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, visit the Copilot Studio website or sign up for our free trial today.

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

Security teams are already familiar with application risk, identity risk, and data risk. Agentic systems collapse those domains into one operating model. Autonomy introduces a new problem: a system can be “working as designed” while still taking steps that a human would be unlikely to approve, because the boundaries were unclear, permissions were too broad, or tool use was not tightly governed.

The OWASP Top 10 for Agentic Applications (2026) outlines the top ten risks associated with autonomous systems that can act across workflows using real identities, data access, and tools.

This blog is designed to do two things: First, it explores the key findings of the OWASP Top 10 for Agentic Applications. Second, it highlights examples of practical mitigations for risks surfaced in the paper, grounded in Agent 365 and foundational capabilities in Microsoft Copilot Studio.

OWASP helps secure agentic AI around the world

OWASP (the Open Worldwide Application Security Project) is an online community led by a nonprofit foundation that publishes free and open security resources, including articles, tools, and documentation used across the application security industry. In the years since the organization’s founding, OWASP Top 10 lists have become a common baseline in security programs.

In 2023, OWASP identified a security gap that needed urgent attention: traditional application security guidance wasn’t fully addressing the nascent risks stemming from the integration of LLMs and existing applications and workflows. The OWASP Top 10 for Agentic Applications was designed to offer concise, practical, and actionable guidance for builders, defenders, and decision-makers. It is the work of a global community spanning industry, academia, and government, built through an “expert-led, community-driven approach” that includes open collaboration, peer review, and evidence drawn from research and real-world deployments.

Microsoft has been a supporter of the project for quite some time, and members of the Microsoft AI Red Team helped review the Agentic Top 10 before it was published. Pete Bryan, Principal AI Security Research Lead, on the Microsoft AI Red Team, and Daniel Jones, AI Security Researcher on the Microsoft AI Red Team, also served on the OWASP Agentic Systems and Interfaces Expert Review Board.

Agentic AI delivers a whole range of novel opportunities and benefits. However, unless it is designed and implemented with security in mind, it can also introduce risk. OWASP Top 10s have been the foundation of security best practice for years. When the Microsoft AI Red Team gained the opportunity to help shape a new OWASP list focused on agentic applications, we were excited to share our experiences and perspectives. Our goal was to help the industry as a whole create safe and secure agentic experiences.

Pete Bryan, Principal AI Security Research Lead

The 10 failure modes OWASP sees in agentic systems

Read as a set, the OWASP Top 10 for Agentic Applications makes one point again and again: agentic failures are rarely “bad output.” But they are bad outcomes. Many risks show up when an agent can interpret untrusted content as instruction, chain tools, act with delegated identity, and keep going across sessions and systems. Here is a quick breakdown of the types of risk called out in greater detail in the Top 10:

Agent goal hijack (ASI01): Redirecting an agent’s goals or plans through injected instructions or poisoned content.

Tool misuse and exploitation (ASI02): Misusing legitimate tools through unsafe chaining, ambiguous instructions, or manipulated tool outputs.

Identity and privilege abuse (ASI03): Exploiting delegated trust, inherited credentials, or role chains to gain unauthorized access or actions.

Agentic supply chain vulnerabilities (ASI04): Compromised or tampered third-party agents, tools, plugins, registries, or update channels.

Unexpected code execution (ASI05): Turning agent-generated or agent-invoked code into unintended execution, compromise, or escape.

Memory and context poisoning (ASI06): Corrupting stored context (memory, embeddings, RAG stores) to bias future reasoning and actions.

Insecure inter-agent communication (ASI07): Spoofing, intercepting, or manipulating agent-to-agent messages due to weak authentication or integrity checks.

Cascading failures (ASI08): A single fault propagating across agents, tools, and workflows into system-wide impact.

Human–agent trust exploitation (ASI09): Abusing user trust and authority bias to get unsafe approvals or extract sensitive information.

Rogue agents (ASI10): Agents drifting or being compromised in ways that cause harmful behavior beyond intended scope.

For security teams, knowing that these issues are top of mind across the global community of agentic AI users is only the first half of the equation. What comes next is addressing each of them through properly implemented controls and guardrails.

