{"id":18191,"date":"2025-02-06T09:00:00","date_gmt":"2025-02-06T17:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/insidetrack\/blog\/?p=18191"},"modified":"2025-02-13T09:09:44","modified_gmt":"2025-02-13T17:09:44","slug":"unlocking-enterprise-ai-extensibility-at-microsoft-with-microsoft-copilot-studio","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/insidetrack\/blog\/unlocking-enterprise-ai-extensibility-at-microsoft-with-microsoft-copilot-studio\/","title":{"rendered":"Unlocking enterprise AI extensibility at Microsoft with Microsoft Copilot Studio"},"content":{"rendered":"\n
\"Microsoft<\/figure>\n\n\n\n

Microsoft 365 Copilot extensibility is a revolutionary new framework for advancing enterprise AI. By creating their own agents, individuals and teams can customize Copilot\u2019s behavior with additional instructions, grounding, and actions, all while providing a clear and discoverable entry point in the tool\u2019s user interface.<\/p>\n\n\n\n

These agents help employees reach beyond Microsoft Graph and Microsoft 365 applications to do their work more thoroughly and efficiently. By empowering users to experiment with AI-driven assistance and capabilities internally at Microsoft, we\u2019re unlocking efficiency, process automation, and data-driven insights tailored to specific individuals\u2019 or teams\u2019 needs.<\/p>\n\n\n\n

One tool is making Copilot extensions accessible to more employees than ever before: Microsoft Copilot Studio.<\/p>\n\n\n\n

This low-code solution makes it possible for both technical and non-technical users to create their own agents and tailor Copilot\u2019s capabilities to their work. At Microsoft Digital, the company\u2019s IT organization, we\u2019re the first to implement Copilot Studio and develop a methodology for empowering our employees to create while establishing guardrails to keep our organization\u2019s data safe.<\/p>\n\n\n\n

As a result, we\u2019ve built best practices that help us protect employees while enabling helpful agents\u2014from individualized tools to organization-wide utilities. We\u2019ve also learned lessons that can help customers navigate their own Copilot Studio journey.<\/p>\n\n\n\n

Extending enterprise AI with Microsoft Copilot Studio<\/h2>\n\n\n\n
\"Hasan,
Aisha Hasan (left to right), Lianne Zelsman, David Johnson, Eileen Zhou, Jake Visser, and Amy Rosenkranz (not pictured) are all part of a team enabling Microsoft Copilot Studio internally at Microsoft.<\/em><\/figcaption><\/figure>\n\n\n\n

Microsoft Copilot Studio<\/a>, a part of Microsoft Power Platform, empowers employees to build their own agents or use them to extend Microsoft 365 Copilot\u2019s value. It uses the same low-code connector model as Power Platform to power actions through first-party and third-party services.<\/p>\n\n\n\n

As a result, users can create their own agents tailored to specific professional needs and business functions. These agents can narrow the focus of knowledge within the Microsoft 365 Graph, reach outside of it, and even take actions.<\/p>\n\n\n\n

There are several ways to create agents. They range from simple natural language queries in Copilot Studio agent builder through Copilot Chat in Microsoft Teams and SharePoint to the full-featured Copilot Studio graphical authoring environment to a combination of Copilot Studio and Azure AI.<\/p>\n\n\n\n

\n

\u201cCopilot Studio is a way for a non-technical person to spin up an agent quickly,\u201d says Amy Rosenkranz, principal product manager responsible for Copilot extensibility internally at Microsoft. \u201cYou can pull from a SharePoint site, from a graph connector, or from the web, and so employees are using it to tailor their experience to their business process.\u201d<\/p>\n<\/blockquote>\n\n\n\n

Building agents with Copilot Studio<\/h3>\n\n\n\n
\"Images
Microsoft Copilot Studio lets creators build their own agents through natural language queries or a low-code graphical authoring environment.<\/figcaption><\/figure>\n\n\n\n

Ultimately, the goal is to help employees work more efficiently by putting them in the driver\u2019s seat through the power of self-directed agent creation. It also helps alleviate strain on business functions by getting people to the answers they need faster, without the need for human intervention.<\/p>\n\n\n\n

\n

\u201cThere\u2019s an important role for Copilot Studio in helping customize the solutions our employees create, whether they want to use existing functionality, extend their knowledge, or expand their skill compatibility,\u201d says Eileen Zhou, senior program manager in Microsoft Digital. \u201cAnd it provides opportunities for both non-technical creators who want to create individualized solutions and people with advanced knowledge who are building more enterprise-focused agents.\u201d<\/p>\n<\/blockquote>\n\n\n\n

To empower our employees for this kind of creativity, we needed to put guardrails in place that ensure they can build agents confidently without putting themselves or the company at risk.<\/p>\n\n\n\n

Managing the scale and sophistication of Copilot Studio creations<\/h2>\n\n\n\n

Building guardrails around agent production meant developing a system for classifying them according to their purpose, reach, and potential risk.<\/p>\n\n\n\n

On one end of the spectrum, simple retrieval agents might only access content that individuals author and own. Non-technical employees typically create this kind of agent through natural language prompts in Copilot Studio agent builder.<\/p>\n\n\n\n

On the other end, more elaborate tools\u2014task or autonomous agents that combine knowledge, action, and orchestration\u2014need to cross data boundaries to accomplish their work. More technically advanced IT employees and professional developers build these agents for larger-scale business functions using the full-featured Copilot Studio authoring environment.<\/p>\n\n\n\n

Agent capabilities<\/h3>\n\n\n\n
\"A
Different kinds of agents have different capabilities, and their escalating access and reach demands protective procedures and policies.<\/figcaption><\/figure>\n\n\n\n

This simple taxonomy doesn\u2019t capture the whole picture though. As a result of the varying reaches and risk profiles for different agents, we tend to group them into three categories:<\/p>\n\n\n\n