At the center of the latest Copilot Studio updates is the general availability of the GitHub Copilot harness, the new foundation for building reasoning-heavy agents and workflows in Copilot Studio. Alongside the harness, recent updates add new ways for agents to use skills, memory, enterprise knowledge, workflows, model context protocol (MCP) servers, connected agents, files, and more.

Build agents and workflows for complex business processes with the GitHub Copilot harness

The GitHub Copilot harness is now generally available in Copilot Studio. This advanced harness is designed for reasoning-heavy agents and workflows that need to complete complex business processes.

The harness sits between the AI model and the agent or workflow you build, orchestrating how the components work together. It helps determine when to call the model, what context to provide, and which tools, MCP servers, or connected agents to use. This allows agents and workflows to plan steps and adapt their approach as they work toward the defined goal in a recursive manner. Basically, rather than relying on predefined paths, the agent or workflow can adjust its execution path based on the goal and the available inputs.

The harness also supports capabilities like skills and memory (see next section) and can natively create and edit Word, Excel, PowerPoint, and PDF files. Each task runs in a secure sandbox governed by Copilot Studio.

All this makes the GitHub Copilot harness particularly well suited for scenarios that combine reasoning with action across multiple steps. For example, an accounts payable agent could read invoices, match them to purchase orders, gather missing information, and route exceptions for approval.

The GitHub Copilot harness is available alongside the standard harness, so you can choose the foundation that best fits what you’re building. Learn more about choosing a harness.

Expand what your agents can do with skills, tools, and connected agents

The most useful agents can do more than answer questions. New capabilities for agents powered by the GitHub Copilot harness give you more ways to equip agents for the work you want them to perform:

• Skills let you package instructions into modular, reusable capabilities. Write a skill or upload an existing skill, add it to multiple agents, and share it with your teammates. This feature helps teams reuse proven approaches instead of rebuilding the same capability for every agent.
• For larger solutions, connected agents (in preview) let a primary agent delegate requests to specialized agents. This can help you create modular agent architectures where one agent serves as the front door and calls specialists for particular tasks.
• Now in generally available, you can also add workflows and MCP servers as tools. Workflows can give agents access to multistep deterministic automation, while MCP servers can connect them to external services and capabilities.
• With the Windows 365 for Agents MCP server, now generally available, agents can interact with a Windows 365 Cloud PC to work with desktop applications, browsers, and user interfaces.

The goal with these capabilities is to help teams move from building isolated agents to creating reusable, extensible agent solutions. Being able to build on proven components and specialized capabilities means complex agents are easier to develop, maintain, and scale across the organization.

Give agents richer context with knowledge, memory, and files

The right context can help an agent deliver more relevant responses and take more appropriate actions as it works.

With Work IQ in Copilot Studio (preview), agents powered by the GitHub Copilot harness can connect to organizational context such as emails, calendar events, files, Microsoft Teams messages, and people information. You can also connect an agent to Foundry IQ to use a knowledge base you’ve already built and tuned in Microsoft Foundry.

Memory (also in preview) adds another source of context by allowing an agent to retain relevant information from previous interactions with an individual user. When enabled, memory can capture preferences and patterns and apply them in later conversations, helping you build experiences that become more relevant over time.

Agents can also take on larger, more complex document-based work. Now in preview, users can give agents files to analyze and work with directly, unlocking scenarios that require agents to reason over substantial documents and use what they find to complete a broader task. Users can also view files the agent creates during the conversation.

These capabilities all help agents work with a deeper understanding of the organization, the task, and the individual user. That richer context can reduce the need for users to repeatedly supply information and help agents not only deliver more relevant responses, but support more complex, ongoing work.

Manage agents with greater visibility and control

New Copilot Studio capabilities give administrators more ways to manage agents within their existing security and governance practices. Recent updates strengthen agent-level identity, expand environment-level observability, and add new trust signals for MCP servers.

First, as of July 2026, Copilot Studio automatically creates a Microsoft Entra Agent ID for every new agent. This gives individual agents their own identity in Microsoft Entra and helps administrators apply identity and access controls at the agent level.

For agents using MCP servers, you can also now submit an MCP server for Microsoft certification. Certification provides customers and administrators with additional information that an MCP server has been evaluated against Microsoft expectations for areas including reliability, security, compliance, and responsible operation.

Finally, with environment-level agent telemetry, now in preview, administrators can export telemetry from Copilot Studio to Application Insights through the Microsoft Power Platform admin center. Use this feature to validate agent runs, monitor tool execution, create alerts, and build custom dashboards for operational analysis.

Together, these updates help organizations treat agents as governed enterprise assets, with clearer identity, trusted connections, and the operational insight administrators need to manage them confidently at scale.

Reach customers across voice and digital channels with real-time agents

Real-time agents are expanding capabilities and channels. You now have new options for where you deploy them, how you customize voice experiences, and how you monitor performance.

Previously available for voice experiences, real-time agents can now also be deployed to digital messaging channels. Currently in preview, this feature allows you to use the same agent configuration across voice and digital messaging to create more consistent, context-aware customer experiences without maintaining separate agents for each channel.

For voice experiences, you can now use GPT-5 Chat. The model, also in preview, uses a text-based voice architecture that converts speech to text, generates a response, and synthesizes it back to speech. This enables advanced voice customization with neural text to speech, as well as greater deployment flexibility.

Finally, you can monitor real-time agents with Application Insights in Azure Monitor, which gives you more visibility into agent performance and helps you identify and troubleshoot issues.

Learn more about real-time agents and best practices for managing them at scale.

More improvements to help you build

A few more Copilot Studio updates help make everyday agent authoring more flexible:

• Choose from more models. Claude Sonnet 5 and GPT-5.5 Chat are now generally available as primary models, giving you more options to match model capabilities to your agent scenario.
• Build with the right foundation for the job. With multiple harness options available in Copilot Studio, you can choose between reasoning-heavy, multi-step experiences and more structured, predictable agent scenarios based on what you need to build.

The latest Copilot Studio updates give makers more building blocks for agents that can reason, act, collaborate, and work with richer context—while giving organizations more ways to manage those capabilities as their agent ecosystems grow.

What comes next

The significance of these updates goes beyond any single feature. Copilot Studio now has more of the building blocks needed for agents to take on consequential business processes: stronger reasoning, reusable capabilities, richer context, more ways to act, and enterprise controls to support them.

That opens the door to a much broader range of agent use cases. As makers begin combining these capabilities in new ways, the question is shifting from what an agent can do toward what work an organization is ready to give it.

Stay up to date on all things Copilot Studio

More is coming across voice channels, workflows, and the building experience. Check out all the updates as we ship them, as well as new features releasing in the next few months here: What’s new in Microsoft Copilot Studio.

