Functioning code is only the first step. The work that follows includes provisioning and securing cloud resources, configuring identity and security models, honoring organizational policies, and establishing deployment processes. Operating the app throughout its lifecycle can slow teams down, consume additional resources, and create a different governance model for every app-building platform.

Today, we’re introducing Microsoft Copilot Managed Runtime into public preview, an enterprise-grade platform to run code within the Microsoft 365 tenant boundary that’s governed by IT and inherits all the usability expectations users have such as sharing, live data connections, and easy access to their apps.

Copilot Managed Runtime already powers the apps built in Copilot Cowork, Copilot Code, and Microsoft Copilot Studio. We’re also enabling access to third-party tooling and professional developers, giving IT admins a consistent way to govern apps and giving users a familiar app experience, across build experiences.

More freedom to innovate, more confidence to run

The Copilot Managed Runtime host gives teams a shared enterprise foundation around the apps they create, bringing together Microsoft-operated cloud hosting, identity, governed data access, and lifecycle management. Instead of assembling that foundation for each application, teams can focus on putting useful apps into people’s hands, with IT retaining control over how those apps run, and who is able to build over which enterprise data sources.

Security and governance are part of that foundation: Microsoft Entra identity provides authorized access, while organizational policies govern the connectors, data, and endpoints applications can use. Automatic version and source control via Git enables true developer workflows and co-dev. Connectors and Work IQ are integrated to make accessing and authorization to the products and data you need easier.

Microsoft operates the platform; your organization sets the boundaries; you remain in control.

That consistency extends across apps built in Microsoft experiences such as Copilot Cowork, Copilot Code, and Copilot Studio as well as SDK-compatible third-party tools, with a centralized inventory in the Microsoft 365 admin center to review access, usage, health, and policy. Builders gain more freedom to create, while IT gets one management model rather than a separate approach for every app-building tool.

Bring your code and the tools you love

The Copilot Managed Runtime SDK is the connective layer between the code you create and the Copilot Managed Runtime host. It gives Microsoft and third-party development experiences a consistent way to build against Microsoft services and move an application from development into an enterprise-managed runtime.

The SDK and command-line interface (CLI) support the full development lifecycle rather than simply packaging the finished app. Developers can scaffold and configure projects, define the data connections their app needs, and generate typed services for working with connectors from TypeScript. They can run and preview applications during development, then deploy and version them through the same toolchain. At runtime, SDK APIs provide a secure bridge between the application and services exposed through the host, including governed access to enterprise data, identity, and Copilot work context.

Developers can continue working with editable, Git-backed code and familiar web technologies in the tools they already use, while giving the resulting application a consistent path to Microsoft 365 for deployment and operation.

With the Copilot Managed Runtime SDK, an app made with Lovable can now run inside your Microsoft tenant, the same way everything else does: same sign-in, same policies, same app inventory.

Lan Roche, Head of Global Partnerships at Lovable

Moving from a working app to a production app usually requires significant platform work. The Copilot Managed Runtime host makes that enterprise foundation part of the deployment model rather than a separate project at the end. Apps deployed to the host can use capabilities such as:

• Microsoft Entra identity and sharing.
• Microsoft-hosted runtime environments for applications.
• Organizational policies for connectors, data access, approved endpoints, and auditing.
• Deployment, versioning, and lifecycle controls.
• Central inventory, monitoring, usage visibility, and IT control.

Teams can preview and improve a new version while the current version remains available to users. Identity and policy are enforced through the host. Monitoring, usage, and inventory give your organization visibility into what’s been built, how apps are being used, and app health. Enterprise readiness becomes the default path, not a checklist that each development team must rebuild.

View, manage, and govern apps in a single place

As those who can build applications and how quickly they can be created keep expanding, that opportunity also raises a practical question for every organization: how do we keep a clear view of what’s running, who can access it, which data and services it can reach, and whether it continues to meet our policy?

Apps hosted with Copilot Managed Runtime appear in the new Apps experience in the Microsoft 365 admin center, giving administrators a central inventory and a consistent place to review access, usage, health, and policy. The same model applies regardless of where the app was built, so IT doesn’t need a separate governance playbook for every creation tool.

Central governance should not require centralized creation. Builders can continue to work in the right experience that fits their job. IT gets a common operating layer for deployment, security, monitoring, and lifecycle management. That separation of open build and managed run is what makes it possible to scale app innovation without scaling operational risk at the same rate.

Enterprise app development and governance scenarios

The Copilot Managed Runtime model supports a wide range of internal business applications. For example:

• A team can create a launch-management app in Copilot Cowork, connecting it to approved planning data, and deploy it through a governed path.
• A developer can pull the code down to continue to build upon what the team created with familiar web technologies and update it without forking or standing up a separate runtime, platform resources, and governance stack.
• An administrator can review the app in their inventory, monitoring usage in one place, and applying a consistent set of controls across applications from different build experiences.
• In each case, the enterprise operating model remains consistent regardless of the authoring toolsets used. That gives makers and developers more freedom throughout the lifecycle to build and iterate and gives IT more confidence once the application reaches users.

Get started with Copilot Managed Runtime in public preview

The Copilot Managed Runtime host and SDK are being introduced in public preview. Microsoft entry points are already live with Copilot Cowork, Copilot Code, and Copilot Studio, and developers can use the SDK and plugins to build applications for the host. Read more Copilot announcements on the Official Microsoft Blog.

