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.

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.

To help teams like yours answer these complex questions faster and move with confidence, we’ve launched the new agent architecture guidance hub and a refreshed Microsoft Copilot Studio guidance hub. These on-demand resources offer end‑to‑end documentation across the agent lifecycle—from design and planning through operations, governance, and advanced architectural patterns.

Built on established practices from Microsoft engineering teams and real‑world deployments, these hubs give architects, developers, and IT a shared blueprint to work from. And they were designed to help your team make smarter architectural decisions, accelerate delivery with practical how‑to guidance, and scale safely with trusted governance, security, and responsible AI practices.

Whether you’re building your first agent or scaling across your enterprise, these hubs can help you start—and stay—on the right path.

Now, let’s explore what each hub offers and how to put them to work for your organization.

Meet the new agent architecture guidance hub

The new agent architecture guidance hub is a technology‑agnostic playbook for designing secure, reliable, and accountable agents. Unlike the Copilot Studio guidance hub and Azure Well‑Architected guidance, this hub focuses on the principles and patterns required to build scalable agent systems—regardless of platform, tools, or runtime.

Grounded in the same practices Microsoft 365‑grade agents use, this hub distills lessons from real‑world deployments into a single source of truth. It provides clear answers to foundational architecture questions, such as how your agents should be structured, how they should run, and how they should be governed at scale.

Use the agent architecture guidance hub to:

• Identify fit for purpose by mapping your scenario to the right agent flows, components, and reference architectures.
• Design for operability by building reliability in from the start, using deployment lifecycle and evaluation guidance.
• Establish trust, traceability, and transparency through responsible AI practices, governance, auditability, and security practices.
• Optimize search and tool‑use patterns by adopting retrieval, grounding, and tool‑execution approaches used in Microsoft 365 Copilot.

Discover the redesigned Copilot Studio guidance hub

The reimagined Copilot Studio guidance hub is your end‑to‑end playbook for designing, building, and operating agents in Copilot Studio. Unlike architecture‑level resources, such as the agent architecture guidance, this hub focuses on hands‑on implementation—so makers, developers, and IT admins know exactly how to execute their work inside the product.

The newly reorganized and expanded hub now mirrors the full lifecycle of an agent. It’s built around five practical stages—Plan, Implement, Manage, Improve, and Extend—so your team can quickly find the right guidance at the right moment, whether you’re starting fresh or scaling an existing deployment:

• Stage 1: Plan. Align on business goals, define success measures, apply responsible AI considerations, and design effective language understanding before building anything. This helps to ensure every agent starts with a clear purpose, measurable outcomes, and a responsible foundation.
• Stage 2: Implement. Focus on the design and build work inside Copilot Studio. Learn generative orchestration patterns, build topics effectively, integrate systems and APIs, and publish agents with confidence using patterns established to work in production.
• Stage 3: Manage. Operate agents with governance, ALM, capacity planning, project security, testing guidance, and compliance best practices. This stage helps teams define the guardrails and decisions needed to maintain trust, reliability, and control over time.
• Stage 4: Improve. Center continuous optimization around analytics, KPIs, and conversation insights to drive measurable improvements in accuracy, containment, deflection, and user satisfaction—turning real usage data into targeted enhancements.
• Stage 5: Extend. Go beyond out‑of‑the‑box capabilities with hands‑on extension guidance. Use the Copilot Studio Kit and work with the Microsoft 365 Agents SDK to add custom logic, actions, and richer workflows tailored to your organization’s unique scenarios.

Together, these stages make this hub a practical, step-by‑step playbook for building agents in Copilot Studio that are useful, safe, and maintainable from day one—and that can scale as your needs grow.

Build agents with confidence

Successful agents require more than a powerful platform—you also need clearer choices, practical guardrails, and a way to spend less time reinventing the wheel. The new agent architecture guidance hub and Copilot Studio guidance hub (together with our other resources like the Copilot Studio adoption site and Copilot Studio community forum) make it easier to go from early experiments to confident, repeatable delivery.

Use the agent architecture guidance hub to clarify what to build and why. Then, turn to the Copilot Studio guidance hub when you’re ready to design, build, and operate those agents more effectively in Copilot Studio.