Reimagine business processes

Discover how AI agents can help your organization work smarter and move faster.

Explore Copilot Studio

The post New and improved: GitHub Copilot harness, agent skills, and richer context appeared first on Microsoft Copilot Blog.

Expectations for agents are changing quickly. Teams want to move beyond conversational experiences to systems that can help get work done by interacting with applications, executing workflows, collaborating across tools, and supporting customers more naturally across channels.

But getting there can be tough. Many organizations are still balancing modern, real-time AI experiences with older systems and processes that were never designed to work together. That can leave teams stuck maintaining brittle automations, disconnected processes, and rigid customer interactions that are difficult to evolve. New updates in Microsoft Copilot Studio focus on helping organizations achieve more connected, adaptive automation systems—structured where needed and adaptive where valuable.

Computer use and workflows: Adapt automation to your team’s real work

Traditional automation works best in predictable environments. But many real business processes are anything but predictable. Interfaces change. Vendor portals update unexpectedly. Legacy systems lack APIs entirely. As a result, even relatively simple processes can require constant maintenance just to keep automations running reliably.

That’s the kind of gap computer-using agents are designed to help close.

Computer-using agents are now generally available

With computer-using agents now generally available in Copilot Studio, organizations can build agents that interact directly with websites and desktop applications through the user interface (UI). This helps you automate processes that previously relied on brittle scripts or manual workarounds because the underlying systems lacked APIs.

With the new release also comes new enterprise-ready capabilities designed to help you operationalize UI automation more confidently. Organizations can now manage credentials more securely, choose models best suited for different automation scenarios, and build more resilient automations that can adapt to changing interfaces instead of breaking whenever a screen or webpage changes.

In addition, organizations can now embed computer-using agents directly into multi-step workflows. This feature, now moving into preview, further helps teams combine API-based actions, approvals, business logic, and adaptive UI interactions within the same automation system.

But adaptability automation still needs structure. As organizations scale beyond isolated automations, teams need a way to orchestrate all these in a way that’s easier to understand, maintain, and evolve over time.

That’s where the new workflows experience in Copilot Studio comes in.

A simpler, more intuitive way to build powerful workflows

Now available in early release environments, the redesigned workflows experience introduces a more intuitive visual designer for building and orchestrating agentic automation in one place. Instead of stitching together disconnected tools and logic across multiple surfaces, you can design workflows end-to-end on a unified canvas. This helps you more clearly see how actions, decisions, and AI-powered steps work together across a business process.

A core component of the new experience is the ability to add existing agents directly into workflows. These agent nodes allow you to create automated solutions that keep the scalable reliability of workflows while bringing in AI intelligence when you need it. For example, when a workflow hits a decision that can’t be captured in simple if-then logic—where it needs to use reasoning over context, orchestrate tools, or retrieve knowledge from multiple sources—an agent node can help bridge the gap and make your workflow more effective.

The new designer also helps reduce friction for teams building and maintaining these systems. Inline configuration, simplified building blocks, and node-level testing help validate workflow behavior earlier and iterate more quickly. In addition to agent nodes, AI-powered actions like classification, content generation, and decision support can now be incorporated directly into the workflow.

Together, these updates help organizations combine deterministic orchestration with adaptive execution—structured where needed, adaptive where valuable.

How Graebel combines flows and computer-using agents

Graebel, a global leader in talent mobility, processes thousands of employee relocation requests each year. Most of these come in as unstructured emails filled with unique instructions, attachments, and edge cases. Because Graebel’s proprietary Global Connect platform lacked API support, earlier automation efforts proved too rigid to keep up with the variability of real-world requests. That meant lots of manual input and handoffs—which automation was supposed to solve. Basically, Graebel needed automation that could use reasoning, not just click.

Working with GET AI and Microsoft, Graebel built the Graebel Service Order Agent in Copilot Studio using computer use capabilities to help automate the process end to end. The agent can interpret incoming emails, validate requests against business rules, operate Global Connect directly through the UI, and escalate exceptions through workflows when needed.

By adopting Microsoft Copilot Studio and AI agents, we’ve moved beyond traditional automation to a more intelligent, scalable operating model. This initiative strengthens our ability to serve clients faster and more accurately while positioning Graebel for long-term growth.

—Matt Brownlee, Chief Revenue Officer, Graebel

The Service Order Agent is live today and designed to scale across more than 30 relocation service categories. So far, results include a meaningful reduction in manual effort, faster service-order turnaround, more consistent data quality, and a repeatable blueprint for bringing intelligent automation to the rest of their operations.

Connect intelligent automation systems with Work IQ and interoperable agents

As automation systems become more adaptive, another challenge quickly emerges: connection. Even the most capable agent can only go so far if it operates in isolation. Many organizations are still navigating fragmented ecosystems where agents, workflows, APIs, and external tools all function separately. This naturally makes it difficult to share context or complete work across systems without custom integration effort.

This fragmentation—which is very common—slows adoption and makes it harder to scale intelligent automation beyond isolated pilots.

Now, new interoperability and extensibility capabilities in Work IQ help organizations build more connected agent systems—making it easier for agents, workflows, and enterprise tools to operate together across environments.

With the new Work IQ REST API and command-line interface (CLI) capabilities, teams can integrate Work IQ more flexibly into existing operational and development workflows. Support for remote model context protocol (MCP) servers also introduces a more standardized way to connect agents with tools, services, and enterprise resources. This reduces the need for one-off integrations across growing agent ecosystems.

And as organizations deploy more specialized agents across departments and business processes, coordination between those agents becomes increasingly important. With agent-to-agent (A2A) communication now generally available in Copilot Studio, agents can exchange information, delegate tasks, and be set up to work together more effectively across systems and workflows.

Together, these updates continue the shift from isolated AI experiences toward connected operational platforms—where workflows, agents, APIs, and enterprise systems can be designed to collaborate more naturally across the organization.

Learn more about these new Work IQ interoperability and extensibility updates.

Bring more natural, responsive experiences to customer voice interactions

For many organizations, voice support is still one of the most difficult channels to modernize. Customers get stuck in rigid phone trees, repeat information multiple times, or lose context entirely when they’re transferred to a live agent. Meanwhile, service teams are under pressure to handle growing call volumes without sacrificing customer experience.

Copilot Studio is helping organizations move beyond those limitations with real-time voice agents, now generally available in North America through Dynamics 365 Contact Center. These capabilities help organizations build more natural voice experiences that can identify callers, answer questions, take action during conversations, and transition customers to live agents while preserving context.

Support for speech-to-speech (S2S) voice experiences also makes it easier to connect voice agents into existing customer service and operational systems.

Now, as voice agents become part of real customer interactions, governance and operational readiness become increasingly important. A poor escalation experience, missing context during handoff, or lack of monitoring can quickly become a customer trust issue—not just a technical issue.