Administrators can enable and disable apps and review the default policies in the Apps experience in the Microsoft 365 admin center.

AI will keep lowering the barriers to application creation. Trust, control, and reliability need to advance just as quickly. With the Copilot Managed Runtime host and SDK, teams get the freedom to build in the tools they choose, and organizations get a consistent way to deploy, secure, govern, and operate what those teams create, leaving your enterprise with apps built for work.

We look forward to seeing what you build.

The post Build where you want, run with confidence: Now Microsoft hosts and manages the code created by Copilot appeared first on Microsoft Copilot Blog.

But generating an application is only part of the equation. To solve real business problems, applications need to connect to enterprise data and systems, operate securely, and fit within the processes people rely on every day. And as more people become app builders, IT needs the governance and controls to confidently bring those solutions into the enterprise.

That’s why we’re introducing natural language app building in Copilot Cowork and Copilot Studio, bringing agentic app creation into the same trusted, connected enterprise platform you already rely on. In Copilot Cowork, build apps with the new /app skill now available via the Microsoft Frontier program. In Copilot Studio, build apps alongside agents and workflows to turn ideas into complete business process solutions, rolling out in public preview over the next week.

Whether you start in Copilot Cowork or Copilot Studio, the same capabilities empower you to start with the outcome you want, shape it through natural conversation, connect it to organizational data, and publish an enterprise-ready, governed solution.

Build an app by describing what you need

App building starts with a conversation. Choose App (Preview) from the Copilot Studio home screen or invoke the /app skill in your Copilot Cowork chat. Then, simply describe the business outcome, users, data, and actions you need. Copilot Studio uses agentic coding to turn your intent into a working app scaffold.

From there, you can continue to iterate in natural language, inspect the app in preview, and review the underlying code. The experience is designed to serve a broad spectrum of builders: information workers can stay focused on the solution, while advanced makers and developers can go deeper into the app’s structure and code when they need more control.

Connect apps to your business data

Apps built with Copilot Cowork and Copilot Studio use connectors to work with your business data, including using Work IQ to access organizational context. This allows makers to turn organizational information into usable, connected experiences—not just surfacing information, but taking action and writing results back to the systems within your Microsoft 365 tenant boundary where work happens.

For example, an onboarding app can use connectors to show progress from a business data source, surface learning resources, and update onboarding records. As another example, a field service app can retrieve product technical context from a third-party system, present guided steps, and write results back to connected systems. The result is a structured app experience that’s grounded in the data and services people use to get work done.

Build enterprise apps with open standards and centralized control

Apps created in Copilot Cowork and Copilot Studio are full-stack apps built using open standards. They can use Git-backed source control, deployment stages, and version isolation so teams can continue improving the next version without disrupting the live experience.

By default, identity with Microsoft Entra, as well as organizational data and connector policies, are respected. IT administrators have centralized visibility in the Microsoft 365 admin center, which shows an inventory of published apps and operational controls to help govern, secure, and manage them throughout their lifecycle. Makers can focus on building and sharing solutions, while IT maintains the oversight needed to run them confidently across the organization.

Start building apps with Copilot Studio

You can start building apps today by joining the Frontier program and using the /app skill in Copilot Cowork. Access to app building natively within Copilot Studio is rolling out in public preview over the next week. When available in your environments, you’ll be able to open Copilot Studio, click the apps tile, and describe what you want to build using natural language. App building and running follows the usage-based billing model.

When published, apps appear in the Microsoft 365 admin center, giving administrators centralized visibility and controls to help govern them from the start. Users will be able to discover and use shared, enterprise-ready applications at managedapps.cloud.microsoft.com.

With apps alongside agents and workflows in Copilot Studio, teams can create complete, interactive business experiences and move from an idea to an enterprise-ready solution. We will continue improving the experience as we learn from customers.

We look forward to seeing what you build.

From idea to app

Create full-stack business apps through conversation with Copilot Cowork and Copilot Studio.

Build your first app

The post Build apps in Copilot Cowork and Copilot Studio appeared first on Microsoft Copilot Blog.

Today, we’re expanding that choice with the addition of Mistral Medium 3.5 for agent building and orchestration. Medium 3.5 is currently available worldwide for customers in early release environments.

For organizations in the European Union (EU), this model has the added benefit of providing more flexibility in how their agents are powered, while keeping data processing in-region. It also helps these teams avoid the extra procurement overhead that can come with adding a new model provider.

Medium 3.5, per Mistral, was built for “long-horizon tasks, calling multiple tools reliably, and producing structured output that downstream code can consume.” Reasoning effort is configurable per request, so the same model can answer a quick chat reply—or, alternatively, work through a complex agentic run. You can read more about this model on Mistral’s blog.

Model access and admin controls

We’re rolling out Medium 3.5 for customers in early release environments. As an experimental model, we recommend using it in non-production scenarios while testing and evaluations are completed.

As with all external model providers in Copilot Studio, admins stay in control:

1. Opt in via the Microsoft 365 admin center to allow the Mistral Medium 3.5 preview for your tenant.
2. Enable external model providers in the Microsoft Power Platform admin center so makers in your selected environments can select Mistral Medium 3.5 in the Copilot Studio model picker.

