In this edition of our monthly roundup, we’re recapping the most exciting new features Microsoft Copilot Studio released in October 2025.

Build and optimize agents

Validate agents at scale with evaluations for automated testing

Agent quality just became significantly easier to measure and improve. With the automated agent evaluation experience, now available in public preview, makers can systematically test and validate their Copilot Studio agents at scale. Instead of running scenarios one by one, they can build and execute evaluation sets directly from the agent or the Test Pane, delivering structured, repeatable insights both before and after publishing.

This new experience offers flexibility in how evaluation sets are created. Makers can upload files with predefined questions and answers, reuse recent Test Pane queries, add cases manually, or instantly generate queries using AI. This approach ensures that test coverage spans organization-specific scenarios while also incorporating AI-suggested questions based on agent metadata and topics, providing a comprehensive view of performance.

Evaluations are powered by a robust grader framework that gives makers control over how accuracy is measured. Options range from strict checks such as Exact Match and Partial/Contains, to semantic comparisons like Similarity and Intent Match, and even AI-powered metrics including relevance, completeness, and groundedness. Each test delivers clear pass/fail results, detailed scores, and drill-down views into the knowledge and topics used.

For cases where reference answers are critical, makers can define expected responses manually or upload them in bulk, ensuring evaluations remain precise, transparent, and aligned with business expectations. AI further the Analytics tab in Copilot Studio accelerates validation by automatically generating test sets that can be executed immediately with AI metrics graders or combined with manual and uploaded sets for broader coverage.

These capabilities introduce a scalable, repeatable framework for agent quality, helping teams identify gaps early, reduce surprises in production, and track improvements over time. While multi-turn testing and additional graders are on the roadmap, this public preview represents a major leap forward in automated validation. 

Evaluations are available now in public preview. You can access them from the agent or test pane by selecting Evaluation.

Build with the latest OpenAI models in Copilot Studio

Copilot Studio continues to evolve with new model updates that improve performance and expand flexibility for makers. Depending on use case and application, different models may provide better responses to users. We’re committed to providing model choices that work for your business processes.

Starting October 27, 2025, GPT-4.1 became the default model for all newly created agents, replacing GPT-4o. Testing shows meaningful gains in both latency and response quality, helping agents deliver faster, more consistent results. GPT-4o will remain available through November 26, 2025, and agents in production will continue to leverage this model until then. However, you can update the model and opt in to GPT-4.1 today through the model-selection experience.

In addition, Copilot Studio is expanding availability of the GPT-5 family of models, first introduced in August 2025. Makers can now use GPT-5 Auto, GPT-5 Chat, and GPT-5 Reasoning not only in test environments but also in deployed agents. These models bring enhanced reasoning, richer dialogue capabilities, and more flexible problem-solving for complex scenarios. Please note that GPT-5 models remain in public preview and are not yet recommended for production use.

Together, these updates give makers access to the latest OpenAI advancements while maintaining continuity for existing agents. You continue to have top model choice at your fingertips to help create and deploy more accurate and effective agents at scale.

Speed up agent flow execution with express mode

Flow execution just got faster in Copilot Studio. Express mode, now in preview, optimizes agent flows to increase the likelihood that they’ll finish the flow within two minutes. This avoids agents or apps timing out while they wait for a response.

Express mode works best in flows that are logic-heavy but data-light. It limits flows to under 100 actions and smaller payloads so that the entire execution is more streamlined. For scenarios where large data sets needs to be moved or loops occur to iterate over large arrays, makers should test both with and without express mode.

This feature is in public preview and on by default. You can find the express mode toggle located on the flow’s Overview page in the editor.

Enable file uploads in omnichannel conversations

Copilot Studio now supports file uploads for custom agents in omnichannel scenarios. This means users can share images, documents, and other supported file types directly during agent interactions. This enhancement makes conversations more dynamic and context-rich by letting customers provide relevant files like receipts, forms, or photos right in the chat.