That’s why we’re also sharing a new in-depth voice agent governance guide. It covers practical considerations for scaling customer-facing and real-time voice agents responsibly, including escalation testing, monitoring, security, compliance, and operational readiness.

Learn more about real-time voice agents in Copilot Studio and explore the new governance guidance for customer-facing voice agents.

What else is new and improved in Copilot Studio

• A new orchestration layer in Copilot Studio improves how agents execute business processes with greater accuracy and efficiency. Built on an upgraded AI stack, it has demonstrated measurable gains—improving evaluation performance by approximately 20% while decreasing net token usage by 50%—so agents can complete tasks more reliably and cost-effectively.¹ By strengthening tool orchestration and execution quality, the new orchestrator helps ensure more consistent outcomes across complex, multi-step business processes. The result is faster, more dependable automation that scales across enterprise scenarios. This feature is currently in early release environments, where it applies automatically.
• Agent lifecycle visibility updates help the whole team understand an agent’s approval and publishing status. Agent creators can more easily understand whether an agent is still generating, ready for testing, successfully published, or encountering issues, which reduces guesswork during development and iteration. For IT and platform teams managing agents across environments, clearer publishing and status visibility can make it easier to identify stalled deployments, troubleshoot operational issues, and maintain better oversight as agent programs scale.

All together, these updates are focused on helping teams solve the kinds of problems that slow automation efforts down in the real world: workflows that break when systems change, disconnected tools that create extra manual work, and customer experiences that still feel rigid or fragmented.

With new investments across computer-using agents, workflows, interoperability, and real-time voice, Copilot Studio continues to expand as the agentic platform for building agents, apps, and workflows. The goal is simple: help organizations build systems that are easier to connect, easier to adapt, and easier to operate at scale—without losing the structure, visibility, and governance enterprise teams depend on.

Stay up to date on all things Copilot Studio

More is coming across voice channels, workflows, and the building experience. Check out all the updates 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 productivity within your organization, visit the Copilot Studio website or sign up for our free trial today.

Take your automation further

Design adaptive AI systems that integrate across tools and workflows to help teams get meaningful work done.

Try Copilot Studio today

¹ Source: Microsoft usage data, 2026.

The post New and improved: Computer-using agents, a new workflows experience, and real-time voice experiences appeared first on Microsoft Copilot Blog.

As organizations scale their use of AI agents, IT teams face a familiar challenge: how do you expand automation without losing control? Individual agents can be powerful, but as they connect through workflows and integrate across systems, requirements for visibility, governance, and predictability become much more complex. And capability must be grounded in confidence.

The April 2026 updates in Microsoft Copilot Studio focus on building that confidence across the platform. From increasing visibility and governance for admins to expanding intelligent workflow capabilities, these features help you move from isolated automation to connected, reliable systems.

Build and scale agents with better visibility and control

As agents expand across organizations and business processes, admins need clear visibility into how they’re performing, how they’re secured, and what they’ll cost to run. These updates help you manage agents more effectively without adding more friction—or risk.

See agent performance and status more clearly

Copilot Studio now surfaces agent status directly in the authoring experience, giving you immediate insight into each agent’s security and protection posture. You can quickly identify issues like authentication gaps or policy impacts and investigate them at the source. This helps reduce guesswork and speed up resolution.

As you gain clearer visibility into agent performance, you can also share those insights more safely. The Analytics Viewer role, now generally available, introduces read-only access to an agent’s Analytics page.

The Analytics Viewer role allows us to provide meaningful performance insights to business and operational stakeholders while maintaining strict production governance. It cleanly separates operational visibility from agent configuration and publishing rights.

—Mohamed Arhab, Solution Architect, City of Montreal

Allowing analysts and stakeholders to monitor performance, without giving them the ability to modify the agent, helps resolve a long-standing tradeoff between visibility and control. Now it’s easier to share insights broadly while maintaining clear separation of responsibilities.

Speaking of extending visibility and control, there’s more good news: Microsoft Agent 365 is now generally available. Agent 365 is the centralized control plane for managing agents across your environment. This brings together visibility into agent inventory, permissions, behavior, and activity in one place so that you can monitor and govern agents consistently, not just where they’re built.

For Copilot Studio customers, this means the agents you create can be managed alongside agents from Microsoft 365 and partner ecosystems, with shared policies, security controls, and lifecycle oversight. As Agent 365 continues to expand its integrations and multi-agent capabilities, it further strengthens Copilot Studio’s role as the place where agents are built—while governance scales across the full system. Learn more about Agent 365.

Plan and scale with clearer cost visibility

The expanded agent usage estimator now includes Dynamics 365 agents, such as Sales Qualification Agent and Customer Service Agent. By forecasting Copilot credit usage across both Copilot Studio and Dynamics 365 scenarios in one place, you can model usage more accurately and scale deployments—helping avoid unexpected cost surprises.

With these recent admin updates, the result is fewer bottlenecks, better-informed decisions, and a clearer path to scaling agents across your organization.

Expand workflows into intelligent, governed automation systems

In Copilot Studio, workflows are step-by-step automation processes that complete actions or tasks in a deterministic, reliable way. As workflows become the backbone of business automation, these new updates help you extend their capabilities—bringing in more AI-powered reasoning, centralized governance, and a growing ecosystem of tools in a way that’s reliable and secure by design.

Design and validate workflows with more clarity

One powerful way to make your workflows more adaptable and effective is by embedding Copilot Studio agents directly into them. Using agent nodes inside workflows means that instead of just performing the task with rigid logic, the workflow can delegate reasoning, decisions, or output generation to an agent at any prescribed step of the process.

This makes workflows more resilient to real-world situations—which have a lot of variability—while still following the defined structure that make IT teams less nervous.

In addition to embedding agents, you can now also add and configure AI actions directly within the flow to understand requests, route work, and generate content dynamically. And with the ability to test individual steps using sample inputs, teams can validate behavior earlier, debug more effectively, and refine workflows before they’re deployed.

In practice: Unifi, North America’s largest provider of aviation ground handling services, used Copilot Studio and Power Platform to automate legal contract review by combining agents with deterministic workflows. Instead of relying on a single agent, they broke the process into coordinated steps that extract, classify, and validate key terms across documents. This system reduced contract processing from days to minutes and delivers the same level of performance as much more expensive, off-the-shelf products built specifically for the legal industry.

The result is a workflow experience that’s more adaptable and more predictable to operate. This helps give teams—both makers and administrators—more confidence in creating more sophisticated automation that doesn’t sacrifice clarity or control.

Scale workflows across systems with built-in governance

Speaking of clarity and control, there are also new updates to workflows that help you scale automation without introducing new governance risks.