Until both switches are on, the model will not appear to makers. This gives IT teams a structured path to pilot, evaluate, and expand usage on their terms.

Get started with Mistral Medium 3.5 in Copilot Studio

• Admins: Review the enablement guide and model provider terms, then complete the two-step opt-in.
• Makers: Once your admin has enabled access, open any agent in Copilot Studio and select Mistral Medium 3.5 (Experimental) from the model selector.

Bringing choice and control together

With Mistral Medium 3.5, Copilot Studio continues to expand the range of models available for agent development—while keeping orchestration, governance, and lifecycle management in one place.

The result: customers can choose the right model for each scenario, meet regional and compliance requirements, and scale agents confidently within a unified platform.

More choice. More control. One platform.

Model choice, on your terms

Build and scale agents with flexible models—while keeping control of your data and governance.

Try Copilot Studio today

The post Mistral joins Copilot Studio’s growing lineup of model providers appeared first on Microsoft Copilot Blog.

That’s why we’re excited to announce the general availability of real‑time voice agents in Microsoft Copilot Studio launching in Dynamics 365 Contact Center. These agents are designed for nuanced, high‑impact interactions where voice experiences need to adapt in the moment—while still operating within trusted, enterprise‑grade solutions.

Real-time voice agents build on the momentum of Copilot Studio as a proven, enterprise-scale platform. Over 80% of Fortune 500 companies now have active agents built using our low-code/no-code tools, creating a strong foundation for bringing real-time, conversational voice experiences into their customer workflows.¹ This widespread adoption shows how ready organizations are to extend their existing Copilot-powered agents into natural, responsive voice interactions.

Why AI voice support needs to go off script

For decades, menu‑based interactive voice response (IVR) systems provided predictability, reliability, and compliance at scale. Over time, organizations layered in speech recognition and automation to reduce friction and manage growing call volumes more efficiently. These approaches remain critical today and continue to power successful customer service operations across industries.

What’s changed is not the importance of voice, but the expectations customers now bring into voice interactions. Conversations rarely follow a straight line. Customers interrupt, clarify, change direction mid‑call, or introduce urgency without warning. When that happens, rigid interaction models can struggle to keep up, even when the underlying systems are reliable.

Meanwhile, across industries, contact centers are under pressure to do more with less. Interaction volumes continue to rise, margins are tighter, and customer expectations are shaped by digital experiences that feel fast, personal, and responsive. Many teams are already exploring AI through chatbots, voice automation, or workflow tools, but scaling those experiments into production voice experiences that customers trust is far harder than running a pilot.

Voice, in particular, exposes gaps immediately. Latency, awkward handoffs, or missing context are noticed in real time, often at the most critical moments. That’s why simply adding automation isn’t enough. As organizations move toward agentic, AI‑first service models, voice needs to work as part of a unified service layer: one where understanding, reasoning, and action happen together, and where context carries forward if escalation is required.

Meeting this bar doesn’t require replacing the voice systems that already work. It requires extending them with capabilities designed specifically for live, conversational interactions. This makes it possible to move beyond scripted interactions without treating voice as an isolated AI experiment.

Meet real-time voice agents for AI voice support

Real‑time voice agents represent a new premium mode within voice agents that sits under the broader category of conversational AI. They are optimized for low‑latency, interruptible, speech‑to‑speech conversations with real‑time reasoning. This distinction helps teams choose the right interaction model for each scenario without treating all voice interactions as equal.

These agents can move from intent to action to confirmation within a single interaction. They can retrieve or update information mid‑conversation and take action as the interaction unfolds. Customers can get faster resolution, while service teams can maintain consistent experiences and centralized operational control. This also frees human agents to focus their time and energy on conversations where judgment and empathy matter most.

High-volume self-service, designed for everyday voice interactions

Real-time voice agents are built for the high volume, business-to-consumer (B2C) interactions that define customer service at scale. These everyday inbound calls make up the majority of customer engagement across industries. To support this breadth, Copilot Studio enables organizations to grow their voice strategy—starting with deterministic, template-driven flows and expanding into dynamic, real-time voice agents as needs evolve.

Copilot Studio provides a documented set of external voice agent templates designed for unauthenticated, customer-facing interactions across both Copilot Studio and Dynamics 365 Contact Center, covering many of the core workflows customer service teams handle today, including:

• Billing and payments, which are among the most frequent and sensitive contact center interactions. Customers want clarity and resolution in the same call, not a handoff or follow-up. These scenarios often start with deterministic flows—confirming identity, checking balances, or processing payments—but can switch to dynamic, real-time voice agents that explain charges, respond to questions, and adapt tone as situations become more urgent.
• Order and reservation support across retail, travel, and hospitality, which often requires more dynamic handling. What begins as a simple status check can quickly shift into a change request or issue resolution. Real-time voice agents adapt to these pivots by grounding responses in live order or reservation data. They’re designed to act while preserving relevant context, supporting organizations as they evolve from structured flows to more flexible conversational automation.
• Eligibility and verification scenarios in healthcare, financial services, telecom, and the public sector, which rely on accuracy and trust. Deterministic steps—collecting required information, confirming eligibility criteria—can be paired with dynamic voice capabilities that answer questions as they arise and help preserve continuity if escalation or additional support is needed.
• Appointment scheduling and changes often involve interruptions and evolving preferences. Organizations can begin with predictable scheduling flows and grow into dynamic, real-time voice agents that let customers book, reschedule, or confirm details conversationally, without unnecessary restarting or repeating information as needs shift.
• Account and membership management, which often spans multiple tasks, from updating personal details to managing subscriptions or reviewing benefits. Deterministic updates can be combined with dynamic, context-aware voice interactions that stay connected to live account data, keeping these conversations efficient, accurate, and natural from start to finish.

