Then, customers like you pushed us further.

You told us where agents didn’t scale, where authentication slowed runs, and where it was hard to understand why something failed—or to prove it behaved correctly. You also told us where your organization needed more control, visibility, and flexibility before rolling out computer‑using agents at scale.

Today’s updates are a direct response to that feedback.

Computer‑using agents in Microsoft Copilot Studio now offer more model choice, stronger security and governance, and easier scale—so you can automate more of your work across web and desktop apps with confidence.

Here’s what’s new with computer use—and why it matters.

Build more powerful agents with Copilot Studio

Create, customize, deploy, and manage your agents with Copilot Studio. Check out available features, use cases, resources, and FAQ.

Let’s get started

Choose the right model to navigate dynamic interfaces

Computer-using agents now support multiple foundation models, including Anthropic’s Claude Sonnet 4.5 alongside OpenAI’s Computer-Using Agent. This gives you the flexibility to choose the best fit for each agent, based on the interface and the task.

• Use OpenAI Computer-Using Agent to orchestrate multi‑step web and desktop flows.
• Opt for Anthropic Claude Sonnet 4.5 when you need high performance reasoning on dynamic user interfaces (UIs) and interpretation of dense, changing dashboards.

Secure authentication with built in credentials and Azure Key Vault

Authentication shouldn’t be the reason automations stall. Computer use now offers built‑in credentials so agents can:

• Securely perform website and desktop app logins.
• Reuse them across multiple agents and automations.
• Eliminate manual login prompts during runs, enabling unattended execution.

For example, if an agent needs to log into a vendor portal and update a desktop ERP every night, built-in credentials now let the agent authenticate to both the web portal and the desktop app automatically. This removes manual interruptions and makes overnight processing dependable while maintaining governance controls. No need to babysit “unattended” runs.

You can choose between two storage options aligned to your governance needs: internal storage (encrypted in Microsoft Power Platform) for low-friction setup, or Azure Key Vault for enterprise-grade secret management.

Credentials are encrypted and are never exposed to the AI model, so only authorized agents can access them. This way, your security and compliance team can feel confident scaling CUAs to more scenarios.

See every computer-using agent action with session replay and audit logs

As agents touch more business‑critical systems, teams need to know what happened, why it happened, and where.

Computer use now has advanced monitoring and richer observability, so operations, security, and compliance teams can inspect behavior step‑by‑step. This includes:

• Session replay with screenshots.
• Step‑by‑step action logs with action types, coordinates, timestamps, and context.
• Run summaries instruction text, duration, action counts, average time per action, and human escalation counts.
• Resource tracking including websites, desktop apps, credentials used.
• Export options for offline review.

But what does this look like in practice? Imagine an agent run produces an unexpected update, and your team can’t tell whether the agent misread the UI, clicked the wrong control, or encountered a hidden pop‑up.

Session replay and action logs now show exactly what the agent saw and did, pinpoint the step where the UI changed, and produce an exportable record for audit review. That way, you can fix issues faster and retain a defensible compliance trail.

Beyond the monitoring pane, compliance is further strengthened through:

• Microsoft Purview integration, sending audit logs to Purview.
• Dataverse logging with configurable verbosity—choose All data, Data without screenshots, or Minimal.
• Retention options from 7 days to indefinite, to match regulatory and governance requirements.

Simplify infrastructure with managed Cloud PCs for computer-using agents

Scaling UI automation shouldn’t require managing fleets of desktops or fragile virtual machines. The new Cloud PC pool, powered by Windows 365 for Agents, provides fully managed cloud‑hosted machines that are Microsoft Entra joined and Intune enrolled, designed for computer use runs and built to scale with demand.

In other words, these Cloud PC pools provide managed capacity for high-volume runs when demand spikes—without the overhead of keeping dedicated hardware patched, available, and idle the rest of the time. This way, your team can handle spikes without over-provisioning hardware.

Note: For evaluation, you can create up to two Cloud PC pools per tenant with 50 hours of free usage for published autonomous agents—making it easier to pilot CUAs at scale before broader rollout.

Extend—don’t replace—your automation

If you’ve built automations with Microsoft Power Automate and RPA, computer use expands what you can automate—especially when:

• Interfaces change frequently
• APIs aren’t available
• Decision logic becomes more complex

Thankfully, you can keep classic RPA for deterministic scenarios with stable interfaces. CUAs then add flexibility and adaptive reasoning where RPA falls short (such as dynamic web apps, shifting layouts, or complex decisioning). After all, the goal isn’t to start over—it’s to modernize and extend what you already have.

For example, say you have an RPA bot that depends on fixed selectors. Historically, it broke each time a web form changed, forcing constant script updates.

Now, the RPA stays the same, while a CUA handles the variable UI portions—navigating changing layouts, interpreting dialogs, and escalating edge cases. The result? Reduced maintenance and improved reliability.

Get started and help shape what comes next

Ready to try computer‑using agents in a US‑based Copilot Studio environment?

1. Create or open an agent in Microsoft Copilot Studio.
2. Go to Tools → Add tool → New tool and select computer use.
3. Describe the task you want the agent to perform in natural language.
4. (Optional) Choose a model, configure built‑in credentials, and set up a Cloud PC pool for secure, scalable runs.

For deeper guidance, configuration details, and best practices, see the computer use documentation.

Before you go: We’re actively investing in advanced governance, operations, and scale for CUAs—and customer feedback directly informs the roadmap. Tell us what you think of the latest CUA updates today:

• Email feedback to computeruse-feedback@microsoft.com
• Join the Copilot Studio community

The post Computer-using agents now deliver more secure UI automation at scale appeared first on Microsoft Copilot Blog.

In this edition of our monthly roundup, we’re recapping the most exciting new features recently released in Microsoft Copilot Studio.