Workflows can now connect to a broader ecosystem of tools, including model context protocol (MCP) server-enabled tools (preview), which makes it easier to take action across systems while staying within Microsoft security, permission, and compliance boundaries. This allows workflows to execute tasks and involve users for review and approval within governed processes.

We’ve also introduced a centralized, admin-controlled environment for Workflows Agent. This makes it easier to apply data loss prevention (DLP) policies consistently and maintain visibility across automation, so workflows remain compliant by design, even as they scale.

Together, these updates make it easier to move from isolated automations to connected, intelligent systems. With those systems, you can scale workflows across your organization with greater confidence, control, and flexibility.

Bring business apps directly into your agents

As agents become part of everyday work, a common gap emerges: they can generate insight, but acting on that insight often requires switching tools, re-creating context, or handing work off across systems. Support for apps in agents, now generally available, helps to close that gap.

Turn intent into action inside Copilot Chat

Agents built in Copilot Studio can now surface rich, interactive app experiences directly in Copilot Chat, allowing users to review data, update records, approve requests, or create assets in place. Instead of switching tools or re-creating context, work happens seamlessly within the flow of conversation. This helps reduce friction and empowers teams to move faster from insight to execution.

Work across the systems your business already runs on

Apps in agents bring together Microsoft and partner applications—from Power Apps to Dynamics 365 and beyond—so agents can take action across the systems your teams already use. These experiences are built and orchestrated in Copilot Studio, where you define how agents interact with apps, data, and workflows to support real business processes.

Extend and scale with trusted integrations

Through the Agent Store, you can adopt ready-made agent experiences or extend your own with partner-built integrations—while maintaining enterprise-grade security, permissions, and admin control. Options include:

• Adobe Express (seen above)
• Box
• Figma
• Monday.com
• Wix

These options (and more) make it easier to scale agent usage across your organization without losing oversight.

These capabilities, all generally available now, help teams shift agents from being informational tools to operational ones. They bring real business actions into Copilot Studio agents in a way that’s both more functional for users and manageable for IT—helping teams complete work efficiently while maintaining the governance needed to scale.

Learn more about apps in agents.

What else is new and improved in Copilot Studio

• Evaluation insights and automation updates now make it easier to generate test cases from analytics, simulate multi-turn interactions, and automate evaluations through APIs and connectors. You can turn real user conversations into targeted test sets, better reflect complex, real-world scenarios, and run evaluations programmatically. Together, these capabilities help you operationalize agent quality and maintain confidence as you scale.
• Custom metrics for outcome-based measurement help you track what actually matters to your business, not just usage. Define success in your own terms—like resolution rates or conversions—and automatically evaluate conversations against those outcomes, making it easier to understand impact, align stakeholders, and make data-driven decisions.
• Work IQ API is now available in public preview to bring Copilot’s intelligence layer—grounded in organizational context, memory, and signals—into your own agents and workflows. With built-in orchestration and enterprise-grade security, you can build agents that understand what’s happening across your business without managing raw data or complex integrations.
• Agent-to-agent (A2A) communication is now supported in Work IQ, allowing agents to collaborate as peers and delegate tasks using shared organizational context. This makes it easier to build multi-agent systems that can coordinate work, maintain context across interactions, and deliver more grounded, role-aware outcomes.
• GPT-5.5 Thinking is now available in Copilot Studio early release cycle environments as GPT-5.5 Reasoning, further expanding model choice with its more advanced analysis capabilities. This model is also rolling out across Microsoft 365 Copilot in Copilot Chat, Word, Excel, and PowerPoint.

Stay up to date on all things Copilot Studio

More is coming across voice channels, workflows, and the building experience. Check out all the updates 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 productivity within your organization, visit the Copilot Studio website or sign up for our free trial today.

Build agents your way

Create, deploy, and scale custom agents and workflows with Copilot Studio.

Try Copilot Studio today

The post New and improved: Agent governance, intelligent workflows, and connected app experiences appeared first on Microsoft Copilot Blog.

Microsoft Copilot Studio helps organizations move beyond isolated AI experiences and build connected systems of agents that can scale, adapt, and deliver real business value. Recent enhancements focus on making it easier for agents to work together across tools and data sources, while giving makers more control over how those agents behave in production.

What you’ll see this month: New generally available capabilities for multi-agent coordination across Microsoft Fabric, the Microsoft 365 Agents SDK, and open Agent-to-Agent (A2A) protocols—all of which help agents collaborate across your ecosystem and perform more valuable work. Plus, you’ll find updates to prompt authoring, model choice, and governance controls that can help make it faster to build and refine high-quality agent experiences with confidence.

Agents that work together across your entire ecosystem

The challenge in scaling AI inside an organization isn’t creating a useful agent. It’s about getting many agents—across teams and tools—to work together in a way that’s reliable and repeatable.

In many organizations, data teams might build one kind of agent, app teams another, and productivity teams yet another. Each agent can be valuable on its own, but once a workflow needs knowledge from one system, reasoning from another, and action in a third—teams often run into brittle handoffs and custom integration work. This slows agent adoption and makes it harder to move from promising pilots to real business impact.

This month, Copilot Studio takes a meaningful step forward: several multi-agent capabilities are rolling out to general availability over the next few weeks, giving your teams new ways to connect and orchestrate agents across your ecosystem. These updates include Microsoft Fabric integration, Microsoft 365 Agents SDK orchestration, and Agent-to-Agent (A2A) communication—all designed to help your agents operate together as a coordinated system rather than in isolated silos.

Multi-agent support for Microsoft Fabric

With multi-agent support, your Copilot Studio agents can work with Fabric agents to reason over enterprise data and analytics at scale. That means you can connect business-facing agent experiences more directly to the data estate they already rely on, without treating every data-intensive scenario like a one-off engineering project. Instead of working with limited or disconnected data, these agents will be able to operate with full business context—helping make their outputs more accurate, relevant, and actionable.

Multi-agent support for the Microsoft 365 Agents SDK

Using the Microsoft 365 Agents SDK, teams can now orchestrate Copilot Studio agents alongside agents built for Microsoft 365 experiences. Instead of recreating the same logic across multiple agents (think retrieving data, applying business rules, or completing common tasks), you’ll be able to reuse and combine existing capabilities. This makes it easier to compose cross-app workflows from what’s already been built, reducing duplication and keeping experiences more efficient and consistent.

Agent-to-Agent (A2A) support

With A2A support, Copilot Studio agents can directly communicate with and delegate work to other agents—first-party, second-party, or third-party—using an open protocol that allows universal access. This matters because the future of enterprise AI will not belong to a single stack. Organizations need to build agents on platforms that can participate in a broader ecosystem, not just operate within one product boundary. Copilot Studio A2A provides that interoperability and power.