From conversation to resolution, without breaking flow

Real‑time voice agents are built for real customer service environments, where escalation is a natural part of resolution rather than a failure of automation. At launch, these experiences are delivered through Dynamics 365 Contact Center, with conversation context carrying forward automatically, helping reduce the need for customers to restate information when human judgement is required.

As part of the Copilot Studio product roadmap, real‑time voice agents will also extend to Microsoft Teams Phone and additional Copilot Studio digital apps and channels, enabling organizations to bring consistent, context‑aware voice experiences to more customer touchpoints over time.

Voice automation designed for trust, control, and evolution at scale

For IT teams, voice automation has always been high impact but high risk. Feedback from early internal deployments reinforces the importance of pairing conversational intelligence with enterprise‑grade governance and lifecycle controls.

Innovation in voice does not require giving up control or predictability. Voice is a high‑stakes interaction surface, and customers notice immediately when experiences feel unreliable or inconsistent.

Copilot Studio takes a deliberate approach to real‑time voice by selecting the right models for the right moments, including the latest frontier models, optimized for the right balance of quality, latency, and reliability, without placing that complexity on customers. Built on Microsoft’s enterprise foundations for security, governance, and operational oversight, real‑time voice agents help organizations innovate with confidence while preserving trust.

Get started with Copilot Studio

Support for real-time voice agents is now generally available in North America for Dynamics 365 Contact Center, with language support, additional regions, and broader customer touchpoints expanding over time as part of Copilot Studio’s global rollout.

Learn more about real-time voice agents and sign back in to Copilot Studio to start scaling customer support with agents today.

New to Copilot Studio? Discover how you can transform your business by building, evaluating, managing, and scaling custom AI agents—all in one place. Sign up for a free trial of Copilot Studio today.

Build voice agents that adapt

Create and manage high-impact, flexible voice agents—designed for enterprise scenarios.

Try Copilot Studio today

¹ Source: Microsoft usage data, 2026.

The post Extend AI voice support: Introducing real-time voice agents in Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.

So how do you know when to use agents vs. workflows?

It’s no longer an either-or decision. Here’s how to use agents and workflows together to combine strengths and reduce risks.

What are agents and workflows?

Agents are flexible AI solutions that rely on foundational models to act, share knowledge, and handle tasks. They are powerful precisely because they are flexible. They can interpret unstructured inputs, reason over context, and make decisions beyond fixed logic.

However, organizations often need to know that repetitive parts of their processes will behave consistently, every time they run. Pure agent autonomy doesn’t always hold up to that requirement in production.

Workflows, by contrast, are powerful automations that drive process execution with consistency and speed. They’re designed to deliver the reliability that many business processes require.

At the same time, rigid, rules-based automation has its own ceiling. It’s nearly impossible to anticipate every potential input format, edge case, and decision-making context when building a workflow ruleset. Thus, when the workflow automation encounters something unexpected, it can’t move forward.

Two patterns for scaling automation with AI

While both agents and workflows have their strengths, we’re seeing customers get the most value in Copilot Studio by combining the two. In practice, we’re observing two patterns emerge in how customers apply Copilot Studio, and we’re continuing to deliver product improvements to strengthen and support them.

Workflows that use agents

The first pattern is workflows that call agents. In these instances, the workflow provides the structure for the business process—the defined steps, branching logic, handoffs, and an audit trail. Meanwhile, the agent handles the parts of the process that require judgement. This might include interpreting a document, synthesizing information from multiple sources, or deciding how to route an exception.

Once the agent completes its work, control returns to the workflow, and execution continues predictably.

To make it easier to add agents to workflows in Copilot Studio, we’re introducing agent nodes: the ability for workflows in Copilot Studio to call an agent directly within a workflow. You can build a deterministic, reliable automation, and at the exact moment you need AI reasoning, the flow simply hands it off to an agent.

Setting up an agent node inside a workflow is simple:

1. Create a workflow step called “Add an agent.”
2. Select any Copilot Studio agent you’d like to be include in the workflow.
3. Provide the instructions or task the agent needs to fulfill, and include an option to contact a designated person if specific clarification is needed.
4. Add the rest of the workflow’s steps.

When you run the workflow, the agent will do its job at the appropriate stage, and then the rest of the workflow will automatically continue.

When to use agents inside workflows

Using agent nodes to include agents in your workflows unlocks scenarios that rigid automation alone can’t handle. Some potential uses include the following:

• A procurement workflow that routes to an agent to evaluate vendor proposals against company policies.
• An HR onboarding workflow that personalizes welcome materials based on role and department.
• A customer service process that escalates complex cases to an AI agent for resolution recommendations.

In general, anywhere your 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. This capability is available now in all regions.

Agents that use workflows

The second pattern is equally important: agents that use workflows as tools. When an agent is working through a complex task, it doesn’t need to rediscover how to act every time. Instead, it can call a reliable, tested workflow to execute a well-defined subprocess—and then use the result to continue its reasoning and response.