Build richer agent experiences in Copilot Studio

Automate UI tasks with computer use, now in public preview

Computer use in Copilot Studio is now available in public preview for United States-based environments, giving agents the ability to operate apps and websites directly. Describe a task in natural language, and the agent completes it with a virtual mouse and keyboard—clicking, typing, and navigating user interfaces (UIs). This expands automation into areas where no API or Model Context Protocol (MCP) connection exists—such as data entry, reporting, or information gathering.

The public preview adds several key enhancements. A hosted browser powered by Windows 365 makes it simple to automate web tasks without configuring your own machine, while still supporting local software through registered devices. Templates help makers get started quickly with common workflows.

In addition, credential management allows agents to securely log into sites and apps during runs. While allow-list controls give admins confidence that agents only interact with approved applications and domains. Together, these updates make computer use more secure, resilient, and accessible for enterprise scenarios.

Because computer use relies on built-in vision and reasoning, agents can adapt when interfaces change. This makes it easier to bring Copilot Studio agents into day-to-day processes where human-style navigation is required. Learn more from the announcement blog and try computer use today in the Tools tab in Copilot Studio.

Engage customers on WhatsApp, now generally available

We’re excited to share that the WhatsApp channel for Microsoft Copilot Studio is now generally available. With more than 2.7 billion users worldwide, WhatsApp is the most widely used messaging platform. Now, makers can seamlessly bring their AI agents to where customers already are.

Copilot Studio is the only enterprise-grade AI agent platform with native WhatsApp deployment. In just a few clicks, makers can launch agents that deliver rich, interactive experiences to customers on WhatsApp. Agents can authenticate users by phone number, exchange messages that include images or attachments, and follow the same compliance and governance frameworks that support Microsoft 365 and Power Platform, giving organizations peace of mind as they scale.

This capability opens the door for a wide range of scenarios, from customer support and order tracking to appointment scheduling and product recommendations. By meeting customers in a communication channel they already trust, organizations can reduce friction, accelerate time to market, and strengthen customer relationships.

With WhatsApp now generally available, Copilot Studio helps ensure that organizations can expand their reach and create high-impact customer experiences at enterprise scale. Learn more.

Test and enrich prompts in the prompt builder

Now in preview, makers can systematically test and improve Copilot Studio prompts with new prompt evaluations in the prompt builder. Instead of relying on ad hoc manual testing, you can build comprehensive test sets by uploading cases in bulk, generating them automatically, pulling them from real user activity, or writing them manually. Each evaluation can be customized to focus on what matters most for your use case—tone, clarity, keyword matches, or structured output compliance. Results include both high-level accuracy scores and detailed insights per case, giving makers faster iteration cycles and greater confidence that prompts will perform reliably in real-world scenarios.

The prompt builder also now supports Power Fx formulas directly inside prompts. This lets you enrich your prompts with dynamic inputs such as the current date, text formatting, calculations, or memory table lookups. By combining Power Fx with prompt testing, you can create more context-aware prompts while keeping the authoring experience simple and consistent across Copilot Studio.

Together, these updates reduce rework, shorten testing cycles, and make it easier to maintain reliable, high-quality prompts. Prompt Evaluations are available today in preview, and Power Fx support is enabled by default.

Use file groups as knowledge in Copilot Studio agents, now generally available

Now generally available, makers can organize locally uploaded files into groups and use them as a single knowledge source in Copilot Studio agents. This update helps reduce clutter from long lists of individual files and provides a more structured way to guide agents toward accurate, context-rich responses.

With file groups, you can combine up to 25 groups per agent, covering as many as 12,000 files. You can also add variable-based instructions to fine-tune how knowledge is applied, giving you more control over which content the agent should prioritize in specific scenarios.

File groups can be created during upload or from existing files already added to an agent. Once grouped, the files are treated as one knowledge source. (Note: ungrouping is not yet supported so deleting a file group is required to make changes.)

This capability helps ensure that makers can better organize and scale knowledge within their agents, while providing users with more relevant and precise answers.

Create reusable component collections

Managing copilots across environments is simpler with the component collection capability, now generally available in Copilot Studio. Makers can package agent components, including topics, knowledge, actions, and entities, into collections that can be reused across agents or moved between environments to support application lifecycle management.

To make this process straightforward, you can create solutions to export and import agents and their components using the Copilot Studio Solution Explorer. By grouping everything into a solution, makers can move agents and components across environments in a cohesive, structured way. You can also reuse the agent components to augment other agents in the same environment.

These component collections help teams create a more predictable, consistent approach to managing changes and scaling agents across environments and make creating or augmenting future agents faster than before.

Enable end users to upload files during agent interactions

Agents built in Copilot Studio can now accept files from users and pass them into downstream systems through agent flows, Microsoft Power Automate, or connectors. This opens the door to richer scenarios where file inputs are central to the process, such as document summarization, data extraction, or validation workflows. Makers can now handle these processes without leaving the Copilot Studio experience.

With this update, agents can collect both the file and its metadata (including name, content type, and content) and hand it off for downstream processing. This helps streamline end-to-end processes while reducing the need for workarounds or manual steps.

This enhancement helps ensure that agents can better support real-world business processes, making Copilot Studio a more powerful tool for scenarios where files play a critical role. Learn more about the benefits of file upload for your agents’ users and get started today.

Extend and customize with advanced tools

Unlock advanced scenarios with code interpreter, now generally available

Code interpreter is now generally available in Copilot Studio and Copilot Studio lite (formerly called the Microsoft 365 agent builder), bringing powerful new ways to generate and execute Python code directly within an agent. Makers can use natural language to create Python-based actions, edit the generated code, and save prompts for reuse. At runtime, the agent executes that same code, enabling richer outputs and new possibilities for customization.

