Copilot Agent Builder: How to Build Microsoft 365 Agents

The Agent Builder in Microsoft 365 Copilot (previously known as Copilot Studio agent builder) allows you to easily and quickly create agents for Microsoft 365 Copilot, offering an interactive AI development experience within Copilot.

You can define dedicated knowledge sources, including SharePoint content and information provided by Microsoft 365 Copilot connectors, as well as OneDrive files, Teams chats, Outlook email and public websites, it's possible to test the agent before deploying it in Copilot conversations or sharing it with colleagues in your organization.

In this article, we'll take a closer look at the features and limitations of Agent Builder and learn how to build a custom AI assistant from scratch.

Copilot Agent Builder: a brief introduction

Microsoft 365 Copilot has been available to organizations since November 2023 as an AI assistant added to their Microsoft 365 subscription. Since then, the Redmond tech giant has kept expanding it, introducing a range of new features for its digital assistant, a streamlined experience for building agents, and more.

In November 2023, Microsoft launched Copilot Studio, a conversational AI platform that allows customers to customize Microsoft 365 Copilot and create their own assistants. Microsoft refers to these customized Copilots as “Copilot Agents.”

To simplify the process of creating an agent, Microsoft introduced a new experience for building custom agents with Agent Builder. Agent Builder acts as a lightweight version of Copilot Studio (for a period Microsoft also called it Copilot Studio Lite) built directly into the Microsoft 365 Copilot app, where users can specify what they want their agent to do and what knowledge sources it can use; all through natural language prompts.

Once created, these agents (tailored to our specific needs and requirements) can be used exclusively by their creators or shared with selected colleagues or the entire organization. Let’s explore more in the following sections.

What is Microsoft Copilot?

But before we begin, let’s briefly talk about what Microsoft Copilot is.

Copilot is the digital assistant designed to simplify users’ daily tasks, boost productivity, and spark creativity. Its main purpose is to generate code, assist with writing, and support collaboration. Seamlessly integrated into the most popular Microsoft 365 applications, Copilot offers contextual suggestions and helps users understand information effectively.

Microsoft Copilot isn’t just another productivity tool; it’s a catalyst for a deep transformation in the way we work and interact with technology. It marks a shift from manual and repetitive tasks to a future where people and artificial intelligence collaborate together.

The impact of Copilot has been tremendous, across every industry.

In fields such as law, medicine, and finance, where information overload is a daily challenge, Copilot can make a difference by helping professionals sift through vast amounts of data, draft documents quickly, and make smarter decisions in less time.

Under the hood, Microsoft Copilot is powered by cutting-edge AI technologies. It all starts with large language models (LLMs), particularly the latest GPT models developed by OpenAI and, in a growing number of experiences, Anthropic's Claude models, which administrators can choose to enable. These sophisticated algorithms, trained on massive datasets of text and code, enable Copilot to understand and generate human-like language with remarkable fluency.

Microsoft combines these models with its own orchestration and with Microsoft Graph, which grounds answers in the emails, files, meetings and chats each user can already access, optimizing Copilot’s capabilities for the Microsoft 365 ecosystem.

But LLMs are just the beginning.

Copilot also leverages machine learning, a branch of AI that allows systems to learn and improve from experience without being explicitly programmed. Combined with the context of Microsoft Graph and, where enabled, personalization settings, this helps Copilot give answers that fit the way each person works.

Despite the impressive technology, Microsoft is committed to ensuring responsible use. The development and deployment of Copilot are guided by responsible AI principles, focused on fairness, reliability, safety, privacy, inclusivity, transparency, and accountability. AI is a powerful tool, poised to change many aspects of our work and personal lives. That’s why it must also be trustworthy and ethical.

In that spirit, it's understandable that concerns about data privacy and security arise with AI tools like Copilot. Microsoft takes these concerns very seriously and has implemented robust measures to protect customer data. Copilot is designed to process data in a secure environment, complying with strict privacy standards. Your data is not used to train AI models, and you always retain control over your information.

Microsoft’s assistant features target a wide range of users and professionals, including developers, content creators, and knowledge workers looking for AI-powered assistance in their tasks.