This ability helps agents to build on existing process infrastructure rather than reinventing it. Moreover, it helps give organizations more confidence that the high-frequency or high-stakes parts of the processes can run with the consistency and controls the org requires.

There are two ways to add workflows into an agent:

1. Use natural language to build a workflow directly inside Copilot Studio and include that new workflow in an agent.
2. Alternatively, from within the agent, you can access your library of pre-existing workflows and add them as tools. Then, provide explicit instructions to your agent on when to use the workflow.

That’s it—your agent’s orchestrator will select the right workflows at the right time when needed to complete its work.

When to use workflows inside agents

Adding workflows inside your agents helps add structure and consistency to interactions that still require flexibility. Some potential uses include the following:

• A sales agent assembles the right product details and pricing tier for a deal, then calls a workflow to generate the quote, apply discount rules, and route it for approval.
• A customer service agent determines a refund is warranted, then calls a workflow to validate it against business rules, process the payment reversal, and send the confirmation.
• A procurement agent evaluates which vendor and terms apply to a request, then calls a workflow to create the purchase order in the ERP system and routes it through the approval chain.

Generally, anywhere your agent needs to reliably execute a repeatable process—enforcing business rules, coordinating systems, or ensuring key steps are completed—a workflow can help ground its actions and make outcomes more consistent.

Start using agents and workflows together

Together, these two ways to combine agents and workflows provide you with flexibility to build automations that work better for your real-world needs. Agents handle ambiguity where workflows go brittle; workflows enforce structure where agents might drift.

By embracing a combination of agents and workflows, it becomes easier for different teams to engage in ways that fit the way they work best. Business teams can extend and adapt these automation solutions without rebuilding from scratch. Compliance teams can audit them. Finally, your security and governance teams can choose the right balance of consistency and agility, based on what each scenario requires.

In organizations already using Copilot Studio to support their daily work, both patterns—workflows using agents and agents using workflows—show up regularly:

• A procurement workflow calls an agent to evaluate supplier contracts that arrive in inconsistent formats.
• A customer service agent, handling an open-ended request, calls a workflow to initiate a refund or update an account record.
• An approval process invokes an agent to synthesize context before routing to a decision-maker—and separately, that same agent calls a workflow to send notifications, log outcomes, or kick off downstream steps.

These scenarios show how automation and intelligence can reinforce each other, combining structure and flexibility to deliver more adaptable, dependable results.

Try these capabilities in Microsoft Copilot Studio today.

Transform your business processes

Build powerful AI agents and workflows to assist with and automate work

Try Copilot Studio free

The post Automate business processes with agents plus workflows in Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.

But enabling this kind of capability raises real questions for IT: What risks do these agents introduce? Are they actually being used? And are they behaving as expected?

The more agents you launch and the more powerful these agents are, the more these answers matter. That’s why we’re introducing three new capabilities across Copilot and Microsoft Copilot Studio that help people move work forward faster—while keeping IT firmly in control:

1. Enhanced agents that bring apps directly into chat in Copilot
2. New ways for employees to find the right agent, fast
3. Tools to continuously evaluate agent quality over time

With these capabilities, employees can use their go-to business apps directly in Copilot and get a simpler way to discover the right agents for their tasks. Meanwhile, IT gains objective signals that help validate agent behavior as usage expands. Here’s what you need to know.

Interacting with apps through chat in Copilot

Today, the gap between AI insight and in-app execution starts to close—without IT needing to relax standards or introduce new risk vectors.

When an employee prompts Copilot and calls an agent connected to an approved app, that agent can bring that app’s interactive experience directly into the conversation. From there, the employee stays in the driver’s seat, using chat in Copilot to take real, in‑app actions such as:

• Scheduling a new event in Outlook
• Adding a new sales opportunity to Dynamics 365 Sales
• Creating or editing a flyer in Adobe Express
• Completing an approval form via Microsoft Power Apps

All of this happens without needing to leave Copilot. Employees interact with the app directly in chat or use follow-up prompts to carry out work in the app.

Get started quickly with pre-built app experiences

This month, we’re launching support for a focused set of early experiences, including:

• Microsoft apps, such as Outlook, Dynamics 365 Customer Service (public preview by early April), and Dynamics 365 Sales (public preview by early April)
• Custom line-of-business apps built with Power Apps (public preview this March)

Take Outlook, for example. You can now tell Copilot who you want to meet with, and it’ll find time slots that work. Simply select one, and an agent will schedule that time together. This experience is currently generally available (GA). Similarly, you can ask Copilot to draft an email on your behalf, edit it, and hit send—without leaving the chat (currently in Frontier).

We will also introduce in-chat experiences for a handful of Microsoft partner apps, including Adobe Express, Adobe Acrobat, Base44, Box, Canva, Coursera, Figma, Miro, Monday.com, Optimizely, and Wix. All pre-built partner app experiences will be available via the Microsoft 365 Agent Store by mid-April.

“With the Figma app in Copilot, you can turn conversations into AI-generated FigJam diagrams to take ideas further,” says Brendan O’Driscoll, Figma’s VP of Product. “By connecting Figma with your favorite tools, it’s easier than ever to visualize, iterate, and collaborate with your entire team.”