With this general availability release, the prompt builder now supports create, read, update, and delete (CRUD) operations on Dataverse tables. That means makers can use natural language prompts to perform these actions without leaving Copilot Studio. Furthermore, agents can dynamically generate visualizations and extend their responses, improving efficiency and quality of consistent reusable logic.

Enabling code interpreter is simple and can be done in two ways. Turning it on at the agent level means that every prompt and action within that agent can execute Python. This is ideal for scenarios that require consistent logic across conversations. The other option is enabling code interpreter in the prompt builder (inside your Tools tab) within an agent, which is more lightweight and specific. This is useful for testing or using one-off prompts without impacting the entire agent.

Get started using code interpreter to generate and execute Python code today.

Integrate Copilot agents into native apps with the Agents Client SDK

The new Agents Client SDK makes it easy for developers to embed Copilot Studio agents directly into their Android, iOS, and Windows applications. With this integration, end users can interact with agents inside the apps they already use, starting with multimodal conversations through text and adaptive cards. Support for additional modalities, including voice, image, video, and context sharing, are on their way.

With the SDK, developers can seamlessly extend agents into mobile and desktop environments, enabling richer conversational experiences and unlocking new workflows where customers are most engaged. This creates opportunities to add agent-driven intelligence directly into day-to-day applications, without requiring users to switch contexts.

Platform-specific documentation and packages are also available for Windows, iOS, and Android. The Agents Client SDKs for text and adaptive card conversations are generally available now.

Create MCP connectors directly in Copilot Studio

You can now connect MCP servers to Copilot Studio with just a few clicks. This feature, now in public preview, makes it easier than ever to extend your agents by bringing in MCP connectors without the need for manual setup or custom development.

Makers can simply provide an MCP host URL and Copilot Studio will handle the rest. Within minutes, your MCP servers can be connected and ready to power agent experiences—helping expand the reach of your agents while reducing setup time and complexity.

This update also introduces support for MCP resources, such as files and images. As the MCP ecosystem continues to evolve, resource support expands the kinds of data and interactions you can bring into your agents, helping you design richer and more flexible experiences.

By making MCP integration simpler and adding resource support, Copilot Studio helps ensure that makers can focus on building impactful agent experiences while seamlessly tapping into the growing power of the MCP ecosystem.

These capabilities are on by default, so you can start using them right away to extend your agents with MCP.

Manage and measure agents at scale

Manage agent billing with a dedicated environment in Copilot Studio lite

We’re making it easier to manage agent billing with the introduction of a dedicated environment for Copilot Studio lite (formerly called the agent builder).

This environment surfaces optional admin-level information around billing and usage. If your organization has enabled billing for Microsoft 365 Copilot, admins can check message usage directly in the Environments tab, making it simpler to track capacity and stay ahead of demand.

For makers, nothing changes and you can continue creating agents without extra steps. Copilot Studio lite checks for and creates the environment automatically if one does not already exist. The result is a smoother authoring experience for makers and clearer administrative oversight for admins, all aligned with how your organization already manages Microsoft 365 Copilot.

This update helps ensure that admins have the transparency and control they need to manage agent cost controls.

Analyze agent performance and measure impact with new metrics

Several new analytics capabilities in Copilot Studio give makers and admins deeper visibility into how agents are used, how effective they are, and the value they deliver.

Themes for generative AI questions in public preview

This feature looks at generative AI questions from the previous week and groups them into suggested themes. The themes show what types of questions customers are asking most and provide a detailed analysis of how well the agent responded. This helps makers quickly identify gaps in coverage and focus improvements where they matter most. This feature is in preview for all customers using generative answers for agents meeting the minimum threshold of 50 weekly questions.

Insights for unanswered generative AI questions in public preview

Copilot Studio now surfaces themes for unanswered generative AI questions directly in the Analytics dashboard. Makers can quickly spot patterns in what users are asking but not getting answers for, helping them prioritize knowledge updates and reduce coverage gaps with less manual review.

Agent monthly usage limits (general availability)

Analytics now display each agent’s monthly Copilot credits limit (as set in the Power Platform admin center) alongside month-to-date usage. Makers no longer need to switch tools to monitor usage and can act earlier if an agent is trending toward its limit.

Active users metric (general availability)

A new view provides visibility into the unique users interacting with an agent. Custom reports include data on daily active users, trend lines over time, and monthly active users. This metric helps teams understand engagement patterns beyond session counts. This data is generally available for agents that are configured for authenticated users.

ROI analysis for agent runs (general availability)

Makers can now define and track savings for autonomous agent runs segmented by time, money, or both. These can be tracked at either the run or tool level. Results are calculated automatically for the selected analytics period, with settings applied retroactively to past runs. This makes it simple to measure ROI in real time and guide investment decisions with data.

These various enhancements expand the analytics toolkit, helping teams measure adoption, spot performance issues, and quantify the business value of their Copilot Studio agents. Learn more about analyzing conversational agent effectiveness.

Upskill with agents

Build your skills with Copilot Studio Agent Academy

We’re excited to introduce Copilot Studio Agent Academy: a free, self-paced curriculum designed to help makers and developers build real, useful agents with Microsoft Copilot Studio.

The curriculum is structured into three progressive levels: Recruit (available now), Operative (coming soon), and Commander (coming early next year). Each level builds on the last, guiding learners from foundational concepts to advanced enterprise deployment. The Recruit module covers how to set up your environment, create your first agent, add topics and generative answers, and publish it to Microsoft Teams. Every module includes guided labs created by the Microsoft Power Platform Advocacy team.

For experienced makers, Agent Academy is a chance to pick up new tips and tricks, strengthen your best practices, and point your colleagues to an approachable way to get started. With a low barrier to entry and room to grow, the curriculum provides a clear path from first steps to organizational scale. As an added bonus, the first 100 learners to complete Recruit will receive a Credly badge for their agents.