The main ways to use Microsoft Copilot

• Adopt Copilot: Microsoft offers various Copilot assistants to boost productivity and creativity. Integrated into a variety of Microsoft products and platforms, Copilot transforms the digital workspace into a more interactive and efficient environment.
  ‍
• Extend Copilot: Developers can incorporate external data to streamline user workflows and reduce the need to switch contexts. This not only enhances productivity but also encourages greater collaboration. With Copilot, it's easy to integrate this data into commonly used Microsoft products.
  ‍
• Build your own Copilot: Beyond adopting and extending, you can create a custom Copilot for a unique conversational experience using Microsoft Foundry, Azure AI Search, Microsoft Copilot Studio, and other Microsoft Cloud technologies. A custom Copilot can integrate business data, access real-time external data via APIs, and be embedded in enterprise applications.

Licensing

Microsoft Copilot is available in various forms, with pricing packages tailored for different use cases, such as:

• Copilot (Free): The free version offers access to generative AI features for tasks like computer management (in Windows), online search (in Edge), and general chatbot interactions on the web.
  ‍
• Microsoft 365 Premium: Designed for individual users who want to make the most of generative AI. It replaced Copilot Pro in October 2025 and, for $19.99 per month, combines the Microsoft 365 apps with Copilot in Outlook, Word, Excel, PowerPoint and OneNote and the highest Copilot usage limits for consumers.
  ‍
• Microsoft 365 Copilot Chat: Available to business users at no extra cost, it offers secure AI chat grounded on the web and lets users build and use agents, with pay-as-you-go options for agents that work on company data.
  ‍
• Microsoft 365 Copilot: This version is built for individuals and teams working with Microsoft apps. It includes access to Copilot Studio, enterprise-grade security, privacy, and compliance, as well as advanced capabilities.

There are also multiple Copilot versions tailored for specific Microsoft tools. For example, there are integrated Copilot solutions in Microsoft Dynamics for sales and customer service teams, and Microsoft Security Copilot, which is also embedded in tools such as Microsoft Purview.

So, what can Copilot actually do?

Let’s take a look:

• Contextual AI assistance: Copilot understands the content and context of the information it receives to provide relevant and personalized suggestions.
  ‍
• Integration with Microsoft 365: Copilot is embedded in Microsoft 365 apps like Word, Excel, PowerPoint, and Outlook, making it readily available for everyday tasks.
  ‍
• Natural language interaction: You can interact with Copilot using plain language, eliminating the need to learn complex commands.
  ‍
• Content creation and summarization: Copilot can generate text, emails, and presentations, as well as summarize existing content to highlight key points. You can even create images using Copilot, thanks to its built-in image generation capabilities.
  ‍
• Data analysis and visualization: Microsoft Copilot analyzes data, identifies trends, and creates powerful visualizations to communicate insights effectively.
  ‍
• Collaboration: Copilot enhances teamwork by suggesting edits, organizing discussions, and providing summaries of meetings and chats.
  ‍
• Workflow automation: Copilot turns repetitive tasks into automated workflows, boosting productivity and fostering innovation.
  ‍
• Constant evolution: Microsoft regularly adds new capabilities and prebuilt agents to its digital AI assistant, such as Researcher, Analyst and Copilot Cowork, so it becomes increasingly helpful over time.

In short, using Copilot means having a personal assistant built directly into Microsoft 365 apps. It understands and generates text, which means it can summarize long documents, write emails, and even help plan your next big project or translate that pile of confusing documents demanding your attention.

But it’s not just about text.

Copilot can explore Excel spreadsheets, extract useful information, create formulas, and even generate sophisticated charts that visualize data. If PowerPoint is your thing, Copilot can help design slides, suggest content, and even draft speaker notes—so you can focus on your presentation without distractions.

The best part? Copilot is everywhere in Microsoft 365. No matter which Microsoft app you’re using, it’s there to help with everything: writing a flawless reply to a tricky email, building an impressive presentation in minutes, or analyzing a mountain of data with just a few clicks.

And it's flexible. Whether you're a marketer looking for ideas, a salesperson prepping the perfect pitch, or a data analyst deep in numbers: Copilot is ready to help.