The impact of multi-agent systems

We’ve already seen the power of this approach with the Ask Microsoft web agent, one of our early “customer zero” implementations. As site traffic and knowledge sources grew, the single-agent architecture began to strain, creating slower response times. Using Copilot Studio, the team upgraded the agent to a modern architecture with generative orchestration and multi-agent coordination.

Now, multiple sub-agents handle different parts of the site—Microsoft Azure, Microsoft 365, pricing, trials, and more—while the main agent orchestrates them to provide fast, coherent, multi-turn responses. This setup allows Ask Microsoft to answer complex questions involving multiple products or services, and to tailor responses based on where the customer is on the site.

Building a more advanced assistant with Copilot Studio has meaningfully raised the bar for our customer experience and enabled us to scale faster across products to deliver real business impact.

—Alyse Muttera, Director of eCommerce Programs at Microsoft

To show how this approach works in other organizations, consider a common scenario at a bank. The loan department has one agent handling mortgage applications, while the banking department runs a separate agent for account inquiries. A customer, however, expects a single seamless experience.

Multi-agent orchestration lets each specialized agent manage its area of expertise while coordinating responses behind the scenes. For instance, if a customer asks about a mortgage payment and their account balance in the same interaction, the system delivers a cohesive, context-aware answer that combines insights from both agents—no juggling multiple interfaces required.

When specialized agents work together behind the scenes, customers can get a unified experience and employees can get time back.

That’s exactly the kind of impact Coca‑Cola Beverages Africa is realizing today by using Copilot Studio agents and Microsoft Dynamics 365 to autonomously run planning cycles and automate workflows end to end, saving planners 1 to 1.5 hours every day.

These features will be fully available to all eligible customers as of April 2026. Three capabilities, one outcome: agents that can operate more like a system and less like a collection of disconnected point solutions.

Build prompts faster while maintaining control

As agent experiences grow more sophisticated, the quality of the prompt an agent maker uses matters more. A great prompt yields more powerful results from agents than a good prompt, and fine-tuning prompts is key to unlocking them.

But in practice, prompt iteration has historically felt disjointed and slow. Makers previously balanced their flow of work with jumping into a separate editor, making a small change, testing it, and then repeating the process again. That friction can add up quickly, especially when teams are tuning prompts for specialized business scenarios.

The new immersive Prompt Builder, now generally available, helps reduce that friction by bringing prompt editing directly into each agent’s Tools tab. You can update instructions, switch models, add inputs or knowledge, and test changes—all in one place. Instead of breaking context every time you want to refine an agent’s behavior, you can iterate while staying grounded in the agent you’re building.

This matters most in real-world scenarios where prompt behavior is tied to domain knowledge and policy nuance. For example, a team building an agent to support clinical documentation might need to refine instructions, swap in a better knowledge source, and test outputs against terminology that is common in healthcare but more likely to trigger default safeguards. Doing that from one workspace can make iteration faster and help lower the effort required to get a production-ready result.

More options for prompts: Content moderation and model choice

Speaking of triggering default safeguards, Copilot Studio has also added content moderation settings for prompts, now generally available in supported regions. This gives makers more control over harmful content sensitivity on managed models, including turning down that sensitivity to help unblock legitimate scenarios in industries like healthcare, insurance, and law enforcement, where default settings may be overly restrictive for the content being processed.

For even more control over prompts, the Prompt Tool now supports Anthropic Claude Opus 4.6 and Claude Sonnet 4.5 in paid experimental preview in the United States. That gives makers more choice in matching the right model to the right prompt, rather than forcing every scenario into the same tradeoff profile. This feature is great for teams that want more flexibility in how they balance performance, reasoning depth, and cost.

All together, these improvements help teams move faster on prompt iteration while maintaining the control and flexibility required in production scenarios.

What else is new and improved in Copilot Studio

We have also recently released several additional updates across automation, meetings, retrieval quality, and model support.

• ServiceNow and Azure DevOps connector quality improvements are now generally available. These help agents better understand operational questions, retrieve the right ticket or work item data, and return more complete, actionable answers automatically.
• Evaluation automation APIs are now generally available through Microsoft Power Platform APIs and connectors. These APIs help make it easier to run evaluations programmatically and integrate quality checks into continuous integration and continuous delivery (CI/CD) workflows.
• Agents for Microsoft Teams meetings can now access real-time meeting transcripts and group chat. This supports scenarios like answering questions during the meeting, surfacing relevant information, or helping track decisions and follow-ups as they happen.
• Model context protocol (MCP) apps and Apps SDK support have expanded how agents connect to your external work apps, helping to make it easier to integrate business systems and enable agents to take action across your broader ecosystem—not just respond with information.
• Additional model support, including Grok 4.1 Fast, GPT-5.3 Thinking, and GPT-5.4 Instant in paid experimental preview, gives makers more options as they tune experiences for speed, cost, and capability.

Overall, these updates reflect a continuing broader shift in Copilot Studio: moving from building individual AI experiences to building connected, governed systems that can fit more naturally into how work already happens. As you scale up your organization’s use of multi-agent ecosystems, these will help your teams reach further across channels and knowledge sources to more accurately fulfill your business needs.

Stay up to date on all things Copilot Studio

More is coming in April 2026 across voice channels, workflows, and the building experience. Check out all the updates 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 productivity within your organization, explore Copilot Studio features and pricing or sign up for our free trial today.

Build powerful agents

Create, customize, deploy, and manage agents with Copilot Studio—and explore the features, use cases, and resources that help you get there.

Try Copilot Studio today

The post New and improved: Multi-agent orchestration, connected experiences, and faster prompt iteration appeared first on Microsoft Copilot Blog.

Microsoft Copilot Studio and Agent Builder in Microsoft 365 Copilot are designed to help customers reliably create agents that scale and deliver real, sustained business value—not just prototypes. Recent enhancements focus on making it easier to move from building an agent to running one confidently across complex, dynamic environments, with consistent quality and the ability to evolve as business needs change.

Discover the latest capabilities in agent evaluations, exciting updates for computer-using agents (including expanded model support), a new Agent Academy Operative training path, and more. Plus, learn how you can use these capabilities to help ensure your agents are ready for scale.

Build trust at scale with enhanced agent evaluations in Copilot Studio

Agents aren’t “set and forget.” Prompts evolve, models update, and data changes—which raises a critical question as agents take on real work: can we trust them at scale? Agent evaluations answer that question with evidence. They’re designed to turn expectations into measurable checks, help teams catch regressions early, and provide a repeatable way to assess agent quality as behavior and context evolve.

For example, a finance leader rolling out an agent for expense policy guidance or month‑end analysis needs to trust its behavior before moving beyond a pilot. With enhanced agent evaluations in Copilot Studio, teams can now validate performance using their own scenarios, policies, and production data—measuring quality, usability, and responsiveness across a full test set instead of isolated cases.