Your learning journey starts today. Explore Agent Academy and help bring more makers into the Copilot Studio community.

Stay up to date on all things Copilot Studio 

Check out all the updates live as we ship them, as well as new features releasing in the next few months here: What’s new in Microsoft Copilot Studio.

To learn more about Microsoft Copilot Studio and how it can transform your organization’s productivity, visit the Copilot Studio website or sign up for our free trial today.

The post What’s new in Copilot Studio: September 2025 appeared first on Microsoft Copilot Blog.

Starting today, customers with U.S.-based environments can add computer use to their agents directly as a tool.

New enhancements to computer use

With this public preview release, we’re introducing several enhancements:

• Hosted browser (powered by Windows 365) – Start automating web tasks right away, no machine setup required. Need to use custom desktop applications or access internal sites? You can always register your own machine.
• Getting started templates – Quickly explore pre-built templates for common scenarios to spark inspiration.
• Credentials – Securely store and use login credentials for websites and desktop applications that computer use needs to access.
• Allow-list – Define exactly which websites and applications computer use is permitted to operate on. If there is an attempt to go outside this list, the run will automatically stop.

Unlock new automation scenarios

With computer use, you can enable your agents to perform even more tasks, such as:

• Market research and data gathering – Build agents that can navigate across different websites, filter and read through dashboards, and collect the insights you need for analysis.
• Inventory tracking – Let agents check supplier portals and e-commerce sites to monitor product availability, delivery estimates, or stock levels.
• Automated data entry – Many processes require transferring information between systems that don’t expose APIs. Now your agents can navigate to those forms and enter the data for you.

Already using desktop flows in Microsoft Power Automate?

If you already use machines to run desktop flows, you can also use them for computer use in Copilot Studio. This allows you to build UI automations that go beyond the traditional limitations of robotic process automation (RPA), handling complex and dynamic interfaces with ease.

Computer use is especially valuable when:

• UIs shift frequently – Apps and websites are dynamic by nature, with layouts that can vary across versions.
• It’s easy to get started – Simply describe what you want in natural language, no coding required. You can test and refine with a side-by-side view of the computer and the reasoning chain.
• Vision matters – The task depends on what’s visible on screen, such as interpreting charts and images.

Get started

You can try the public preview of computer use today in Copilot Studio:

1. In any US-based environment, create or open an existing agent.
2. Go to Tools → Add tool → New tool.
3. Select computer use and start building by simply describing the task you’d like done.

We can’t wait to see what you’ll create with computer use! To learn more, check out the documentation. If you have questions or feedback, we’d love to hear from you at computeruse-feedback@microsoft.com.

Microsoft Copilot Studio

Transform business processes across your organization.

Try for free

The post Computer use is now in public preview in Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.

In this edition of our monthly roundup, we’re recapping new features in Microsoft Copilot Studio that were released in June 2025.

Copilot Studio agent builder enhancements in Microsoft 365 Copilot

Bring new knowledge to agents created in the agent builder

For many of us, critical knowledge is fragmented across various sources. It’s easy to find yourself digging through endless Microsoft Teams chats, email threads, and scattered SharePoint sites and documents to find the right piece of information. Emails hold key decisions and plans, Teams chats capture daily collaboration and contexts, and valuable files seem to be lost forever at the moment you need them most.

That’s why we’ve introduced powerful new knowledge sources in the Microsoft Copilot Studio agent builder embedded in Microsoft 365 Copilot. Your agents can now reference Outlook emails and Teams messages—including group chats, channels, meeting chats, and even files you upload directly.

Whether you’re in IT building a support agent trained on policy docs, internal email threads, and technical chat discussions, or a project manager automating reports pulled from daily team messages and inbox updates, you can now give your agents the ability to access a broader set of sources.

To make adding knowledge easier than ever, the builder also suggests relevant knowledge sources based on your recent activity and queries. This helps you identify and connect the right data more quickly. With just a few clicks, you can equip your agents with the same knowledge and context your team relies on to get work done.

These features are generally available now for all users with a Microsoft 365 Copilot Chat license or an active pay-as-you-go plan. Open the agent builder and try them out today, and infuse your agents with even more knowledge to help you move faster, work smarter, and stay informed. Learn more.

Organize knowledge and guide agent responses with file grouping

Earlier this year, we introduced file collections, which give makers the ability to upload multiple files as knowledge sources for their agents. Now, we’re expanding that functionality with file grouping, a new capability (now in preview) that helps you better organize files and fine-tune how your agent uses them.

With file grouping, you can now name and describe your file sets and, more importantly, provide group-specific instructions that guide your agent’s retrieval behavior. This makes it easier to tailor responses based on use case, document type, or even user role without needing to change the content itself.

For example, you might group together internal HR policies, product-specific documentation, or region-specific guides, and tell the agent to only reference that group when certain variables are met. It’s a more structured, transparent way to manage uploaded knowledge, and it makes your large Microsoft Dataverse knowledge bases easier to navigate and control.

To try it out, go to “Add Knowledge” in Copilot Studio and upload two or more files. You’ll see a toggle to enable grouping, along with options to name the group and set instructions. Learn more.

Copilot Studio enhancements for makers

Build and configure powerful agents with the new Tools experience

Tools give agents their power and determine what tasks they can handle as well as what actions they can perform. A new, streamlined Tools tab experience now makes it easier for makers to discover, configure, and manage everything agents need to get work done.

You can now access all your tools in one place. Whether you’re connecting to Outlook, SharePoint, SAP, Snowflake, custom connectors, or Microsoft Power Automate flows, you’ll now find everything in a single, unified view. This includes custom connectors and Model Context Protocols (MCPs) built for your organization.