Whether you’re experimenting with your first agent or managing a collection of agents in Microsoft Copilot Studio, put these resources to work to make your next build easier, safer, and faster.

The post New resources and guidance to plan, build, and operate enterprise-ready agents 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.

This shift marks the moment AI moved from helping people do work faster to helping organizations optimize their workflows.

Microsoft Copilot Studio has played a central role in this transition. It gives you more flexibility to evaluate and use the models best suited to your business as agent adoption scales.

In 2025, we laid the groundwork for what scalable, impactful agentic work should look like. In 2026, we believe the organizations that benefit most will be the ones that build on that foundation. These six trends define what organizations need to make agent adoption stick in 2026 and beyond:

1. Ability for anyone to turn intent into agents
2. Agents that can own workflows from end to end
3. Power to coordinate agents for real outcomes
4. Flexibility to control your agent models
5. Agents that can act across your systems
6. Capability to scale agents without sacrificing control

Organizations that have all six aren’t just experimenting with agents. They’re operationalizing them, turning curiosity into confidence, and transmuting innovation into sustained business value.

1. Ability for anyone to turn intent into agents

Historically, building an agent meant translating business intent into technical instructions. This process slowed adoption and limited who could participate. In 2025, that barrier fell away. Conversation became the agent-making interface in both Copilot Studio and the Agent Builder in Microsoft 365 Copilot Chat. Now, people can describe what they want done using natural language and create an agent to do it. These agents can interpret intent, context, and goals thanks to their underlying model and knowledge, not specially built code.

That shift is designed to empower everyone on your team to build agents. Sales leaders, operations managers, and human resource (HR) officials no longer need to wait for technical assistance to automate everyday work. Meanwhile, IT teams retain clarity and structure under the hood, with agents grounded in logic that can be reviewed, refined, and governed—all in Copilot Studio.

The results? Faster fast agent creation, broader participation, and fewer translation gaps between business needs and technical execution.

For example, a sales operations manager can now describe and publish an agent that:

• Monitors pipeline changes, such as changed estimated close dates.
• Flags deals that may be at risk, based on predefined criteria (e.g., no activity with stakeholders for over a month).
• Notifies account owners with recommended next steps based on the type of flag.

The payoff: More people can build knowledgeable, context-aware, and helpful agents, which can translate to less bottlenecking on centralized teams and faster time to value.

2. Agents that can own workflows from end to end

For many teams, early adoption wins came from AI assistance: drafting content, summarizing meetings, answering questions. Useful, but incremental. In 2025, agents crossed an important threshold; they evolved from helping with work to handling it on your behalf. With agent flows and the Workflows Agent, agents can now own repeatable processes from end to end, automatically advancing work when required.

In other words, agents unlock new opportunities to streamline and scale how work gets done. An onboarding process no longer stalls due to a missed handoff. A request doesn’t linger in a queue waiting for manual follow-up. Agents move work along reliably with automated approvals, escalating to humans only when judgment is required. For leaders, that can mean faster cycle times and fewer hidden bottlenecks. For teams, it can translate to more time spent on decisions—not coordination.

For example, a company could use Copilot Studio to automate a multi-step process for expense submission, validation, and reimbursement. The process:

• Triggers when an employee submits a wellness or reimbursement request.
• Guides the employee through required forms and documentation in a single, user-friendly flow.
• Validates submissions against global wellness policy rules and regional guidelines.
• Routes requests across the appropriate software as a service (SaaS) tools and internal HR systems.
• Escalates exceptions to a human only when needed.

The payoff: Faster resolutions using consistent criteria, less potential for human error, and a daily pain point made smoother with an agent.

3. Power to coordinate agents for real outcomes

Often, meaningful business outcomes don’t happen in a single step or system. As soon as agents move beyond simple tasks, coordination becomes increasingly challenging. Multi-agent systems addressed this complexity head-on in 2025, allowing agents to specialize, delegate, and collaborate toward shared goals.

Instead of designing one agent to handle every step, organizations can now compose agents that mirror how teams already work. One agent might monitor signals, while another gathers or validates information, and a third prepares recommendations or takes action.