Although many Windows 11 users were initially skeptical when Microsoft began investing heavily in Copilot, the service has grown significantly since its preview release.

Today, it is considered one of the best productivity tools.

According to Microsoft’s latest earnings call for the fourth quarter of fiscal year 2026, held in July 2026, Microsoft 365 Copilot has passed 30 million paid seats, and net seat additions more than doubled compared with the previous quarter. Microsoft also described Copilot as evolving from a chat assistant into agents capable of completing multi-step tasks, with Copilot Cowork becoming generally available in June 2026.

Who can use Agent Builder: licensing and access

Access to Agent Builder, and to the capabilities an agent can use, depends on the licenses assigned in the tenant. Both Agent Builder and Copilot Studio are included in the Microsoft 365 Copilot license for authenticated users. Organizations that haven't assigned Copilot licenses to everyone can still use the tool: agents grounded only on web knowledge can be built at no extra cost, while agents that work on organizational data can run on Copilot Credits or a pay-as-you-go plan.

‍

Colleagues can add a shared agent only if they hold the license required by the capabilities configured in it. Admins can also enable or disable the Agent Builder entry point for users from the Microsoft 365 admin center.

Copilot Agent Builder: features and how to build your own agent

Microsoft offers many Copilot solutions designed to meet the specific day-to-day needs of businesses.

To give organizations more control over their AI assistants, Microsoft’s Copilot Studio allows users to create and customize their own Copilots, and the tech giant is now introducing significant updates to the experience.

Agent Builder focuses on declarative agents: assistants that follow dedicated instructions and draw on chosen knowledge sources whenever a user asks them something. Autonomous agents, which perform tasks triggered by actions coming from various tools, systems and databases without manual requests, are built instead in Copilot Studio.

Agent Builder leverages Power Platform APIs but does not store data in Dataverse or consume the tenant's Dataverse storage entitlement.

To help users get started, Agent Builder also offers templates: preconfigured agents with a description, instructions and prompts for common scenarios, which can be used as they are or customized, for example by adding the team's own knowledge sources.

To highlight the potential of agents built with Copilot Studio, Microsoft shared several case studies. In one instance, Pets at Home, a UK-based pet care company, created an agent for its profit protection team, enabling them to "assess potential loss cases more effectively and spend more time on qualified analysis instead of just gathering information." In another example, McKinsey & Company built an agent to speed up the client onboarding process, cutting wait times by 90% and administrative work by 30%.

The Agent Builder offers a simple interface that lets you quickly and easily create declarative agents using natural language, manually, or starting from a template.

Agent Builder allows you to configure specific knowledge sources that the agent can reference. This feature helps the model provide more relevant responses based on specific files, folders, and sites from SharePoint and OneDrive, Teams chats and meetings, Outlook email, uploaded files and Microsoft 365 Copilot connectors.

You can enable or disable web content when creating or editing your agent. When web content is enabled, the agent can use publicly available information on the web to enrich responses to a prompt. The responses shown to users include citations and an icon indicating the use of web content. When web content is disabled, the agent only uses its pre-trained knowledge and the custom knowledge sources you provide. In the current interface the option appears as the Search all websites toggle, and up to four specific public URLs can also be added as knowledge sources.

The agent can also reference specific SharePoint sites, files, and folders as knowledge sources.

However, when using SharePoint sources, you must consider the following limitations:

• You can select up to 100 SharePoint files and one SharePoint list per agent; other source types have their own limits, summarized in the table below.
• Files already uploaded to SharePoint may have existing permissions and sensitivity labels, which will be respected when the agent generates a response.

Knowledge source limits per agent

‍

Uploaded files become embedded content of the agent, so anyone who can use the agent can receive answers based on them. To keep answers anchored to the material provided, the Only use specified sources toggle on the Configure tab makes the agent prioritize those sources for search-type questions.

To get started with Agent Builder, simply open the Microsoft 365 Copilot app, and select New agent in the left pane. The same entry point is available in Copilot inside Teams (desktop and web), in both Work and Web mode, but not in the mobile apps.