Side‑by‑side comparisons then help catch regressions before changes go live. Meanwhile, built‑in transparency and session replays support internal and external stakeholder review. The result is a clear, evidence‑based path from experimentation to trusted deployment.

Available in public preview, here’s a quick rundown of the latest eval enhancements.

Holistic and multi-dimensional agent evaluation

• Set-level grading framework: You can now evaluate agents across an entire test set instead of individual test cases, enabling an accurate measure of overall quality. By consolidating results from multiple tasks, makers can better understand real-world performance by seeing how agents maintain quality across a range of scenarios.
• Multiple graders per test set: With the ability to apply multiple grading approaches—such as quality, performance, and usability assessments—to the same test set, teams can gain a more complete evaluation without the complexity of managing separate test sets.
• Comparative testing: Teams can compare multiple agent versions side by side, which can make it easier to spot regressions and validate improvements before pushing the best version live.

Improved transparency and control

• User reactions and feedback: Makers can now provide quick feedback on evaluation results using a simple thumbs up or thumbs down action. This feedback helps Copilot Studio capture signals about evaluation accuracy, grader alignment, and edge cases, which means our team can continuously refine our evaluation models and improve result quality for agent makers.
• Open activity map in evaluation: Direct integration with the activity map gives teams immediate insight into how agents executed tasks, helping identify where issues occurred faster and improve optimization.
• Enterprise-grade auditing: Advanced session replays, action logs, and Microsoft Purview integration offer detailed visibility into agent behavior, helping makers preserve quality and streamline troubleshooting.

Streamlined workflow and data integration

• CSV downloadable format: Makers can now download a ready-to-use comma-separated values (CSV) template that follows the exact structure required for importing test cases into evaluation. Instead of creating files from scratch—and running into formatting errors, missing columns, or failed imports—teams can rely on a validated template that can help shorten setup time and remove unnecessary friction.
• Import production data into evaluation: Real-world production data can now be imported directly into evaluations, providing high-quality test sets that reflect actual user interactions. This is designed to improve evaluation accuracy and help makers tune agents more closely to their specific audiences.
• Import and export of test sets, test cases, and results: Makers can import or export test sets, individual test cases, and evaluation results. This helps simplify teamwork and support repeatable testing across environments—essentials for enterprise-scale agent development.

Scale automation across real-world systems with nimbler computer use

Most organizations don’t lack ideas for automation. Instead, the challenge tends to be with fragmented systems, limited APIs, legacy desktop tools, and workflows that go across multiple departments. Replacing everything isn’t realistic. But maintaining brittle, script-based automation isn’t sustainable either.

Copilot Studio’s computer-using agents (CUAs) can address this gap by interacting directly with web and desktop interfaces, supporting automation across systems that weren’t designed to integrate. They facilitate automation in complex, dynamic environments where traditional robotic process automation (RPA) falls short.

Consider a customer support organization handling service requests across disconnected systems. When a customer submits a support request, a computer-using agent can:

1. Retrieve customer and entitlement details from the customer relationship management (CRM) system.
2. Create or update a case in the service management system.
3. Pull relevant troubleshooting steps from a knowledge base.
4. Update the case status and resolution checklist in Microsoft SharePoint.
5. Notify the assigned service representative and escalate if service-level agreements (SLAs) are at risk.

This would be impossible with RPA alone because of the need to transcend systems. Although pieces could be automated, a person historically would need to initiate each step. With computer use, the organization can now accelerate this process and mitigate missed steps, without requiring a redesign of existing systems.

And the latest updates enhance the value of your computer-using agents, adding key capabilities that enable improved flexibility, security, and scalability:

• Expanded model availability: We’ve added Claude Sonnet 4.5 as an additional model choice for CUAs. You can choose between Anthropic models and OpenAI’s Computer-Using Agent to get the best possible results for your task.
• Built-in credentials: Simplify and secure authentication with built-in credentials that require minimal setup. Users simply input their username and password once, and Copilot Studio stores the credentials securely.
• Enterprise-grade logging and auditing: New monitoring tools, integrated with Microsoft Purview, enhance computer-using agent session visibility. This includes detailed logs of agent activity and session replays with screenshots that support traceability and compliance processes.
• Cloud PC pool: Powered by Windows 365 for Agents, this scalable, managed cloud infrastructure integrates with Microsoft Entra and Intune. These PC pools auto-scale based on workload demand, helping you handle spikes without over-provisioning.

We know the more tools that help drive operational efficiency while maintaining control over automated workflows, the more confident teams can be about adopting computer use. That’s why these updates help elevate computer-using agents as a more reliable, adaptable solution for enterprises looking to scale their use of agentic automation.

Learn to build multi-agent systems with the Agent Academy Operative path

Finished the Recruit training from the Copilot Studio Agent Academy and looking to go deeper? The new Operative path unlocks the next level of training for agent makers who are ready to build their skills. It’s designed for practitioners who already have their first agent working and want to expand their skills to build more sophisticated, production-ready solutions.

The Operative path walks learners through building a complex, multi-agent hiring automation system, using it as an applied learning example that can be adapted to any business scenario.

Along the way, participants develop critical skills such as writing clear and effective agent instructions, selecting and evaluating AI models, and applying advanced prompt patterns, agent flow integration, and Model Context Protocol (MCP). The curriculum also emphasizes operational readiness, including feedback loops, telemetry, and AI safety throughout the agent lifecycle.

By the end of the path, learners can gain a deeper understanding of how to design, build, and architect scalable multi-agent systems that can evolve with business needs. For creators ready to move from basic agents to more advanced, reliable solutions, the Operative path provides a practical and structured next step.

What else is new and improved in Copilot Studio

Now, let’s take a quick look at some other exciting updates—all generally available (GA)—that further enhance your Copilot Studio (and Agent Builder) experience:

• Copy agents from Agent Builder into Copilot Studio to scale impact: Agents that start as individual ideas in Agent Builder and prove team-wide value can now be opened directly in Copilot Studio for a more extensive maker experience. This unlocks advanced features such as topics, automations, expanded publishing channels, and enterprise governance controls, including data loss prevention and application lifecycle management. For example, a support representative’s personal helper agent can be expanded into a shared tool that categorizes tickets, suggests responses, and routes issues to the right specialists—without rebuilding from scratch.
• Query your agent inventory from Azure Resource Graph: The Microsoft Power Platform agent inventory, which organizes and displays all your published Copilot Studio and Agent Builder agents, is now generally available. Admins can query this inventory programmatically using Azure Resource Graph to access detailed data about both draft and published agents across the tenant, using Azure portal, CLI, PowerShell, or REST API.
• Generate icons for your agents using AI in Agent Builder: Makers can now generate custom agent icons directly in Agent Builder using AI. Instead of browsing or creating artwork manually, they simply describe how the icon should look—using the agent’s description or a custom prompt—and get a unique icon designed to stand out in the Agent Store.
• Try the Copilot Studio extension for Visual Studio Code: The Copilot Studio extension lets teams version, edit, and deploy agents directly from Visual Studio Code, making it easier to align with existing software development workflows.

