before general availability, and it has given no date. The latest tagged release is version 4.1.0, from the ninth of June 2026, though the code was still changing this week. The project says it is moving towards shared governance across several organisations. Package names have changed more than once, so check the current documentation before relying on any detail I have given.

Linda To recap, this toolkit checks and records what an agent does, but people still have to decide what agents should do. If you'd like to know more, sign up for our podcast at agile-insights.com.au.

More on #microsoft

Episode 25 · Primer and discussionThe managed loop: what you still own when the vendor runs your agent.Episode 22 · Primer and discussionFrom Pilots to Programs: govern an agent by what it does.Episode 17 · Primer and discussionSwitching on a role pack is a process decision, not an I T toggle.Episode 10 · Primer and discussionMicrosoft now ships the controls for AI agents. The decisions are still yours.Episode 20 · Primer and discussionUsage is not quality: who reads the feedback?Episode 15 · Primer and discussionMicrosoft governs the access. You still have to govern the answer.

Every episode tagged #microsoft

All of the reference series (16) · Follow AI Governance Reference in Apple Podcasts or any podcast app

Everything from Agile Insights: briefings, Making You Think and the reference series