By enabling end user file uploads, agents can analyze attachments in real-time and deliver more accurate, personalized responses. This is a critical capability for customer service and contact center scenarios, where exchanging documents or screenshots is often key to resolving issues quickly. The feature also unlocks richer use cases for image analysis and document-based reasoning, improving both response quality and customer satisfaction.

File upload support is enabled by default for omnichannel custom agents, with optional controls available for agent makers to restrict supported file types in the agent manifest. All file types supported by Microsoft 365 Copilot are allowed up to 5MB (unless admins add restrictions).

This update enhances both the maker and end-user experience, and brings a richer more comprehensive level of service for end users relying on the agent for support.

Access external files and data with Model Context Protocol resources

Copilot Studio now supports Model Context Protocol (MCP) resources, expanding what agents can do with existing MCP connections. Makers have been able to use MCP tools to trigger actions and retrieve information. Now with resources support in preview, agents can read external content like files, API responses, or database records directly through MCP. This brings richer, real-time context into every interaction.

MCP resources act as file-like data objects that agents can query and reference during conversations. This allows agents to access customer-specific or system-specific content dynamically, without manual updates or re-training. For example, an agent could read the latest policy document stored in an MCP resource, summarize an uploaded file, or use current data from an API—securely and in context.

This enhancement builds upon the existing MCP integration in Copilot Studio, supporting deeper connections between agents and the systems they support. MCP resources are available now in public preview and are on by default for supported environments.

Measure and improve performance

Measure the return on investment (ROI) for conversational agents

Organizations can now view the ROI of conversational agents in Copilot Studio to calculate how much time and money the agent saves compared to other methods. Already available for autonomous agents, this enhancement, now generally available, gives teams a unified view of how all agent types drive direct business impact.

From the Analytics tab, makers can configure savings settings for each agent. This is where you define how much time or cost is saved per interaction or workflow. Copilot Studio then aggregates these metrics automatically. The resulting ongoing view helps quantify the business value agents deliver through reduced manual effort, faster resolutions, or process efficiencies.

By expanding savings analytics to include conversational agents, Copilot Studio helps organizations evaluate agent performance and impact consistently across their agent portfolio. With this capability, right inside the Analytics tab in Copilot Studio, makers can make data-driven decisions about where to invest and improve.

Analyze user questions by theme

Copilot Studio now helps makers understand agent performance by intelligently and automatically grouping user questions into themes. The themes give you category-level insights into customer intent and frequent topics, with a more manageable number of groups.

In the Themes list, you can see key metrics such as question volume, response rate, and user satisfaction. This at-a-glance overview makes it easier to see which topics your agent handles well and focus on areas where it may need refinement. Makers with the appropriate permissions can also drill down into each theme to review specific user questions, agent responses, and related metrics. This deeper visibility helps identify patterns in user intent, uncover gaps in coverage, and guide targeted improvements to knowledge and content.

The feature is automatically available for agents that use generative answers and have received at least 50 user questions within the past seven days. Once enabled, insights appear directly in the analytics dashboard, no further setup is required.

By organizing user questions into themes, Copilot Studio gives makers a clearer view of what customers are asking for and how effectively agents are responding. This helps the team continuously improve agent responses for their customers by making data backed improvements to their knowledge sources.

Test and debug faster with an improved activity map

Test and troubleshoot Copilot Studio agents faster and more intuitively, thanks to a series of updates to the activity map and testing experience. These enhancements create a more cohesive view of how agents reason over data and user queries to respond. That, in turn, helps makers debug efficiently and refine performance with less context switching.

Makers can now view the transcript and activity details together, eliminating the need to toggle between separate views. This unified view provides a clearer picture of how each session unfolds, drawing from user input through the agent’s reasoning and response generation. The updated layout also lets makers pin sessions, adjust visible columns, and submit feedback on session details directly to Microsoft—improving collaboration and visibility.

It is now easier then ever to navigate activity data, understand the agent’s chain of thought, and connect analytics insights to individual sessions for deeper evaluation. These enhancements are generally available, with continued refinements releasing progressively across environments.