The big takeaway: Stronger Copilot Studio tools for more scalable agent experiences

These updates aren’t just new features; they strengthen the tools teams rely on to create agents that scale with their business. By enhancing flexibility, security, and visibility, these updates are designed to make it easier to scale agents without starting over each time.

This continuity helps makers innovate quickly while IT teams maintain control over governance, compliance, and performance—bridging the gap between rapid iteration and enterprise-grade reliability. Why? Because at the end of the day, the best agents are those that are built to grow with your needs, and with these updates, that evolution becomes more attainable every month.

Stay up to date on all things Copilot Studio

Check out all the updates 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 productivity within your organization, visit the Copilot Studio website or sign up for our free trial today.

Create your next agent

Build, evaluate, manage, and scale custom agents—all in Copilot Studio.

Try Copilot Studio today

The post New and improved: Agent evaluations, computer use, and advanced maker training appeared first on Microsoft Copilot Blog.

November 2025 was a busy month for Microsoft Copilot Studio, marked by major announcements at Microsoft Ignite 2025 and a wave of new features now rolling out to makers. It’s clear that organizations are moving beyond traditional automation and into a new era of agent-driven work. In this month’s roundup, we’re spotlighting our most significant Ignite updates and introducing powerful new capabilities you can start using today.

Copilot Studio enhancements and new features

From automation to outcomes: Ignite 2025 highlights

Microsoft Ignite 2025 underscored a clear trend: organizations are accelerating their shift toward agentic business transformation. Copilot Studio is the fully managed platform that enables them to build, govern, and scale AI agents across the enterprise. At Ignite 2025, we introduced new capabilities that create a more robust, secure agent creation experience for every user—from makers to professional developers to IT administrators.

Highlights included a redesigned conversational authoring experience, natural language file generation, and a seamless one-click upgrade path from Agent Builder in Microsoft 365 Copilot to Copilot Studio. That means business users can turn ideas into working agents faster, without waiting on development cycles and then expand when ready. This changes the game on how teams use technology to make a step change within a business process.

Makers now have even more flexibility with model choice across GPT-5 and leading third-party models, built-in agent evaluations, expanded computer use automation, and deep integration with more than 1,400 systems through Model Context Protocol (MCP), Power Platform connectors, and Microsoft Graph. In real-world terms, this removes the “user tax” of context switching and managing data silos. Whether you’re looking for help with invoice processing or supplier discovery, these agents bring collective insights to help drive a process forward.

For administrators, Ignite 2025 delivered major governance updates. These included expanded analytics and insights, real-time protection powered by Microsoft Defender, and new oversight capabilities through Microsoft Entra Agent ID that gives IT teams the confidence to scale AI safely.

We also introduced Microsoft Agent 365, the unified control plane for enterprise agents. Agent 365 centralizes governance, policy management, and monitoring. This includes new MCP servers that allow agents to schedule meetings, generate documents, send emails, and update CRM records with full compliance and audit support.

To dive deeper into all the announcements, see our full Ignite 2025 recap: Why Microsoft Copilot Studio is the foundation for agentic business transformation.

GPT-5 Chat: Ready for production in Copilot Studio

GPT-5 Chat is now generally available in the European Union and United States. This means makers can confidently use this model in production scenarios for workloads that could benefit from GPT-5 Chat’s improved responsiveness, accuracy, and instruction-following. This means makers can confidently use this model in production scenarios for workloads that could benefit from GPT-5 Chat’s improved responsiveness, accuracy, and instruction-following.

You can enable GPT-5 Chat directly from an agent’s overview page. You can even set it as the primary model for scenarios like high-volume employee support or step-by-step process guidance.

We’ve also started rolling out the GPT-5.2 series as experimental models for U.S. customers in early release environments. These models improve performance across the board, including coding and multilingual use cases. This replaces the GPT-5.1 series, including in any agents created using GPT-5.1 models. Since these models are experimental, they’re best suited for test scenarios rather than production—but they give you an exciting preview of what’s coming next.

You can read more about model choice and how to test them out in Copilot Studio.

Combine autonomous workflows with human judgment

One of the most important evolutions this month is human-in-the-loop (HITL), now in preview. This capability lets agents pause and ask for human input before moving forward. That may sound simple, but it fundamentally changes what organizations can trust agents to do.

With this feature, an agent can send a structured request (delivered as an Outlook form) to designated reviewers. Once the reviewer responds, the agent resumes and uses the submitted values as parameters. This provides real-time human judgment without disrupting the overall workflow.

HITL is especially useful when an agent needs clarification, additional context, or explicit approval to proceed. It supports scenarios such as confirming project updates, confirming procurement orders, validating financial reports, escalating complex customer support cases, resolving ambiguous data, or gathering information that only a person can provide. The result is more flexible and reliable automation that adapts to real-world conditions.

To use HITL, open the agent-building experience and select Add tool. Choose the request for information in Copilot Studio agent flows (preview) action under the Human-in-the-loop connector, then configure fields such as the title, message, assignee, and inputs. The agent will automatically trigger the request whenever the workflow calls for it. Learn more about request for information.

Add curated Outlook and SharePoint tool groups to agents for faster setup

Makers can now streamline agent configuration by adding curated Action Groups from Outlook and SharePoint connectors, now in preview. Instead of identifying and configuring individual actions one by one, teams can bring in complete sets of related tools, such as “manage emails” or “manage files,” with a single selection. This makes it easier to equip agents with the capabilities they need to support common workflows across communication and content management.

Each Action Group contains the most relevant and reliable tools for its scenario. Shared inputs automatically apply across the group to reduce setup time and improve consistency. Makers can either specify their own values or opt to have AI dynamically fill inputs based on context. Try it both ways—each action is fully editable even after it’s added. This flexibility helps ensure agents behave predictably while still allowing customization for unique business processes.

To use Action Groups, open an agent’s Tools section, select Add tool, choose Outlook or SharePoint, and pick the tool group you want to add. This provides a faster, clearer, and more guided way to build workflow-ready agents.

SharePoint grounding: Turning content chaos into decision clarity

Any team that uses SharePoint knows that it can sometimes be tough to find exactly the nugget of information you need among all your content. Fortunately, if you’re using SharePoint as a knowledge source, your agents just got a lot smarter. We shipped an upgraded tenant graph grounding architecture that improves how agents retrieve and rank information across your organization. This translates into more precise, more context-aware responses, especially in content-heavy environments.