Build observable, governed, and secure agents with Microsoft Copilot Studio

In agentic AI, the risk isn’t just what an agent is designed to do, but how it behaves once deployed. That’s why governance and security must span both in development (where intent, permissions, and constraints are defined), and operation (where behavior must be continuously monitored and controlled). For organizations building and deploying agents, Copilot Studio provides a secure foundation to create trustworthy agentic AI. From the earliest stages of the agent lifecycle, built in capabilities help ensure agents are safe and secure by design. Once deployed, IT and security teams can observe, govern, and secure agents across their lifecycle.

In development, Copilot Studio establishes clear behavioral boundaries. Agents are built using predefined actions, connectors, and capabilities, limiting exposure to arbitrary code execution (ASI05), unsafe tool invocation (ASI02), or uncontrolled external dependencies (ASI04). By constraining how agents interact with systems, the platform reduces the risk of unintended behavior, misuse, or redirection through indirect inputs. Copilot Studio also emphasizes containment and recoverability. Agents run in isolated environments, cannot modify their own logic without republishing (ASI10), and can be disabled or restricted when necessary (ASI07, ASI08). For example, if a deployed support agent is coaxed (via an indirect input) to “add a new action that forwards logs to an external endpoint,” it can’t quietly rewrite its own logic or expand its toolset on the fly; changes require republishing, and the agent can be disabled or restricted immediately if concerns arise. These safeguards prevent localized agent failures from propagating across systems and reinforce a key principle: agents should be treated as managed, auditable applications, not unmanaged automation.

To support governance and security during operation, Microsoft Agent 365 will be generally available on May 1. Currently in preview, Agent 365 enables organizations to observe, govern, and secure agents across their lifecycle, providing IT and security teams with centralized visibility, policy enforcement, and protection capabilities for agentic AI.

Once agents are deployed, Security and IT teams can use Agent 365 to gain visibility into agent usage, manage how agents are used, and enforce organizational guardrails across their environment. This includes insights into agent usage, performance, risks, and connections to enterprise data and tools. Teams can also implement policies and controls to help ensure safe and compliant operations. For example, if an agent accesses a sensitive document, IT and security teams can detect the activity in Agent 365, investigate the associated risk, and quickly restrict access or disable the agent before any impact occurs. Key capabilities include:

Access and identity controls alongside policy enforcement to ensure agents operate within the appropriate user or service context, helping reduce the risk of privilege escalation and applying guardrails like access packages and usage restrictions (ASI03).

Data security and compliance controls to prevent sensitive data leakage and detect risky or non-compliant interactions (ASI09).

Threat protection to identify vulnerabilities (ASI04) and detect incidents such as prompt injection (ASI01), tool misuse (ASI02), or compromised agents (ASI10).

Together, these capabilities provide continuous oversight and enable rapid response when agent behavior deviates from expected boundaries.

Keep learning about agentic AI security

Agentic AI changes not just what software can do, but how it operates, introducing autonomy, delegated authority, and the ability to act across systems. The shift places new demands on how systems are designed, secured, and operated. Organizations that treat agents as privileged applications, with clear identities, scoped permissions, continuous oversight, and lifecycle governance, are better positioned to manage and reduce risk as they adopt agentic AI. Establishing governance early allows teams to scale innovation confidently, rather than retroactively building controls after the agents are embedded in workflows. Here are some resources to look over as the next step in your journey:

OWASP Top 10 for Agentic Applications (2026): The baseline: top risks for agentic systems, with examples and mitigations.

Microsoft AI Red Team: How Microsoft stress-tests AI systems and what teams can learn from that practice.

Microsoft Security for AI: Microsoft’s approach to protecting AI across identity, data, threat protection, and compliance.

Microsoft Agent 365: The enterprise control plane for observing, governing, and securing agents.

Microsoft AI Agents Hub: Role-based readiness resources and guidance for building agents.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

OWASP Top 10 for Agentic Applications content © OWASP Foundation. This content is licensed under CC BY-SA 4.0. For more information, visit https://creativecommons.org/licenses/by-sa/4.0/

The post Addressing the OWASP Top 10 Risks in Agentic AI with Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.

Wave 3 of Microsoft 365 Copilot

Wave 3 marks a new version of Microsoft 365 Copilot, moving beyond assistance to embedded agentic capabilities. And this is just the start, with much more product innovation to follow in the months ahead.