Together, these agents are designed deliver outcomes that would be difficult for any single agent to manage alone. More importantly, they remove a layer of decision-making from the stakeholder. Instead of figuring out which system or agent holds the right answer, you can simply ask your question and let the agentic system coordinate the rest. Complex workflows become easier to reason about, evolve, and scale—without adding mental overhead for the people involved.

For example, a manufacturing company might use:

• One agent grounded in internal policy and safety documentation.
• Another agent trained on equipment manuals and training materials.
• A third agent connected to supplier-provided expertise.
• A coordinating agent that evaluates each question and routes it to the right source automatically.

The payoff: More clarity around which system or agent to use—just ask, and the right expertise can come together behind the scenes. This can help keep complex work cohesive, not cobbled together.

4. Flexibility to control your agent models

As agents moved into real business workflows, one reality became clear: not every task has the same requirements or permissions. Some scenarios call for deeper reasoning. Others prioritize repeatability and efficiency at scale. Still, others must meet strict regulatory, security, or data residency standards.

In 2025, Copilot Studio expanded model choice to meet those needs. It now supports Anthropic models, chat and reasoning-specific models, access to thousands of models through Microsoft Foundry, and bring-your-own-model options. You can select the right model for each workload while IT teams maintain policy alignment and oversight. This gives your organization flexibility in how agents behave and perform, without fragmenting the experience.

For example, an organization in a regulated field might use:

• One model optimized for policy interpretation and complex reasoning.
• Another tuned for cost efficiency in high-volume, repeatable requests.
• Central governance to ensure each model is applied appropriately.

The payoff: Instead of compromising between performance and compliance, agents can be configured to match the realities of the work they support—and evolve as those requirements change.

5. Agents that can act across your systems

For years, AI has been good at suggesting what people should do, but it hasn’t been equipped to help make it happen. In 2025, capabilities like Model Context Protocol (MCP) and computer use began to close that gap. Agents can now connect to systems, navigate interfaces, and take action across tools—not just give recommendations.

This addresses one of the biggest gaps in early AI adoption by reducing the handoffs that drastically slow work. When agents can act across environments to update records, trigger workflows, and interact with real systems (like clicking around a website and filling out form fields), work moves forward automatically, at any time of day. This can help reduce delays, manual errors, and the risk that important follow-ups get lost between tools or teams.

For example, an operations agent could autonomously:

• Identify a supply issue based on predefined signals.
• Update the system of record with the latest status.
• Fill out and file a ticket to initiate remediation.
• Notify relevant stakeholders with context and next steps.

The payoff: Faster response times, fewer handoffs, and agents that operate across real-world systems, not just chat windows.

6. Capability to scale agents without sacrificing control

Widespread agent adoption raises a familiar concern: How do you prevent innovation from outpacing governance? Leaders want to move quickly, but not at the expense of visibility, security, or cost control. In 2025, Copilot Studio addressed that gap by bringing lifecycle management, agent evaluations, and enterprise controls directly into the agent experience.

Organizations can now understand which agents are in use, how they’re performing, and what they cost across environments. Admin controls are designed to align agent behavior with intended use, while agent evaluations support ongoing quality and improvement. Paired with Microsoft Agent 365, organizations get a unified view of agents across Microsoft 365 Copilot and Copilot Studio, giving business and IT leaders the clarity needed to scale with confidence.

For example, IT leaders can:

• See which agents are used, by whom, and at what cost.
• Evaluate agent quality and performance over time.
• Communicate performance insights to business leaders to help increase buy-in, investment, and adoption.
• Apply consistent governance without slowing innovation.

The payoff: Agents can move from pilots to production faster, with fewer surprises and clearer business impact.

How to turn agentic momentum into results

The question for 2026 isn’t whether agents will be used—it’s how deliberately they’ll be put to work. Over the past year, the foundations for scalable agent adoption came together. The opportunity now is to move from experimentation to widespread execution.

We believe organizations that’ll get the most value in the year ahead will do three things consistently:

1. Broaden who builds by empowering business teams to create and refine agents in partnership with IT teams, who provide guardrails without stifling creativity.
2. Standardize how agents are shared and reused, so successful patterns move beyond individual productivity into team and enterprise workflows.
3. Measure what matters as a matter of course, using visibility into usage, quality, and cost to guide where agents are expanded, improved, or retired.

