Who can see your AI agent? Agent sharing limits in the Power Platform admin center

Who can your AI agent be shared with? Agent sharing limits in Copilot Studio

Who can your AI agent be shared with? In Copilot Studio, owners and editors can share an agent, and one click can share it with an entire security group. Sharing limits let IT put a guest list on it.

Think of a party invite

Without limits, anyone with the invite can forward it to everyone they know. With limits, it becomes a guest list: named people only, up to a number you choose.

What IT can control

Sharing limits for agents are a Managed Environments control in the Power Platform admin center. There are three main settings:

  • Let people grant Editor permissions: controls whether makers can share an agent with people who can change, configure and publish it. Editor permissions can only go to individuals, never to security groups.
  • Let people grant Viewer permissions: controls whether makers can share with people who can only chat with the agent, including security groups.
  • Only share with individuals (no security groups): blocks security group sharing, and lets you cap the number of viewers for each agent.

Where to find it

In the Power Platform admin center, select Manage, then Environments, pick a managed environment, select Edit Managed Environments, and use the Manage sharing section. You can also apply the controls at scale with environment groups and rules.

Good to know

The rules apply when someone tries to share. People who already have access keep it, but an agent that breaks the new rules can only be unshared until it complies. It can take up to an hour for the rules to start working, and the limits apply to agents that require sign-in.

Status

Microsoft’s release plan lists block and limit sharing for Copilot Studio as generally available since 23 May 2025, after a public preview from 17 December 2024. Neither Learn page marks the sharing limits as preview.

Practical tip

Start with Viewer sharing to individuals only and a sensible cap, then widen it for teams that need more. To apply it at scale, add managed environments to an environment group and publish the rule: only published rules are enforced.

Sources

One practical AI idea a day from AI Powered 365.

Share this content:

I am Yogeshkumar Patel, a Microsoft Certified Architect and Azure AI Engineer specialising in enterprise ERP and intelligent automation. With deep expertise across Dynamics 365 Finance & Supply Chain, Power Platform, Azure, and AI engineering, I design and lead large-scale digital transformation initiatives that integrate business systems with advanced AI capabilities. With over six years of experience delivering multi-entity ERP rollouts, AI-driven automation, and secure cloud architectures, my focus is on building intelligent, scalable, and governance-led enterprise ecosystems that enhance operational efficiency, data-driven decision-making, and long-term strategic value. Holding a Master’s degree from the University of Bedfordshire, I specialise in integrating AI and agentic systems into core business processes streamlining supply chains, automating complex workflows, and enhancing insight-driven decisions through Power BI, orchestration frameworks, and governed AI architectures. Passionate about practical innovation and knowledge sharing, I created AIpowered365 to help businesses and professionals move beyond experimentation and adopt real-world, enterprise-ready AI and agent-driven solutions as part of their digital transformation journey. 📩 Let’s Connect: LinkedIn | Email 🚀

Post Comment


→ Table of Content