You’ll also enjoy a more intuitive experience for discovering and adding prebuilt connector actions. Using prebuilt connector actions means you don’t have to build your own from scratch. With just a few clicks, you can set up agents to perform meaningful actions—like sending an email, updating a record, or scheduling a meeting—across Microsoft 365 (including Teams and Outlook), Dataverse, and other services.

Exploring available tools is easier, too. You can see all tools associated with each connector, helping you determine how these capabilities can work together across systems.

Tool configuration has also improved, with enhanced input widgets like calendar controls, file pickers, and time zone selectors. The tab also integrates with IntelliSense to help you configure tools more efficiently, and if a tool is not performing the way you expect, there’s now improved debugging tools like error messages. This will make it much easier to quickly identify and resolve issues with your tools like flows, connector actions, MCPs, and more.

Altogether, the new Tools experience gives you a more centralized, intuitive view that reduces friction when connecting tools, knowledge sources, topics, and flow. All this is designed to make it easier to build the agents you want, with the capabilities they need. Learn more.

Add logic and test your prompts directly inside the prompt builder

The prompt builder tool in Copilot Studio allows makers to create reusable, modular prompts that guide an agent to perform a specific task, such as summarizing, classifying, or extracting information. Assigned to agents or flows, prompts enhance reasoning and output quality for the user. The prompt builder tool has two new features designed for you to enrich and validate your prompts without ever leaving the editor.

You can now add Microsoft Power Fx logic directly inside your prompt inputs. This lets you dynamically calculate values, format or search text, manipulate collections, and more. You can do all this without setting up separate variables. For example, you can insert the current date, clean up messy input, or reference memory tables to ground the prompt with relevant context. Just type “/” or use “+Add content” to bring in a formula. It’s all the flexibility of Power Fx, now right where you need it. Learn more.

We’re also introducing prompt evaluation and testing in prompt builder, now in public preview. You can upload or generate test cases and run them in batches. Choose evaluation types like semantic similarity or JSON match, then review accuracy scores and detailed results. Each test run is saved so you can track performance over time. It’s a simple, scalable way to improve prompt quality without any custom tooling or manual experimentation required. From the prompt list, simply click the “…” menu and choose “Test” to get started. Learn more.

These updates turn the prompt builder into a more powerful end-to-end workspace. Whether you’re creating prompts that drive critical business workflows or experimenting with new agent behaviors, you can now iterate faster, catch issues earlier, and deliver more reliable outcomes with less guesswork. It’s everything you need to go from idea to tested, production-ready prompt, all in one place.

Validate and extract text with Power Fx regular expressions

Parsing and validating text just got a major upgrade in Copilot Studio. You can now use industry-standard regular expressions in Power Fx formulas to match, extract, and work with complex text patterns.

Regular expressions (regex) offer a compact and powerful way to describe how a text pattern should be matched. They allow you to perform text validation and extraction. If your agents rely on pulling out details from user input, like extracting tracking numbers, validating email addresses, or calculating durations from structured text, this update is for you. Makers who work with integrations, dynamic data inputs, or more advanced business logic will especially benefit from the precision and flexibility that Power Fx regular expressions provide.

Before this update, these kinds of tasks required long chains of text functions or limited entity configurations. Now, with support for IsMatch, Match, and MatchAll, you can achieve the same results with less effort. You can even reuse expressions across the Microsoft Power Platform suite.

Regular expressions may seem intimidating if they’re new to you, but the results are powerful. Find full details, syntax tips, and examples on Microsoft Learn. Then, start exploring the many ways Power Fx regular expressions can enhance your agents’ functions and responses. Learn more.

Streamline connections with in-chat single sign-on (SSO)

For users, setting up connections to services used by knowledge, tools, topics, and agent flows is also easier thanks to in-chat single sign-on (SSO), now in preview. When a user needs to access additional services that require credentials during an agent chat, the agent can automatically authenticate those other services. Instead of opening a separate Connection Manager page and jumping between windows, the agent prompts the user with an adaptive card for one-click approval. The agent makes the connection on the user’s behalf and uses that connection to continue responding to the user’s prompt.

Use any Copilot Studio-supported language with generative orchestration

Generative orchestration in Copilot Studio is now available in all Copilot Studio-supported languages beyond English (US). This is a major step toward making advanced AI capabilities accessible to makers and users around the world.

Until now, generative orchestration was only available for agents built in English (en-US). With this update, you can build agents in your preferred language and still take full advantage of features like natural language reasoning, dynamic workflows, and data-aware actions. You can also test and validate orchestration behavior in different languages, helping ensure your agent responses are high quality and contextually accurate across languages before you publish.

If you’re building connected agents, there’s more good news: when a handoff occurs from one agent to another, the orchestrator seamlessly continues the conversation in the user’s language—no additional language configuration is required in the target agent. This makes it easier to scale multilingual solutions without duplicating setup across your connected agent ecosystem.

This update is now in public preview across all regions and languages supported by Copilot Studio. To try it out, simply enable generative orchestration in your agent. You can either set a non-English primary language when creating the agent, or add additional languages via settings once orchestration is turned on. Learn more.

Analyze knowledge use in autonomous agents, insights for unanswered questions

Agent analysis just got more insightful in Copilot Studio thanks to two exciting new features. These insights help you better understand how your agents perform and identify areas where there is room to improve.

Agents with autonomous capabilities (through triggers) have provided run history analytics in the Activity tab. Now, makers can garner additional new insights with knowledge source analysis. This feature, now generally available, lets you see how your autonomous agents and agent flows used the knowledge they’re grounded in during each run. These metrics help you assess relevance, adjust content, and improve performance over time. It’s a valuable new lens into what’s working inside your autonomous agents while they’re working for you.