Copilot Cowork

Working closely with Anthropic, we have brought the technology that powers Claude Cowork into Microsoft 365 Copilot. It’s this multimodel advantage that makes Copilot different. Your work is not limited by one brand of models. Copilot hosts the best innovation from across the industry and chooses the right model for the job regardless of who built it. This is a pattern of work that will only become more powerful as new models and ways of working emerge.

Copilot Cowork brings long‑running, multi‑step work into Microsoft 365 Copilot, moving beyond prompts and responses toward execution that unfolds over time. And, with Work IQ, it has the full context of your work, not just fragments of data, so it can reason over all relevant materials. Instead of asking Copilot to generate a single artifact, Cowork allows you to delegate meaningful work and stay in the loop as that work progresses.

With Cowork, Copilot can break down complex requests into steps, reason across tools and files, and carry work forward with visible progress and opportunities to steer. Tasks are no longer confined to a single turn or a single app. They can run for minutes or hours, coordinating actions and producing real outputs along the way.

Cowork is built with enterprise needs in mind. Work is observable. Actions are transparent. Documents are immediately enterprise knowledge that’s protected and ready to share. Progress can be reviewed, guided, or stopped. And everything operates within Microsoft’s security, identity, and governance framework, so organizations can adopt these capabilities with confidence.

By combining Anthropic’s agentic model for multi-step tasks with Microsoft 365, Cowork delivers a managed, enterprise‑grade experience that pairs powerful reasoning with the controls enterprises expect. This is the promise of Copilot: the best AI innovation from across the industry delivered quickly with the intelligence of Work IQ and trust of Microsoft’s Enterprise Data Protection. Cowork is being tested with a limited set of customers as a research preview and will be available through the Frontier program in March.

Join the Frontier program to get access to Microsoft’s latest AI innovations.

Microsoft 365 Copilot in Word, Excel, PowerPoint, and Outlook 

Today, many AI tools treat the creation of an artifact as a single-shot task. They connect to Microsoft 365 data but miss key context. They create content that doesn’t follow how apps natively work. They create version sprawl by producing files that are locally downloaded. And they do not respect the existing confidentiality protections within an organization.

Wave 3 of Copilot will now work alongside you in Word, Excel, PowerPoint, and Outlook, creating, editing, and refining high-quality content from start to finish inside a document, spreadsheet, presentation, or email. And it uses Work IQ to stay grounded in the context of your work, so edits always reflect what is current and relevant across your files, meetings, chats, and relationships.

Copilot does the heavy lifting by updating existing work: refining a Word document into a polished draft, improving Excel spreadsheets with real formulas, producing slides in PowerPoint that match how your organization builds decks—including understanding layouts, object styles, and brand kits— and drafting and refining emails directly in Outlook. And because this work happens inside the apps where people already work, every change is transparent, reviewable, and reversible as you iterate.

During preview, we described these capabilities as “Agent Mode.” As we moved toward general availability, it became clear that this isn’t a separate mode at all—it’s core to how this next wave of Copilot works.

Microsoft 365 Copilot enforces existing Microsoft 365 permissions and sensitivity labels and saves files to OneDrive and SharePoint—with tenant-level controls—so protected content isn’t processed when extraction isn’t allowed. This means organizations can apply governance, audit, compliance, and retention policies at scale.

These new Copilot experiences are generally available in Excel and Word, with PowerPoint and Outlook starting to roll out over the coming months.

Agents in chat

Not all work starts inside a document or an app. Often, it begins conversationally—with a question, an idea, or a rough intent that needs to be turned into action.

That’s why, in Wave 3, chat in Copilot is the entry point for chat‑first creation and execution. From chat, you can create documents, spreadsheets, and presentations directly from a conversation, or ask Copilot to take common workplace actions—like scheduling a meeting or drafting and sending an email to your team—without copying and pasting between tools or switching contexts. These end‑to‑end workflows move work forward immediately and set Copilot apart.