Build the app experiences your team needs

You’re not limited to the apps we ship out of the box. Your team can build agents in Copilot that work with the mission-critical apps that your systems, processes, and workflows depend on.

Under the hood, two open extensibility standards make this possible: MCP Apps and the OpenAI Apps SDK. Both give development teams a structured way to connect the apps your organization relies on to agents in Copilot—so those apps can surface interactive experiences directly in chat. Agents built with either standard use familiar development patterns, so your team can build and iterate without requiring a steep learning curve.

MCP Apps and Apps SDK will roll out to GA on web and desktop later this month, with mobile following this spring. Share the Apps SDK and MCP Apps technical documentation with your development team to get started.

Get to know the IT controls

Even as agents become more powerful, we’ve designed this experience with governance in mind. Agents with interactive app experiences use the same governance and admin patterns you already trust for agents in Copilot, keeping IT control the top priority.

You decide which agents are available in your tenant, and who can use them—globally, per agent, or for specific departments. Each agent operates strictly within existing app permissions and identity boundaries, so you can enable richer experiences in Copilot without opening new, unmanaged entry points into your environment.

All agents can be monitored end‑to‑end using Agent 365—a unified control plane that gives IT a single place to see which agents are live, where they can act, and how they’re being used. With it, you can control how agents are provisioned and scoped before rolling out this new experience broadly. Learn how to provision your organization’s agents at scale.

Empowering employees to find the right agent fast

As agents in Microsoft 365 Copilot become more capable, employees need a reliable way to find the right agent for the task at hand. But when dozens of agents are available, employees shouldn’t have to know which one to use when. Agent Recommendations (generally available) surfaces the right agent at the right moment, directly in the flow of work.

When users prompt Microsoft 365 Copilot, the system analyzes their intent and suggests an agent that’s already installed and approved by IT. No special syntax or prompt engineering required.

These recommendations are assistive, meaning employees can choose to start a new conversation with the suggested agent or continue in their current chat. All the while, discoverability only happens within known, governed boundaries —mitigating the introduction of new risks. This helps employees quickly find agents purpose-built for the scenario at hand, while IT maintains a consistent governance model as usage expands.

Holding agents to your organization’s standards

As organizations rely on more agents for more impactful work, quality and reliability stop being nice‑to‑haves—they’re essential. Small changes to prompts, models, or data can introduce drift that can be hard to detect, especially as agent usage expands across teams and scenarios.

Agent Evaluations in Microsoft Copilot Studio (currently in public preview) gives you a structured way to answer the question: Is this agent actually doing what it’s supposed to do?

Evals work by running agents against authentic questions and scenarios, then generating objective scores for accuracy and intent alignment—so quality isn’t just assumed; it’s measured. By comparing results over time, teams can help catch regressions earlier, validate improvements, and apply a consistent quality bar before agents reach broader use.

These signals reinforce that agents aren’t set‑and‑forget automation; they’re managed enterprise workloads. With objective evidence in hand, IT and makers can make informed rollout decisions and scale agent usage more confidently, knowing behavior is monitored, and reliability can be improved as usage grows.

Learn how to set up Agent Evals in Microsoft Copilot Studio, so you can assess agent quality and readiness before expanding usage.

Make agents more capable while staying in control

Support for apps in agents, Agent Recommendations, and Agent Evals are designed to work together as a system, helping organizations move faster—without compromising trust. By treating agents as first‑class, governed workloads, IT teams can enable more capable agents while maintaining the control their organizations expect.

To get started:

• Learn how dev teams build with Apps SDK and MCP Apps
• Control agents from end-to-end with Agent 365
• Discover how to configure Agent Evals

The post Enable agents to bring apps into the flow of work—while keeping IT in control appeared first on Microsoft Copilot Blog.

Then, customers like you pushed us further.

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

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

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

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

Build more powerful agents with Copilot Studio

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

Let’s get started

Choose the right model to navigate dynamic interfaces

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

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

Secure authentication with built in credentials and Azure Key Vault

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

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

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

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

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

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

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

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

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

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

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

Beyond the monitoring pane, compliance is further strengthened through:

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

Simplify infrastructure with managed Cloud PCs for computer-using agents

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

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

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

Extend—don’t replace—your automation

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

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

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

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

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

Get started and help shape what comes next

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

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

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

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

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

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

Grok 4.1 Fast is a fast‑reasoning, text‑generation model (generation of images and other media types are not supported) that is designed for large context, deep tool use, and can be used to handle complex workflows. This addition reflects our ongoing commitment to give you more flexibility when designing and optimizing agents—so you can choose the right model for every business scenario.

Expanding our model line-up

Copilot Studio aims to give makers the ability to evaluate and use the model best suited to transform their business. With the addition of xAI Grok 4.1 Fast, we’re building on that commitment.

Alongside OpenAI and Anthropic models, xAI adds even more depth to your multi‑model lineup—while still keeping responsible AI principles at the center. Before rollout, every model in your Copilot Studio lineup goes through security, safety, and quality evaluations.

When using Grok 4.1 Fast in Copilot Studio, customer data is not retained or used to train xAI’s models. xAI’s models are hosted outside Microsoft-managed environments, and when you use Grok 4.1 Fast in Copilot Studio, your relationship with xAI will be independent of Microsoft and governed by xAI’s Enterprise Terms of Service and Data Protection Addendum.