Manage and govern at scale

Control org-wide sharing of agents in Copilot Studio lite

A new admin control in the Microsoft 365 Admin Center, now generally available, gives organizations stronger governance over how agents created in Microsoft 365 Copilot are shared across the tenant. Admins can now restrict or disable organization-wide sharing of agents built in Copilot Studio lite (formerly known as the agent builder). This ability helps prevent oversharing while supporting safe adoption at scale.

From within the Microsoft 365 Admin Center go to Copilot > Settings > Data Access > Agents page, admins can choose who is allowed to share agents with the entire organization: all users (default), no users, or specific users and groups. When you place restrictions on sharing, the “Anyone in your organization” option in the agent-sharing dialog is disabled. Makers can see a tooltip explaining the policy. Existing access remains unchanged, but makers must comply with the defined settings before updating or broadening sharing.

This control helps ensure that agent collaboration aligns with organizational policies and regulatory requirements. This is particularly important for organizations in spaces like finance, healthcare, and government. By bringing this configuration directly into the Microsoft 365 Admin Center, admins can manage agent governance alongside other Microsoft Copilot and AI settings, simplifying oversight and reducing risk.

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: October 2025 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 consumption. 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 consumption 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 consumption 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.

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

Copilot Studio new features and enhancements

Configure advanced natural language understanding natively in Copilot Studio

Natural language understanding (NLU) is what makes conversations in Copilot Studio feel intuitive, personalized, and less robotic. With the new NLU+ option, makers can now train high-accuracy models directly in Copilot Studio—no external services or extra setup required.

NLU+ is designed for agent applications with lots of conversations where understanding the user’s meaning and intent are critical, such as customer care centers. You can define a large number of custom topics, entities, and annotated examples to fine-tune how your agent interprets user intent. Because NLU+ uses a grammar-based model, it delivers predictable, repeatable results that match what you’ve trained the model on.

You can also extend your models with synonyms and entity items to improve recognition and routing, especially in complex or high-volume scenarios. This even improves speech recognition for voice-enabled agents. Whether you’re supporting customer service, internal operations, or global deployments, NLU+ helps your agent understand more and miss less.

To get started with NLU+, all you need is a Dynamics 365 Contact Center license. In that environment, head to Settings > Natural Language and select NLU+ as your orchestration engine. From there, you can upload your data, annotate it, train your model, and test it, all within the same intuitive interface.

Enrich custom agents in Microsoft Copilot Studio with insights from Fabric data agents

Bring your most trusted data into every conversation with the new Microsoft Fabric data agents integration in Copilot Studio. Fabric data agents are AI assistants that connect directly to your Microsoft OneLake data, automatically understanding schemas, enforcing your governance policies, and interpreting business context to deliver timely, relevant insights. Rather than switching between analytics tools and chat, makers can now embed these agents into Copilot Studio and surface that data natively.

Unlike standard knowledge grounding, where agents fetch static documents or search hits, Fabric data agents plug directly into your OneLake analytics layer for near-real‑time, governed answers. A user could ask a support agent for last night’s sales trends by region and receive an up‑to‑the‑minute summary that respects the organization’s sensitivity labels and shows exactly where each number came from.

Behind the scenes, Fabric data agents leverage Model Context Protocols, which allow them to collaborate across multiple agents and services and stitch together richer, more complete responses. One agent might pull fresh inventory forecasts, while another layers on compliance checks, all in the same conversational flow. This helps support an ecosystem of intelligent, connected agents that make your workflows more scalable.

By embedding near-real-time analytics, governance, and collaboration, Fabric data agents help your users accelerate innovation, maintain data consistency, and make informed decisions—in the Copilot Studio channels where they already work.

Search and jump to any element in your agent

Ever spent several minutes searching for a particular node, tool, or topic for your agents? Copilot Studio’s new in‑agent search feature puts an end to the scavenger hunt. Simply click the search icon (or press Ctrl+J/ ⌘+J for a shortcut) and start typing a component’s name, description, or keyword.

Whether you’re hunting for a specific topic node, custom variable, knowledge source, message, or connector, the search box quickly surfaces matching items. You can apply filters to narrow down search results by type: tools, skills, topics, knowledge sources, and more. Click any result to jump straight to the configuration page.