You can create your agent in three ways:

• Using the Describe tab with natural language.
• Using the Configure tab to manually create it through the interface (select Skip to configure on the New agent page).
• Starting from a template and refining it with natural language or on the Configure tab.

The Describe tab allows you to build an agent using plain language. As you provide information conversationally, the agent's name, description, and instructions are continuously updated to refine its behavior. This experience offers a rich yet simple way to create a personalized agent using natural language. After creating an agent, you can return to the Describe tab at any time to update it using natural language.

You can build agents by answering the questions posed by the Agent Builder.

The builder incrementally updates the agent with each step of the conversation, and all changes are saved automatically. You can make edits to the agent at any point during the conversation, and any updates to the name, description, and instructions will be reflected automatically. Agent Builder can also add knowledge sources based on your description, and you can add them yourself through the plus (+) icon in the chat box. The icon, instead, is managed from the Configure tab.

The Configure tab allows you to view and modify the agent’s information, offering more control and precision. The Describe and Configure tabs are synchronized: fields in the Configure tab update to reflect the latest changes made in the Describe tab, and you can switch between tabs to use the experience that best suits your workflow when creating an agent.

The following table describes the fields that can be modified to build your own agent:

‍

Once all the steps are completed, we’ll have our agent, ready to be tested.

Agents in the Try it tab are not fully created yet, so some features are not available. For example, they cannot be used to share prompts, provide feedback, or mention other agents in the Microsoft 365 Copilot app. These features become available after the agent is officially created.

The Try it tab initially displays starter prompts, which can be clicked to trigger the prompt and start the conversation. You can select New Chat to begin a new conversation with the agent and view the starter prompts again if needed. When you're satisfied, select Create: the agent is saved as private, and later changes reach users only after selecting Update.

How to share your agent

After creation, the Share button opens a dialog where you can add colleagues or groups with one of two roles. Agents support multiple owners with equal rights, so an agent doesn't remain orphaned when its creator changes role.

• Owner: Edit, share and manage the agent. Only individual users can be owners, not groups.
  ‍
• Chat user: Use the agent without changing it. Groups can be added only with this role.

The Org-wide sharing for chat access toggle makes the agent discoverable by everyone in the tenant through the Agent Store, unless admins restrict this option. For broader distribution, owners can submit the agent to the org catalog: after admin approval, it appears in the "Built by your org" section of the Agent Store.

Agent Builder vs Copilot Studio: which one to choose

Both tools create agents, but they address different needs. Agent Builder fits agents for an individual or a small team, built in natural language on existing content. Copilot Studio fits agents for a whole department, the entire organization or external customers, or agents that need workflows, integrations and tighter lifecycle control.

‍

The choice isn't final: an agent created in Agent Builder can be copied to Copilot Studio, keeping its configuration and instructions, when it needs actions, more data sources or enterprise deployment options. Before building anything, it's also worth checking the agents already included in Copilot, such as Researcher and Analyst or Copilot Cowork.

Copilot Agent Builder: current limitations

Since agents and the Agent Builder feature are still evolving quickly, they come (as is typical in such cases) with a few limitations. While these do not affect the core qualities of the product, they might cause inconvenience for users who are unaware of them.

The main limitations at this time are:

• Agent Builder doesn't support actions that integrate external services: to add actions, connectors or workflows, the agent must be copied to Copilot Studio.
  ‍
• Groups can be added only as chat users: owners must be individual users.
  ‍
• Automatic sharing of SharePoint files and folders is supported only when sharing with specific people or groups, not with everyone in the organization. Therefore, you must manually update file and folder permissions used by the agent to grant access to designated users, so the agent can return information from those knowledge sources.
  ‍
• Agent Builder currently does not support Customer Managed Keys.
  ‍
• Agents created through Copilot Studio Agent Builder cannot be used in Teams group chats or 1:1 chats.
  ‍
• If a tenant has disabled web content via the "Allow web search in Copilot" policy, web content is blocked as a knowledge source in Agent Builder. However, the web content toggle in the knowledge panel is not disabled, which is a UI limitation. The "Allow web search in Copilot" policy overrides the UI setting.
  ‍
• The authoring experience isn't available in the mobile versions of the Microsoft 365 Copilot app and Teams.