Makers can also now view where user questions went unanswered. This happens either because the agent didn’t have the knowledge available to identify an appropriate response, or because there was not a topic configured to handle the query. Now, the list of unanswered questions is categorized into themes and conversation contexts. No more combing through old conversations or building more spreadsheets—the Copilot Studio Analytics page automatically highlights patterns and clusters these topics where responses fell short. These insights, found in the Knowledge section on the page, make it easier to close content gaps and continuously refine your agents. This feature is currently in preview and will appear automatically for qualified customers.

These two features help you turn metrics into a data-driven feedback loop. Pinpoint what’s working, where content can improve, and how to make your agents more effective over time. With every run and agent interaction, you can gain deeper actionable insights to help you improve your agent.

Microsoft Power Platform admin center enhancements for admins

Track usage, manage agents, and allocate capacity

As your organization builds more agents in Copilot Studio, keeping track of them and understanding how they’re used becomes increasingly important. With new visibility and management tools in the Power Platform admin center (PPAC), admins can now support agent solutions at scale with far less manual effort.

The new agent inventory view provides admins with a tenant-wide list of all agents built in Copilot Studio. You’ll find key details like agent name, environment, owner, creation date, and status all in one place. No more checking each environment manually or stitching together spreadsheets. This supports smoother lifecycle management and more consistent agent experiences across teams. Learn more.

The new agent usage analytics experience takes this a step further. Admins can now explore tenant-level data that shows how agents are being used across the organization, including usage trends, billing metrics, and a curated list of top agents. It’s a major step forward in tracking usage and enabling cost control practices at the organization level—helping IT teams see what’s working, what’s underused, and where support is needed. Learn more.

Both features are available in the PPAC today for tenant and environment admins in commercial regions. To get started, enable tenant-level analytics in your environment. Then go to the PPAC, select the “New admin center,” and navigate to Manage > Copilot Studio.

Copilot Studio

Transform your organization’s productivity.

Learn more

Stay up to date on all things Copilot Studio

Check out all the updates live as we ship them, as well as new features releasing in the next few months here: What’s new in Microsoft Copilot Studio – Microsoft Copilot Studio | Microsoft Learn.

To learn more about Copilot Studio and how it can transform your organization’s productivity, visit the Copilot Studio website or sign up for our free trial today.

The post What’s new in Copilot Studio: June 2025 appeared first on Microsoft Copilot Blog.

May 2025 was a big month for Microsoft Copilot Studio and there are a ton of features to catch up on. In this edition of our monthly roundup, we’re recapping the biggest news from Microsoft Build 2025, giving a couple of important updates, and announcing new resources for Copilot Studio adoption and training. 

Microsoft Build 2025 roundup: Our biggest announcements

Microsoft Build 2025 brought a wave of updates to Copilot Studio and Microsoft Dataverse, the operational database for agents, introducing powerful new tools for multi-agent systems, enterprise data access, and custom AI tuning. Here’s a quick overview of what dropped in Copilot Studio.

Multi-agent orchestration: Copilot Studio now supports multi-agent orchestration, allowing agents built with Microsoft 365, Microsoft Azure AI, and Microsoft Fabric to collaborate by delegating tasks and sharing results to complete complex workflows. Copilot Studio will also support the open Agent2Agent (A2A) protocol, allowing agents to connect to those built on third-party platforms.

Computer use in agents: The new computer use capability, currently available to eligible United States-based customers, allows Copilot Studio agents to perform tasks across desktop and web applications, automating repetitive processes like data entry and document processing through AI-powered UI interactions.

Bring your own model and Microsoft Copilot tuning: Makers can access more than 11,000 models in Azure AI Foundry and fine-tune them using enterprise data for even more context-rich and valuable agent responses.

Other updates include:

• Model Context Protocol (MCP)’s general availability and updates.
• In-conversation agent recommendations and handoff.
• Code interpreter for Python-powered logic using natural language.
• Instant agent sharing across your organization.
• New maker controls for knowledge, including options for file collections, code interpreter, moderation, and user feedback.
• SharePoint and WhatsApp channels to publish agents to.
• Security and governance updates.

Get all the details on these announcements in Corporate Vice President Lili Cheng’s blog post. For an even more in-depth update, learn more about how Dataverse supports all these in Corporate Vice President Nirav Shah’s blog post from Microsoft Build 2025. You can also see a roundup of all the Microsoft Dataverse sessions presented at Microsoft Build 2025.

Build, publish, and monetize agents with the Agent Store

Welcome to the Agent Store, your centralized, curated marketplace for agents built by Microsoft, trusted partners, and customers. Accessible through the left side navigation in Microsoft 365 Copilot Chat, the Agent Store makes it easier to browse, try out, and share agents for your business processes without having to build them from scratch. These agents work seamlessly across your Microsoft 365 ecosystem, so you can install an agent once and use it in multiple places. It’s all about speed, trust, and impact at scale.

Right now, the Agent Store has more than 70 agents, ranging from knowledge assistants to complex multi-modal orchestrators. You’ll have access to more as makers and software development vendors build and share new agents in the coming months—and the store will offer personalized agent discovery based on your organizational context. For developers, the Agent Store also provides a platform to share your innovative agents with millions of Microsoft Copilot users and grow your user base.

With robust support through Copilot Studio and the Microsoft 365 Agents Toolkit, the Agent Store includes both low-code and pro-code development options. Whichever way you prefer to build and deploy your agents, this marketplace helps you reduce development time and costs and get them out there faster.

Learn more about finding and publishing agents through the Agent Store on the Microsoft 365 Developer Blog.

Publish custom engine agents to Microsoft Copilot Chat: Now generally available

The ability to publish custom engine agents built in Copilot Studio directly to Copilot Chat is now generally available and automatically enabled. This means all customers can now unlock powerful new ways to customize and extend Copilot experiences with rich, domain-specific intelligence, right inside the tools people use every day.