On top of that, you can now filter SharePoint content using metadata like filename, owner, and last modified date. That gives you much tighter control over which documents your agents rely on when answering questions.

Learn more about these features and using SharePoint as a knowledge source.

Agent Builder enhancements and new features

Use the latest GPT-5 Chat capabilities in Agent Builder

Microsoft 365 Copilot now uses GPT-5 Chat when responding to prompts in agents created with Agent Builder. This brings immediate improvements to speed, quality, and accuracy in carrying out instructions. Organizations relying on agents built in Microsoft 365 Copilot will see immediate quality improvements in employee support, decision guidance, and informational use cases. No additional configuration or opt-in is required where GPT-5 Chat is available.

GPT-5.2 is also now available to use in Microsoft 365 Copilot with both web and work data. This new model series brings improved code generation and multilingual capabilities. Users with a Microsoft 365 Copilot license received priority access to GPT-5.2 on December 11, 2025, and the series is expected to be available to all users in the coming weeks.

Extend your agent seamlessly from Agent Builder to Copilot Studio

Makers can now seamlessly move agents built in Agent Builder (the lightweight agent-building experience inside Microsoft 365 Copilot) into the full Copilot Studio application using the new “Copy to Copilot Studio” action. This capability is generally available everywhere Agent Builder is supported.

This feature allows makers to start prototypes quickly in Microsoft 365 Copilot and then expand them into fully governed, enterprise-ready Copilot Studio agents without rebuilding from scratch. The copy operation creates a version of the agent in the selected environment while preserving the original in Agent Builder. In addition to providing peace of mind, this means your users can still partake in the existing experience while the enhanced version is developed.

Once an Agent gets copied into Copilot Studio, makers gain access to a suite of richer capabilities. This includes lifecycle management, analytics, more third-party connectors, and publishing options that give agents access to channels such as the Teams app store. This helps create a healthy innovation cycle: fast at the edges, controlled at the core. Learn more about copying agents to Copilot Studio.

Streamline employee support with the Employee Self-Service Agent

The Employee Self-Service Agent in the Microsoft 365 Copilot agent building experience is now generally available. This agent provides a centralized AI-powered experience for common employee support scenarios, including HR- and IT-related needs. The Employee Self-Service Agent helps employees quickly get answers and complete tasks such as checking leave balances, reviewing benefits, or submitting IT tickets. This agent provides a centralized AI-powered experience for common employee support scenarios, including HR-related and IT-related needs. The Employee Self-Service Agent helps employees quickly get answers and complete tasks such as checking leave balances, reviewing benefits, or submitting IT tickets.

Built for makers to configure and extend in Copilot Studio, the agent includes prebuilt connectors and workflows for systems like Workday, ServiceNow, and SAP SuccessFactors. It’s fully customizable and extensible. This allows teams to tailor responses, logic, and integrations to their own organizational processes.

To keep employees in their flow of work, the agent can also hand off to Workday or ServiceNow agents when deeper actions are required. This means that instead of employees navigating portals or emailing multiple teams, they can simply ask for what they need. From a business lens, this reduces ticket backlogs, shortens resolution times, and improves employee sentiment.

The Employee Self-Service Agent is designed to work within your existing Microsoft 365 security, privacy, and compliance boundaries. Expanded support for Facilities and other verticals is coming soon. Learn more in the Employee Self-Service Agent announcement blog.

Unlock organizational intelligence: People as a knowledge source

Makers can now add People as a knowledge source in Agent Builder for declarative agents. Agents can reference live directory information, including employees’ roles, reporting relationships, team memberships, and profile details, to answer questions such as “Who is the manager for X?” or “Who is on Y team?” with current, accurate details.

This feature, now generally available, promotes richer organizational insight across internal workflows, approvals, and employee support experiences. It’s especially valuable for onboarding, internal support, approvals, escalation paths, or any workflow where it can be difficult, but critical, to identify the correct person. By grounding agents in live directory data, makers can deliver more accurate, context-aware responses without manual upkeep or duplicated lists.

To enable People as a knowledge source, open Agent Builder, navigate to Knowledge sources, and select “Reference people in organization.” Learn more about People as a knowledge source.

Generate polished documents, spreadsheets, and presentations

This is where AI shifts from “assistant” to “producer.” Agents built inside Microsoft 365 Copilot can now create high-quality Word documents, Excel worksheets, and PowerPoint presentations using the “Generate documents, charts, and code” skillset (formerly known as Cope Interpreter). This capability is generally available everywhere Agent Builder is supported.

These enhanced Office skills bring richer creation and formatting tools directly into your custom agents. Agents can generate structured documents, well-designed slides, and Excel files that incorporate charts, visuals, layouts, and other professional elements. This makes it easier for teams to create reports, summaries, plans, proposals, and analysis as part of an automated workflow. You can do all this using natural language.

To try out this feature, open Agent Builder and toggle on Generate documents, charts, and code. If Code Interpreter was previously enabled, the new capabilities are automatically available.

Use OneNote pages as living knowledge

Makers can now add OneNote pages as knowledge sources in Agent Builder. Many teams rely on OneNote to capture meeting notes, brainstorming sessions, project plans, research summaries, and personal workstreams. This update, now in preview and due to roll out worldwide in December, brings all that information directly into your agents’ grounding experience.

By selecting specific OneNote pages, makers can empower agents to provide responses that reflect real project context and decision history. This is especially helpful for roles that depend on ongoing notes, such as customer success, project management, operations, or research, where critical details often live outside traditional documents.

OneNote support also reduces the need to copy content into files or recreate notes elsewhere. Makers can simply choose the pages they want to include and let Microsoft 365 Copilot agents draw from them automatically during conversations and workflows.

To add this capability: Open Agent Builder, go to Knowledge sources, choose OneNote from the file picker, and select the pages you want to include. Learn more about knowledge sources in Agent Builder.

The bigger takeaway

The story of November 2025 isn’t just new features. It’s a shift in how work gets designed.

We’re moving toward a world where organizations don’t just automate steps—they design intelligent systems of work, where AI agents handle complexity, people apply judgment, and businesses operate with more speed, clarity, and resilience.

And we’re just getting started.

Stay up to date on all things Copilot Studio

Check out all the updates 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 productivity within your organization, visit the Copilot Studio website or sign up for our free trial today.

Microsoft Copilot Studio

Design and scale custom agents to transform your business.

Try Copilot Studio today

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

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.

Microsoft Copilot Studio

Design and scale custom agents to transform your business.

Try Copilot Studio 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 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.

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 usage 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 usage 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.

Copilot Studio

Transform business processes across your organization.

Learn more

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.

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.