Unlocking the power of model choice

Starting today, Grok 4.1 Fast is available in preview in early access environments, and is off by default. Your organization’s admin must explicitly opt in to use the model before US-based makers can build with it.

If an admin doesn’t opt in, nothing changes and makers keep their current model options. Existing agents continue running exactly as they do today.

Learn more about admin opt-in controls:

• Allowing external language models for generative responses
• How to connect to xAI’s models

Choice is everything

Build with confidence by choosing the model that fits your use case—and your goals—best.

Try Copilot Studio today

The post More choice, more flexibility: xAI Grok 4.1 Fast now available in Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.

Then, reality arrives.

The people who use the agent phrase questions differently. Conversations stretch across multiple turns. Context accumulates. Permissions prove table stakes. The right tools need to be invoked. Edge cases appear. Suddenly, the question becomes “can I actually trust how the agent behaves?”

Agent evaluations exist for this exact moment. AI agents do not behave the same way twice. Their responses shift with model updates, data changes, prompts, tools, and context. What works today may drift tomorrow.

Thankfully, agent evaluations reinforce confidence in the agents you build. Let’s walk through how you can make the most of this capability.

Transform your business

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

Try Copilot Studio today

What exactly are agent evaluations?

Agent evaluations (or “evals”) are the standardized mechanism that make agent variability visible and manageable. Unlike debugging, evals are not a one-time check or a manual review. It is a consistent process that helps you stay ahead of what could go wrong and improve agent performance over time.

By running evaluations, makers can launch agents into production knowing how they’ll behave, not how we hope they do. They can also ensure that an agent’s behavior remains stable over time.

As such, every maker should be evaluating all their agents. But this initiative can start with a few quick evaluations that require minimal setup, using default data and default grading to unlock quick signals.

However, as your agents mature, you’ll likely need to evolve this strategy, configuring additional evaluations that test behaviors in specialized scenarios.

Agent evaluation in 8 simple steps

Imagine you’re a maker that just built an internal human resources (HR) agent that helps employees understand leave policies, benefits, and when to escalate to HR systems.

Here’s how you’d evaluate this agent in Microsoft Copilot Studio, from deciding what to evaluate to understanding real-world behaviors and confidently iterating:

Step 1: Decide what you’re evaluating

Before you can run an evaluation, you need to be clear about what you’re trying to validate.

This starts with defining the scenario. What kind of behavior are we testing? What assumptions are we making about the user’s intent, the context, and the information the agent has available? A well-defined scenario sets the foundation for meaningful results.

With this information, you’ll need to define your scope. Some evaluations focus on a narrow behavior to get a precise signal. Others cover a wider range of interactions to reflect real usage. A narrower scope makes results easier to interpret, while a broader scope helps surface risks that only appear at scale.

You’ll need to make these choices deliberately. By explicitly defining the scenario and scope, evaluations produce signals that are relevant, reliable, and aligned with how you expect people to use the agent in practice. And it can impact the success of your evaluation.

Step 2: Ground evaluation in real user behavior

Once you’ve defined the scope, the next question emerges: “What are we evaluating against?”

Strong evaluations start with realistic data. Not idealized prompts, but the messy, imperfect ways people actually ask questions. For your HR agent, this includes vague phrasing, partial information, and mixed intents like asking about leave while referencing a personal situation.

You can bring data from multiple sources, including manually authored scenarios, AI-assisted generation to broaden coverage, imported datasets, and even historical or production conversations.

We recommend starting with a small but meaningful test set, focusing on the high-value scenarios that matter most to your business.

This data ensures that the evaluation inputs reflect real behavior, not the maker’s assumptions. But even with this data in place, you’ll likely ask: “How will this help me judge whether the agent behaved as expected?” This brings us to step three.

Step 3: Define your evaluation logic

Sometimes makers start with default grading to understand baseline behavior, before deciding what they want to measure more precisely.

Meanwhile, others define more specific grading logic upfront based on what they already know and what they want to validate.

Evaluation logic does not require full certaienty at the start. It provides a structured way to observe outcomes and refine what matters over time.

Makers can choose from a collection of ready-to-use graders and even combine multiple graders within a single evaluation to get a richer, multi-dimensional view of agent behavior.

For example, your HR agent configuration might include three separate graders:

1. General quality grader to assess whether the response is complete and addresses the full question.
2. Classification grader, where you describe the expected behavior as using natural language prompts.
3. Capability grader to confirm the agent uses the right topic or tool at the right time.

Even better, you can make these expectations explicit: what matters, what does not, and what “good behavior” looks like in this scenario. By defining evaluation logic upfront, you’ll reduce ambiguity, make success observable and explainable, and shift quality from subjective judgment to measurable signal.

Step 4: Set the right identity context

Once you’ve outlined what you’re testing, you need to define when the evaluation should run. Specifically, which user profile should the agent act like is sending the questions when it’s being evaluated?

The user context you select determines the agent’s behavior, including what data it can retrieve and reason over. It also ensures evaluations catch permission‑related risks early, such as inappropriate data access.

So, making this choice explicit helps avoid a common source of false confidence. When results are reviewed later, makers can trust that successes and failures are grounded in the same access boundaries their users will experience.

For example, an HR agent that references internal policy articles may behave very differently if it’s responding to a full-time employee or a contractor.