Previously announced in public preview, this feature allows makers to publish agents built in Copilot Studio to Copilot, with full access to the features that make agents intelligent and useful. That includes topics, orchestration selection, autonomous triggers, analytics, and Azure AI integrations. These custom agents surface seamlessly across Microsoft 365 apps, including Microsoft Teams, Word, Excel, PowerPoint, and Office.

Custom engine agents in Copilot support messages, quick replies, Adaptive Cards, multi-turn interactions, and multi-message responses—all backed by robust governance and analytics in the Microsoft Power Platform admin center. Now you can confidently scale custom Copilot experiences across your workforce, without changes to existing agents.

General availability brings simplified deployment and seamless integration, turning every custom agent into a first-class participant in the Microsoft 365 Copilot experience. Read more about publishing and deploying agents on Microsoft Learn.

Microsoft Graph connectors are now Copilot connectors

Microsoft Graph connectors are now called Copilot connectors, a name that better reflects their role in powering the Microsoft 365 Copilot experience.

Copilot connectors bring external data into Microsoft 365 so Copilot and Copilot Studio agents can retrieve, apply reasoning to, and act on knowledge beyond the Microsoft 365 ecosystem. These connectors eliminate the need for duplicative uploads or clunky copy-paste workflows.

For developers and makers, Copilot connectors are the bridge between your existing systems and your AI-powered solutions. Whether you’re supporting sales teams to query customer relationship management (CRM) system records, surfacing insights from product documentation, or building custom agents grounded in real enterprise data, connectors make it possible to create truly contextual and intelligent experiences.

The change in name reflects a broader shift: AI isn’t just reading data anymore—it’s working with it. More than 40 Copilot connectors are already generally available or in public preview, including key sources like Gong, PagerDuty, and Unily, so connect your agents and systems in the Microsoft 365 admin center. Read more about building Copilot connectors on Microsoft Learn.

Accelerate agentic operations with new adoption resources

We’re excited to introduce two new resources designed to help your organization get started with Copilot Studio quickly and effectively. Whether you’re launching your first agent or scaling across teams, these tools are built to simplify the building process and drive measurable impact across your organization.

Microsoft Copilot Studio Adoption page

This centralized hub offers comprehensive guidance for seamless integration across teams. It includes:

• Step-by-step setup and deployment guidance.
• Role-based training for business users, developers and admins.
• Best practices and support documentation.
• Tools to help developers and leaders build and scale agents with confidence.

This page is your go-to destination for enabling success from day one. Explore the Copilot Studio AI Agents Hub.

Copilot Studio scenarios in the Microsoft Scenario Library

Explore 35 new custom agent scenarios across seven functional areas—each designed to showcase real-world value and accelerate adoption. Every scenario includes:

• A clear use case with key performance indicators (KPIs) and key users.
• Agent functionality and flow breakdown.
• Architecture and key considerations.

These resources are crafted to help you unlock the full potential of Copilot Studio—empowering your teams to innovate, automate, and scale with ease.

Free Microsoft Copilot Studio training for Microsoft Power Platform makers

If you or members of your team are already familiar with Microsoft Power Platform, you may be wondering how the skills you have built using Microsoft Power Apps or Microsoft Power Automate translate to the world of agents. Microsoft worked with Shane Young, a Microsoft most valuable player (MVP) of 20 years, as part of a paid collaboration to bring you more than four hours of free, hands-on training on YouTube.

This series of videos will help you get started with Copilot Studio at your own pace so you can walk away with your own agents, ready to use. The training series includes demos, step-by-step builds, and deep dives into product-specific features, broken down into four sections:

1. Introduction and demos (7 videos)
2. How to build a conversational agent (8 videos)
3. How to build an autonomous agent (10 videos)
4. Reusing your Microsoft Power Platform skills (4 videos)

Thousands of Microsoft Power Platform makers have already gone through the training, and we encourage you to spread the word and join in. Start watching or share with your team. You may be the makers who create the next best agent in the Agent Store.

More ways to stay up to date on all things Copilot Studio

Check out all the updates live as we ship them, as well as new features releasing in the next few months.

To learn more about Copilot Studio and how it can transform your organization’s productivity, visit the Copilot Studio website or sign up for our free trial. 

The post What’s new in Copilot Studio: May 2025  appeared first on Microsoft Copilot Blog.

Microsoft Copilot Studio

Transform your organization’s productivity with Copilot Studio.

Try for free

For this edition, we’ll talk about how it’s easier than ever to extend Microsoft 365 Copilot with the new embedded Copilot Studio agent builder. We’ll discuss our new autonomic agentic capabilities, hot off the press from our Microsoft AI Tour in London. And we’ll touch on some of the recent model updates to GPT-4o and knowledge enhancements we’ve made—enabling agents to reason over large, complex files that include media. Last, we’ll cover some of the great admin features announced at the Power Platform Community Conference.

Enable Microsoft 365 Copilot to do more with Copilot agents

Your information workers already use Microsoft Copilot to enhance their day-to-day productivity. You can make Copilot even smarter and personalized by extending it with various specialized agents.

You can grant these agents knowledge by pointing them to your enterprise-specific data in Microsoft Dynamics 365 in SharePoint sites, and in line-of-business systems, using graph connectors or simply uploading files. You can also give agents the ability to take actions like sending emails, updating records, or creating support tickets.

You can create a variety of these agents—each equipped with the knowledge and the skills needed to perform a specific function. Your budget agent understands your purchase policies and can take action to submit a new expense report. Your HR agent can help users answer questions about your employee policies and help resolve tickets. All of these can be added to Copilot, giving it new skills and making it increasingly powerful.