In-agent search and filtering also helps you navigate within your agent, digging up specific messages, nodes, formulas, or variables. When you see the element you want, clicking it sends you directly to the page where you created or used the element.

This feature is especially helpful in complex agent ecosystems, where you may have dozens of similarly named tools or nodes that can make updates tricky or time‑consuming. Now, you’ll spend seconds, not minutes, locating the exact element you need, freeing you to focus on refining logic and improving user experiences. In-agent search is generally available worldwide.

Enact end‑to‑end data labeling for secure agent interactions

Keeping sensitive data under control is imperative—but we believe data protection can go hand in hand with your AI initiatives. With the new Dataverse connector for Microsoft Purview Data Map (now generally available), you can automatically discover and catalog your Dataverse tables, fields, and relationships in Microsoft Purview, enriching your data map with metadata and lineage at the click of a button.

But discovery is only the first step. Now in preview, autolabel for Dataverse brings Microsoft Information Protection (MIP) policies directly to your data layer. Personally identifiable information (PII), financial records, and any other classified fields get tagged automatically, so you no longer need to build manual labeling workflows or custom scripts.

Once your data is labeled, Copilot Studio’s labeled experiences (also in preview) help ensure your agents honor those classifications in real time. During test chats, Teams, or Microsoft 365 Copilot sessions, any content marked sensitive by Purview will be masked or blocked according to your MIP rules. Doing so prevents your agents from accidentally oversharing confidential information.

Automatic discovery, classification, and enforcement: together, these features contribute to the seamless, policy‑driven approach to data governance Copilot Studio strives to provide. Turn them on today and continue building trust—with your customers and your IT department—with every interaction.

Admin center enhancements

Manage per‑agent message capacity in the Power Platform admin center

Unpredictable message consumption can cause surprise costs or resource constraints if not managed closely. As part of Microsoft’s comprehensive agent cost management approach, new per‑agent capacity limits in the Power Platform admin center (PPAC) let you earmark a dedicated slice of your prepaid message pack for specific Copilot Studio agents.

How does it work? In PPAC, assign a fixed share of your prepaid message pack—either as a percentage or a specific message count—to each agent. Real‑time usage meters at the agent and tenant levels give you clear visibility into consumption trends. This helps you set message budgets, monitor spend, and avoid surprise overages without building custom scripts or external reports.

This feature helps you ensure your mission-critical agents, like customer support or sales assistants, have the capacity they need, even during peak traffic times. If a lower-priority agent hits its limit, it gracefully switches to your defined fallback behavior. This helps you automatically preserve capacity for your most important workflows, no matter what else is happening across your business.

Manage every agent from a single, scalable interface in the Microsoft 365 admin center

As organizations expand their use of Microsoft 365 Copilot and Copilot Studio, admins need a more intuitive, all-encompassing tool to govern agent usage. The new Agents & connectors page, now generally available in the Microsoft 365 Admin Center, delivers exactly that: a centralized dashboard where you can see all your agents at a glance, from Microsoft‑built and third‑party agents to line‑of‑business and shared custom agents.

From this centralized view, admins can filter by metadata such as sensitivity labels, embedded file details (such as filename or container ID), or owner information. Assign and monitor MIP labels at the agent level to help ensure sensitive content is handled correctly and configure connector behaviors to control how data flows between Copilot and your systems. AI‑powered recommendations surface optimization opportunities, helping you streamline performance and resource usage across your entire agent ecosystem.

When it’s time to audit or share insights, you can export detailed agent inventories in seconds. The page also highlights orphaned agents across Copilot Studio, the Microsoft 365 Agents Toolkit, and the embedded agent builder. Then you can easily block or delete any agents that are no longer secure or needed, heading off potential security and governance issues.

As adoption continues to scale, these capabilities help your organization stay in control—reducing risk, streamlining oversight, and enabling Copilot to be used safely and strategically across the business.