Chat in Copilot is where the ecosystem comes together. Built‑in agents for Word, Excel, PowerPoint, and Outlook let you move easily from conversation into app‑native work. And with agents in Copilot supporting open standards like Apps SDK and MCP Apps, your apps can now surface directly within chat—enabling live, interactive experiences where work actually happens. From sales and customer service insights in Microsoft Dynamics 365, to custom apps built with Microsoft Power Apps, to partner experiences from Adobe, Monday.com, and Figma, Copilot brings your critical tools and insights together in one place.

Copilot also makes it easy for people across your organization to build agents that support their day‑to‑day work using Agent Builder. Meanwhile, IT and business leaders can create more sophisticated business process agents with Microsoft Copilot Studio—from employee onboarding to procurement. Recent updates to Copilot Studio help organizations evaluate agent quality, coordinate multiple agents, and ensure agents work together across systems—while remaining observable, governable, and secure at enterprise scale. 

Copilot works directly inside apps when work is underway, and agents in chat provide the starting point when work begins with a conversation.

Excel, Word, and PowerPoint Agents are rolling out to generally availability in chat in Copilot. Schedule from chat and custom instructions are available today and send email from chat is rolling out with broad availability this spring. 

Multi‑model intelligence

Wave 3 also advances Microsoft’s commitment to model choice in Copilot, so intelligence can show up in the right way for the work at hand, without requiring you to think about models at all.

Many AI tools lock users into a single vendor’s models. Others force people to choose between tools, experiences, or modes depending on the task. That fragmentation creates friction for individuals and complexity for organizations. Leaders end up managing overlapping tools, inconsistent experiences, and rising costs as teams bring their own AI into the business.

At the same time, IT and business decision‑makers are forced into long‑lived vendor bets, even as the pace of model innovation accelerates and better capabilities emerge elsewhere. The result is broken context for users, unnecessary overhead for organizations, and the burden of model selection pushed onto people who just want to get work done.

In contrast, Microsoft 365 Copilot brings leading models from multiple providers directly into the work experience. With Wave 3, Claude is now available in mainline chat in Copilot via the Frontier program, alongside the latest generation of OpenAI models, which continue to roll out with new releases. This means users can access advanced reasoning and multistep capabilities in their everyday Copilot conversations, not just specialized tools. Copilot automatically applies the right model for the task, all grounded in your enterprise context and protected by Microsoft’s security and governance controls.

Agent 365

As organizations adopt agents as part of everyday work, the challenge shifts from experimentation to operating them with trust, safety, and control at scale. IDC projects agent use will increase by an order of magnitude over the next few years, with hundreds of millions—and soon billions—of agents operating across enterprises.¹ That scale creates a new dilemma for IT and security leaders: how to manage agents across the organization without rebuilding infrastructure, weakening security posture, or slowing innovation. This is exactly the scenario Agent 365 was designed for.

Agent 365 is the control plane for agents. In practical terms, it gives IT and security leaders one place to observe, secure, and govern every agent across the organization, and it provides the confidence to move from agent experimentation to enterprise-scale operations. Agent 365 extends the management, security, and governance processes organizations already use for employees to agents, so they can stay in control as agents become part of daily work.

The idea is simple: there is no need to reinvent the wheel. The fastest path to getting agents under control is to manage them in a similar manner to managing users, using familiar Microsoft solutions including the Microsoft Admin Center for agent management and Microsoft Security solutions like Defender, Entra, and Purview for agent security and governance.

Agent 365 will be generally available on May 1, priced at $15 per user per month.

Introducing Microsoft 365 E7: The Frontier Suite

Frontier transformation is real when both sides of the system move together: people and AI operating across the enterprise.

Microsoft 365 E7: The Frontier Suite closes the gap, equipping employees with AI across email, documents, meetings, spreadsheets, and business application surfaces, while giving IT and security leaders the observability and governance needed to operate AI at enterprise scale.

Copilot and agents work together with shared intelligence, understanding context, history, priorities, and constraints. Trust is built in by default—with user data, enterprise data, and agent actions protected through identity, policy, and observability—so AI can scale across the workforce without compromising security or compliance.

Microsoft 365 E7 will be available for purchase on May 1 at a retail price of $99 per user per month, and includes Microsoft 365 Copilot, Agent 365, Microsoft Entra Suite, and Microsoft 365 E5 with advanced Defender, Entra, Intune, and Purview security capabilities to help secure users, delivering comprehensive protection across agents and users.