Users can find various pre-published Copilot agents in a new store within Microsoft 365, and they can interact with them with a simple @mention, or by opening a direct chat window. And users can now easily create their own agents with a new, streamlined Copilot Studio experience embedded directly inside Business Chat and SharePoint. Using this experience, any information worker can easily create an agent, simply by describing what it should do with natural language and pointing it to the knowledge it needs. And with a few clicks the agent is ready to interact with or share with others. This functionality is now generally available—read the full announcement here.

New agentic capabilities coming to Copilot Studio

Copilot Studio offers a complete platform for creating, managing, publishing, and sharing agents, combining managed SaaS infrastructure, built-in AI models, a low-code design environment, and access to thousands of prebuilt connectors. And with Copilot Studio, you can create and publish agents to all kinds of channels—not just to Copilot. You can publish your agents to Microsoft Teams and embed them in websites, or mobile apps, or on social media. And now, with new features we’re releasing in broad public preview at Microsoft Ignite 2024, these agents can do more than just interact with users on chat. They can operate autonomously in the background, reacting to events and not just conversation, and shepherding long-running tasks to completion. This takes us from agents that work with you to agents that work for you.

New autonomous triggers. You can now set your agent to listen for an event and provide language model instructions for how you’d like it to behave when the selected event occurs. You can create a vast array of event triggers to activate your agent—from simple events to complex flows powered by Microsoft Power Automate. For example, you could set your agent to run whenever a new row is added in a particular SAP table. Every time this happens, the agent could generate a summary of a case, look up the assigned worker, and send them an email with relevant documents from a knowledge base.

Testing for agentic triggers

You can also review the underlying logic behind the agents’ previous runs in the activity pane—including what happened once it was triggered, the steps it took to follow the instructions you provided, the systems and APIs it called, and the reasoning it used to make specific choices. This visibility offers valuable insights into the agent’s decision-making process and context, while also displaying detailed steps, variables, and outputs to allow you to debug and improve your agents.

Finally, you can also review the previous runs your agent in the activity pane, allowing you to see each time the agent was run, which runs were successful, which ones were not, and why. Similar to chat transcripts, you can use this agent activity log to review and refine your agents.

Learn more about autonomous agents by reading “Unlocking autonomous agent capabilities with Microsoft Copilot Studio”.

Working with large, media rich files as knowledge

Every single month, we’ve added new knowledge capabilities to Copilot Studio—including new connectors, new supported knowledge sources, and various advanced capabilities. In October 2024, we’ve recently added the ability to reason over rich media like images, graphs, and charts in your knowledge sources. Going beyond just text, the system understands how images contribute to the document’s meaning, offering richer, more informed responses. For instance, if you have a diagram showing the assembly of a product or a chart tracking financial data, you can ask Copilot Studio questions, and it will account for the image’s content, positioning, and relevance within the broader document context.

What sets Copilot Studio apart is its holistic approach to document analysis. It doesn’t just examine individual images in isolation; instead, it considers multiple images on a page, how they are arranged, and how they interact with surrounding text or tables. This allows for more nuanced answers, especially in documents where visual relationships are key. This capability helps agents better utilize not just the text component of the page but analyze complex image-rich documents without missing critical details that might be lost without understanding the visual context.

What’s more, you can now upload multiple large, image rich files, each up to 512 MB, as knowledge sources for your custom agents in Copilot Studio. Our underlying knowledge service, powered by Microsoft Dataverse, indexes the uploaded files and generates vector embeddings of the file content. This allows Copilot Studio to deliver semantic results when users ask questions about the file contents. All files are securely stored in Dataverse, benefiting from the robust security and governance controls that apply across all Microsoft Power Platform constructs, providing strict data safety and compliance at every level.

Announcing several admin features for greater control

We’re excited to announce a suite of powerful new admin features in Copilot Studio, built to give administrators greater control, visibility, and security across the organization’s agent deployments. These tools enable fine-tuned data governance, enhanced auditing capabilities, and robust user authentication, providing admins with everything needed to manage agents across their organizations with confidence.

Admins can now enforce data loss prevention (DLP) policies for critical features like knowledge, AppInsights, connectors, actions, and more—all through the Microsoft Power Platform admin center. To strengthen visibility, we’ve released audit logs in Microsoft Purview and Microsoft Sentinel, allowing for real-time monitoring and alerting on agent activity. Additionally, admins can set up agents to run connectors and flows using end-user credentials by default, ensuring secure, user-specific access.

Further enhancing security, we’re introducing support for sensitivity labels on knowledge with SharePoint, displaying sensitivity levels in chats for transparency. End-user authentication can now use Microsoft Entra ID with certificate providers, supporting the Microsoft Secure Future Initiative requirements for more secure agent interactions. Makers will also see security alerts when publishing an agent if secure defaults have been modified, keeping them informed of potential risks.

Rounding out these new features, admins can configure environment routing for safer, more controlled agent development spaces, as well as a welcome message to inform makers of privacy and compliance best practices. Last, with the new inventory feature in Microsoft Fabric (currently in private preview), admins have a comprehensive view of agent assets, enhancing oversight across Copilot deployments. These updates mark a significant leap forward in empowering admins to manage and secure their agent solutions to meet organizational standards.

Learn more about common security questions.

More ways to stay up to date on all things Copilot Studio

Check out all the updates live as we ship them as well as new features releasing in the next few months.

Watch monthly episodes highlighting Copilot Studio news as well as how to feature deep dives in “This Month in Copilot Studio” with Dona Sarkar, Microsoft Principal Cloud Advocate, and Kendra Springer, Principal Group Product Manager with Copilot Studio.

Get started with Copilot Studio today

To learn more about Copilot Studio and how it can transform your organization’s productivity, visit the Copilot Studio website or sign up for our free trial today.

The post What’s new in Copilot Studio: November appeared first on Microsoft Copilot Blog.