Quarantine agents instantly with the Power Platform API

Trust is foundational to the Copilot Studio user experience. The new agent quarantine API function gives security teams one more reason to feel confident. Admins can now programmatically block or unblock any Copilot Studio agent in seconds, isolating it from users and data while an issue is investigated.

This capability closes a critical governance gap. Before, there was no “big red button” to halt a compromised or non-compliant agent, so some organizations restricted agent creation altogether. Now, IT and CISOs can enable innovation while maintaining strict control, aligning with incident-response and data-subject-request (DSR) policies across ISO, SOC 2, and other compliance frameworks.

The quarantine operation is available today in all regions as part of the Power Platform API suite. Simply call the endpoint from your existing admin scripts or security tooling to place an agent in—or release it from—quarantine. It’s a lightweight addition that delivers heavyweight peace of mind.

Analytics enhancements

Analyze ROI and user feedback with new analytics features

Learning from your agents’ successes (and failures) and your users’ feedback is crucial in continuing to develop your agentic ecosystem. This is especially true for agents with greater responsibilities—the ones that can autonomously handle tasks for you through triggers. That is why we’re excited to announce new analytics features, designed to help you understand the impact your agents have on both your business and your end users.

With the ROI analysis feature, you can now track estimated time and cost savings for each autonomous run or action. These savings are based on the parameters you provide when you first set up the event trigger. Simply enter your organization’s per‑run or per‑action savings (for example, “5 minutes saved per invoice processed” or “$2 cost avoided per support ticket”), and Copilot Studio will calculate cumulative hours and dollars saved over time. Quickly drill into individual agent runs to see which actions deliver the greatest impact, or view aggregate metrics by agent and date range.

Users have long been able to leave a thumbs-up or thumbs-down reaction to an agent response. Now, reaction counts pair up with any user comments in a single view so makers can read exactly why a response delighted or frustrated someone. Being able to access user comments means a better understanding of customer feedback. That, in turn, empowers you to identify pain points, validate improvements, and continuously refine both your autonomous workflows and conversational experiences.

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: July 2025 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.

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.

Power Virtual Agents sessions 

• Vision of the Future of Bots and Bot Building 
• What’s New and Coming for Power Virtual Agents
• Best Practices Around Conversational AI Design Principles (How to Build Engaging Bots) 
• Bot Meets Knowledge Base – Secure and Intelligent Chat Bot with GPT in Power Virtual Agents 
• Unlocking the Power of Chatbots: An Introduction to Power Virtual Agents! 
• Bot Authoring Deep Dive – Advanced Bot Building Concepts 
• Power Platform Architecture Internals  
• Power Platform and Azure: Better Together 
• Transforming Bot Building Using Generative Actions 
• Unleash the Power of Virtual Agents! 
• An Espresso Shot of Being a Power Platform Admin and the Tools 
• Unlock the Power of Power Virtual Agents with Power Automate 

And more! 

Featured Power Virtual Agents speakers 

• Omar Aftab (Vice President for Conversational AI | Microsoft)
• Kendra Springer (Principal Design Lead for Power Virtual Agents and Conversational AI | Microsoft) 
• Bas Brekelmas (Partner Architect, Power Virtual Agents | Microsoft)  
• Gary Pretty (Principal Product Manager, Power Virtual Agents | Microsoft) 
• Dewain Robinson (Principal Program Manager | Microsoft) 
• Henry Jammes (Principal Program Manager, Power CAT | Microsoft) 
• Jack Rowbotham (Senior Product Marketing Manager | Microsoft) 
• Uday Adhikari (Power Platform Lead – North America | Accenture)  
• Dian Taylor (Dynamics 365 Goddess | RSM) 
• Laura Rogers (Microsoft MVP | CEO | IW Mentor) 

Don’t delay—sign up for the Microsoft Power Platform Conference today—we can’t wait to see you in Las Vegas! 
Click here to register: https://aka.ms/MPPC23/Agents/Register 
Click here for hotel reservations: https://aka.ms/MPPC23/Agents/Hotel 
 
 

The post Join us at the second Power Platform Conference this October in Las Vegas appeared first on Microsoft Copilot Blog.