When business and IT teams operate from the same foundation, agents stop being side projects and start becoming part of how work happens. That’s how teams move faster, reduce rework, and work together with AI and automation to create true business transformation.

Where to start—and how to go further

Your best agentic year isn’t defined by how many agents you build, but by how many people rely on them to get work done. Copilot Studio gives you the foundation to do exactly that. Now, 2026 is about building out, driving adoption, and scaling up.

Try this three-step plan for building and scaling your agent strategy with Copilot Studio:

1. Get quick wins. Start by focusing on business-to-employee (B2E) assistive agents. Try downloading the Employee Self-Service Agent from the Agent Store.
2. Create a Center of Excellence (COE). Set up a central team that can help triage cross-team needs and get the broader organization comfortable with agents. This could be a representative from every department, or made up of agent champions (regardless of where they sit in their org). A great COE can help reduce geographic silos and bring consistency to an AI strategy.
3. Measure and reward adoption. What gets measured gets focus and investment. Compare the situation today with the situation post-agent adoption. Did the agent provide value? Has it improved what you set out to change? Prove the progress, and then you can move onto the next process.

Get started today and turn agent curiosity into capability, confidence, and commitment this year.

The post 6 core capabilities to scale agent adoption in 2026 appeared first on Microsoft Copilot Blog.

Today’s leading organizations are going through an agentic business transformation. This change takes AI from concept to measurable impact, by automating existing workflows and using agents to enhance productivity and reinvent entire functions. Copilot Studio, Copilot’s agent platform, provides a fully managed solution for accomplishing this.

Using Copilot Studio, organizations around the world can quickly bring the benefits of AI to their business. Copilot Studio empowers companies to streamline and automate their processes with agentic workflows, create single-purpose agents to solve specific problems, and develop multi-agent solutions that drive measurable business outcomes at scale. The result: a scalable, secure, and governable foundation that supports the needs of IT administrators and business owners measuring return on investment (ROI). This system accelerates agentic transformation by delivering speed-to-value without sacrificing quality or control.

At the same time, with Microsoft 365 Copilot, users can easily use AI to improve their personal and team productivity. This tailored experience for Microsoft 365 Copilot users offers a fast, guided way to set up agents to support your work and automate everyday tasks, removing them from your plate.

Today, we’re excited to share new capabilities in Copilot Studio that support all of these scenarios and groups that use our product, making it easier for makers and administrators to shape agent behavior, enforce organizational standards, and extend functionality with AI.

End-user improvements

Our Copilot Studio experience for building agents and workflows, as well as our agent building capabilities in Microsoft 365 Copilot, continue to support agent creation for all users, from professional makers and IT administrators doing enterprise AI transformation, to employees building agents and workflows for their personal use. Recent updates focus on making the process simpler and more efficient.

What’s new in Microsoft 365 Copilot

• Redesigned creation experience: Build and refine agents through an improved conversational interface that guides users and taps into an expanded set of work-related knowledge sources.
• File generation with natural language: Agents built in Microsoft 365 Copilot, can now create Word, Excel, and PowerPoint files in seconds using natural language commands.
• Seamless upgrade path: Copy agents from Microsoft 365 Copilot to Copilot Studio in one click, unlocking advanced AI agent customization.
• Workflows agent in Microsoft 365 Copilot: Create, build, and manage workflows using natural language in chat. Boost productivity with quick scenarios like daily triage, weekly digests, and lightweight approvals—all directly within Copilot.

Maker improvements

IT application developers and other professional makers in the business can already build sophisticated agents in Copilot Studio without needing to code. Copilot Studio includes capabilities such as connecting and acting across more than 1,400 systems of record via Model Context Protocol (MCP), Power Platform connectors, and the Microsoft Graph. It also includes broad and deep tooling like autonomously writing and executing code, delivering rich out-of-the-box agent analytics and ROI measurement, and more, all built on the Microsoft governance and security platform. We’re excited to share new capabilities that give makers even more flexibility and control to design enterprise agents tailored to their unique organizational needs.