Running the evaluation under only the intended user identity ensures evaluation results reflect real conditions rather than an idealized setup. This can help you identify and mitigate unexpected behavior, such as sharing your company’s healthcare options with a contractor.

Step 5: Evaluate the agent’s responses

Now, it’s time to run your evaluation. Based on the data you provided, Copilot Studio simulates real user prompts and the agent generates responses, curated to your prescribed user context. Each configured grader then evaluates a different aspect of the response, such as quality, correctness, or capability.

This evaluation process turns individual answers into structured signals. Together, these signals make agent behavior observable, repeatable, and explainable at scale.

The maker is no longer relying on intuition or spot checks to assess their agent’s quality. They’ve created a disciplined feedback loop that replaces assumptions with evidence and transforms agent quality from a subjective impression into a measurable outcome.

Step 6: Step back to see the bigger picture

Once your evals gather sufficient signals, your focus shifts outward: “What does this tell me overall?”

Aggregated results provide a high-level view of quality, consistency, and trends across scenarios and graders. For the HR agent, this might reveal strong performance on common policy questions, but weaknesses around edge cases or escalation behavior.

With these signals, you can better prioritize. Not every failure matters equally. Patterns matter more than anomalies. And evaluation becomes a decision-support tool, not just a reporting surface.

Step 7: Investigate why single cases pass or fail

High-level signals are useful, but confidence is sturdiest when it’s grounded in the details.

When a maker drills into a specific test case, explainability comes to the foreground. They can see which grader triggered a failure, how the agent responded across turns, which knowledge sources it used, and whether it invoked the expected tool or topic.

This is often the turning point. Instead of guessing why something went wrong, you can finally understand what actually happened. Was the agent’s instructions unclear? Was the data incomplete? Did the agent confidently answer the prompt when it should have escalated it?

With this newfound understanding, you can make informed changes to your agent, adjusting instructions, data, or behavior based on what the evaluation revealed.

Step 8: Validate progress through comparison

Evaluation doesn’t end with a single run and a few gathered signals. Agents change over time. Instructions get updated. Data grows. Tools are added.

With evaluations as an always-on motion, you can compare runs. You can check whether things are improving and catch regressions early. This ongoing view helps your team answer a simple but critical question: “Are we actually getting better?”

For your HR agent, evaluations might confirm that an update made to the instructions reduced hallucinations without harming coverage. Confidence is no longer anecdotal. It is earned through evidence.

Make agent evaluations your confidence loop

Evaluations don’t slow you down. They accelerate progress. Each iteration builds understanding and offers clarity. Each run reduces uncertainty. And each comparison strengthens trust, empowering you to build with confidence.

That confidence is what encourages teams to move from test to production, and from promising prototypes to agents that can be relied on in real business scenarios at scale.

Ready to run your first agent evaluation? Get tactical guidance for configuring evals in Copilot Studio—complete with best practice evaluation methodologies.

New to Copilot Studio? Discover how you can transform your business by building, evaluating, managing, and scaling custom AI agents—all in one place.

The post How to evaluate AI agents in Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.

This model becomes even more powerful when applied to work. In Microsoft 365 Copilot, it connects to Work IQ to unlock insights, market research, and strategic planning—reasoning across your meetings, emails, docs, and more.

Microsoft 365 Copilot: Your AI assistant

GPT-5.2 is accessible in the model selector in both Copilot Chat and Copilot Studio, so you have the latest innovation to solve your unique business challenges and create more compelling agent experiences.

Want to see GPT-5.2 in Copilot in action? Select GPT-5.2 in the model menu in Copilot, and try one of these prompts:

• “Based on prior interactions with [person], give me 5 things that will be top of mind for our next meeting.”
• “Create side-by-side tables of the top 10 companies by market cap in 2000 and 2025. Then analyze the shifts in industry dominance, innovation cycles, and geopolitical trends—and connect any insight to implications for our 2025 strategic planning.”
• “Give me the top 3 strategic insights from today’s meeting, and show how they connect to our objectives and key results and upcoming milestones.”

Today’s launch of GPT-5.2 is just the latest in our continued commitment to offer model choice in Microsoft 365 Copilot—so our customers have access to the best models from a variety of model makers and can pick the model that’s best for the job at hand. Copilot delivers cutting-edge AI innovation, tuned for work and tailored to your business needs—with the security, compliance, and privacy that you expect from Microsoft.

Discover more with Microsoft 365 Copilot

Get started today

We’re excited to get you secure access to this innovative technology on the day of its release. GPT-5.2 will begin rolling out to users with a Microsoft 365 Copilot license today and is expected to reach all users in the coming weeks. Rollout to Microsoft 365 Premium subscribers will begin early next year.

GPT-5.2 in Copilot Studio is available starting today in early release cycle environments. Agents running currently with GPT-5.1 will automatically move to GPT-5.2.

Our team will continue to refine the experience based on your feedback as we build the future of work together.

Learn more about Microsoft 365 Copilot and Microsoft Copilot Studio and start transforming work with Copilot today. Learn more about GPT-5.2 from OpenAI here. For the latest research insights on the future of work and generative AI, visit WorkLab. 

The post Available today: GPT-5.2 in Microsoft 365 Copilot appeared first on Microsoft Copilot Blog.