Conclusion

Generative AI is still a young technology, but it is becoming more advanced and customizable each day.

The introduction of agents through Agent Builder in the Copilot environment represents more than anything else the evolution of Microsoft’s “copilot” vision and the company’s commitment to pushing the limits of its AI assistant with every iteration.

Though still evolving quickly, the potential is considerable and is sure to intrigue anyone looking to take their business a step into the future.

Building an agent, however, is only half of the job, because the other half is making sure colleagues actually use it, and use Copilot itself, every day. This is where Copilot Circle helps organizations, with an AI agent that reads real Copilot usage, sends personalized nudges in Teams and guides each employee from the first prompt to a daily habit.

FAQ on Copilot Agent Builder

What is Copilot Agent Builder?

Copilot Agent Builder is a feature built into Microsoft 365 Copilot and powered by Copilot Studio (also known as Copilot Studio agent builder or Copilot Studio Lite) that allows users to quickly build personalized AI agents for Microsoft 365 Copilot. It offers an interactive, guided experience designed to help users easily create tailored assistants using natural language, manual configuration or templates.

What’s the difference between Microsoft Copilot and a Copilot Agent?

Microsoft Copilot is the built-in AI assistant in Microsoft 365 apps, designed to support users with daily tasks such as writing, data analysis, and content generation. A Copilot Agent, instead, is a customized extension created with Agent Builder, designed to address specific business scenarios using defined knowledge sources and configurable behavior.

How do I create an AI agent with Agent Builder?

You can create an agent by using a natural language interface called “Describe”, by configuring it manually through the “Configure” tab, or by starting from a template. The Describe and Configure tabs are synchronized, allowing you to switch between them and make changes at any time.

Is Copilot Agent Builder free?

Agent Builder is included in the Microsoft 365 Copilot license. Users who only have Microsoft 365 Copilot Chat can build agents grounded on web knowledge at no extra cost, while agents that use organizational content without a Copilot license require Copilot Credits or a pay-as-you-go plan configured by the admin.

What knowledge sources can an agent use?

Agents can use SharePoint sites, folders and files (up to 100 files and one list), OneDrive files (up to 50), Teams chats and meetings, Outlook email, up to 20 uploaded files and data available through Microsoft 365 Copilot connectors. If enabled, they can also access public web content, either from up to four specific URLs or from all websites.

Can I share my agent with other users?

Yes. You can share an agent with individual colleagues or groups, as owners (Can edit) or chat users (Can chat), with the whole organization through the org-wide sharing toggle, or submit it to the org catalog for admin approval. SharePoint files added to the agent can be shared automatically, but access to whole sites must be granted in SharePoint.

Can the agent be used in Teams chat?

Currently, agents created with Agent Builder can be built and used in Copilot inside Teams, but they can’t be used in Teams group chats or 1:1 chats.

Can I test my agent before publishing it?

Yes. Agents can be tested in a dedicated tab, called Try it, before being published. Some advanced features are not available during testing, but you can still start conversations and observe how the agent behaves.

What are the main limitations of Agent Builder today?

Agent Builder can’t create actions that call external services, each knowledge source type has its own limit, agents can’t be used in Teams group or 1:1 chats, Customer Managed Keys aren’t supported and the authoring experience isn’t available on mobile. Additionally, interface toggles may not always reflect the policies enforced by the tenant.

What is the difference between Copilot Studio and Agent Builder?

Agent Builder is a no-code experience inside Microsoft 365 Copilot for information workers who need agents for themselves or a small team, mainly to answer questions from company content. Copilot Studio is a standalone low-code platform for makers and developers, with connectors, multi-step workflows, autonomous triggers and full lifecycle management. An agent can be copied from Agent Builder to Copilot Studio at any time.

How do I access Agent Builder and get started?

You can access Agent Builder via the Microsoft 365 Copilot app by selecting “New agent” in the left pane, or directly from Microsoft Copilot in Teams. From there, you can start designing your agent using natural language, the configuration interface or a template.