Get started today

Wave 3 of Microsoft 365 Copilot marks a turning point in how AI shows up at work. Agentic capabilities are embedded directly into Word, Excel, PowerPoint, Outlook, and Copilot Chat, bringing multi‑model intelligence into everyday workflows. Agent 365 makes this shift operational by giving organizations a way to observe, govern, and secure agents as they move from experimentation to enterprise‑scale use. Microsoft 365 E7 brings it all together by unifying productivity, AI, identity, and security into a single foundation.

Together, these changes make frontier transformation real: intelligence that understands the context of work, and trust that allows AI to scale safely across the workforce. When intelligence and trust move together, AI stops being an experiment and starts becoming how work gets done.

• Visit Microsoft365.com/copilot or download the Microsoft 365 app on your mobile device to get started.
• For the latest research and insights on AI at work, visit WorkLab.
• Learn from our engineering leaders how Microsoft delivers AI built for work at the Microsoft Frontier Transformation digital event on March 9, 2026, at 8:00 AM PT.

Footnotes

Microsoft 365 E7 is available with and without Teams.

¹IDC Info Snapshot, sponsored by Microsoft, 1.3 Billion AI Agents by 2028, May 2025 #US53361825

The post Powering Frontier Transformation with Copilot and agents 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.

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.

The post New and improved: Agent evaluations, computer use, and advanced maker training 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.

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

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.

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.

What you can do with the Copilot Studio extension for Visual Studio Code

As agents grow beyond a few topics and prompts, teams need the same development hygiene they use for apps: source control, pull requests, change history, and repeatable deployments. The VS Code extension brings that workflow to Copilot Studio so makers and developers can collaborate without losing governance or velocity.

The extension supports a simple loop that fits naturally into your SDLC:

1) Clone an agent to your local workspace

Pull the full agent definition from Copilot Studio into a folder on your machine, so you can work locally with the full context of your agent.

2) Edit confidently in VS Code

Make changes to your agent components (topics, tools, triggers, settings, knowledge references) using a structured agent definition format and your existing VS Code workflow. The extension also provides IDE help like syntax highlighting and IntelliSense-style completion so edits are faster and less error-prone.

3) Review changes before they land

Preview what changed, compare cloud vs local, and resolve conflicts before you apply updates. This helps teams avoid overwriting each other’s work and makes collaboration practical at scale.

4) Apply changes back to Copilot Studio

Sync your updates to the cloud to test behavior and create evals as part of your normal iteration loop.

5) Deploy with the processes your team already uses

Use standard Git workflows and integrate agent definitions into automated deployment processes. This is the missing piece for teams that want agents to move through environments with the same rigor as code.

Built for development teams

The extension is designed for the way engineering teams actually work:

• Standard Git integration for versioning and collaboration
• Pull request-based reviews so changes are discussed and approved
• Auditability over time, with a clear history of modifications
• VS Code ergonomics: keyboard shortcuts, search, navigation, and a local dev loop

This extension is especially helpful if you:

• Manage complex agents with many topics and tools and need fast search and navigation
• Collaborate with multiple people and need PR workflows for safe changes
• Want agent definitions in source control and environment sync through DevOps pipelines
• Prefer building with your IDE plus an AI assistant for faster iteration

Develop Copilot Studio Agents using GitHub Copilot  

The Copilot Studio extension for Visual Studio Code lets you build and refine your Copilot Studio agent with AI help in the same place you write code. Use GitHub Copilot, Claude Code, or any VS Code AI assistant to draft new topics, update tools, and quickly fix issues in your agent definition, then sync changes back to Copilot Studio to test and iterate. The result is a faster inner loop with fewer context switches and a workflow that fits how development teams already work.

Get started

1. Install the extension from the Visual Studio Marketplace
2. Clone your first agent from Copilot Studio
3. Make a small change locally
4. Use Apply Changes to sync back to Copilot Studio and test

Learn more and share feedback

We built this extension so agent development can feel like the way software teams already work: in your editor, with source control, and with AI help when you want it. Try it in your next agent update and let us know what you want to see next!

• Learn more in Copilot Studio docs
• GitHub issues and feedback

The post Copilot Studio extension for Visual Studio Code Is now generally available 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.

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