• Choose your own model: Select from leading options like OpenAI’s GPT‑5, Anthropic’s Sonnet 4.5, and Opus 4.1 to power your agents. This empowers you to tailor agent intelligence to fit your specific business scenario, optimize performance, experiment with new capabilities, and deliver agents that meet your organization’s unique needs.
• Ensure agents are ready for launch, and don’t regress over time, with Evaluations: Built-in evaluation tools help you test agents against real-world scenarios, compare versions, and track performance with clear metrics. Evaluations can give teams greater confidence that their investments are performing as expected.
• Computer use: Agents can now automate tasks across apps and websites, using secure Windows 365 experiences—from hosted browsers for quick web automation to IT-managed Cloud PC pools for rapid scalability.

Admin improvements

As agents become central to automating work and transforming workflows, Copilot Studio is introducing new governance and protection capabilities designed to help organizations maintain strong oversight.

• Expanded agent analytics: Clear insights into connected and child agent performance, detailed visibility into Copilot Credits consumption and limits, AI-generated summaries of top analytics insights, and interrogating analytics using natural language.
• Real-time protection: Copilot Studio integrates with Microsoft Defender and other trusted security platforms, providing continuous monitoring and protection against threats like prompt injection—helping every agent run more safely.
• Microsoft Entra Agent ID: Every agent made in Copilot Studio now gets a unique Microsoft Entra Agent ID, making it simple to register, manage, and govern your entire agent fleet.

Agent 365 and Copilot Studio: Unified control for agents

Agents are handling more responsibilities across enterprise operations and Copilot Studio is your launchpad for building them. With the introduction of Agent 365—the control plane for agents, the rich governance and management capabilities we offer today including sharing controls, advanced connector policies, agent inventory, zoned environment management, and more, will also be surfaced in the Agent 365 platform when using agents built in Copilot Studio.

Additionally, in Copilot Studio, makers can now build agents that use the new Agent 365 MCP servers. These servers allow agents to schedule meetings in Microsoft Teams, draft documents in Word, send emails in Outlook, and update customer relationship management (CRM) records in Microsoft Dynamics 365. This supports delivery of intelligent, compliant workflows and agents with built-in audit trails and granular policy enforcement—all from one platform.

Agent 365 is available starting today in Microsoft 365 Admin Center with Frontier, Microsoft’s early access program for the latest AI innovations.

Scale to the Frontier Firm with control

True transformation happens when agents are built for scale, governed for compliance, and measured for impact. Copilot Studio delivers that foundation, so organizations can build enterprise multi-agent systems, automate workflows with precision, and reimagine processes while minimizing risk.

EY’s results show what’s possible when you invest in a comprehensive agent platform, built on Microsoft. They are just one of many enterprise organizations implementing agents with Copilot Studio. In this case, their PowerPost Agent built on Copilot Studio led to major improvements in journal processing:

• 95% reduction in lead time
• 37% cost savings¹

Implementing the PowerPost Agent with Microsoft Copilot Studio has fundamentally transformed our journal processing. What once took minutes now happens in seconds—streamlining workflows and improving accuracy.

—Paula Korczak, Product Manager for General Ledger, EY

That’s the difference between cobbling together siloed agent platforms versus investing in a managed scalable agent platform like Copilot Studio: agents and agented process design that is repeatable, auditable, and scalable.

Get started today

To learn more about Copilot Studio and how it can transform your organization’s productivity, visit the Copilot Studio website and sign up for a free trial today. Take the Agent Readiness Assessment to benchmark your organization’s agent maturity across five critical areas—strategy, data, process, culture, and security—and get a personalized report to accelerate scalable agent adoption and drive agentic business transformation.

Want to explore all of Copilot Studio’s adoption content? Visit the Copilot Studio adoption page.

¹ EY redesigns its global finance process with Microsoft Power Platform

The post Why Microsoft Copilot Studio is the foundation for agentic business transformation appeared first on Microsoft Copilot Blog.

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

Build and optimize agents

Validate agents at scale with evaluations for automated testing

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

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

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

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

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

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

Build with the latest OpenAI models in Copilot Studio

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

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

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

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

Speed up agent flow execution with express mode

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

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

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

Enable file uploads in omnichannel conversations

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

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

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

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

Access external files and data with Model Context Protocol resources

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

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

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

Measure and improve performance

Measure the return on investment (ROI) for conversational agents

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

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

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

Analyze user questions by theme

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

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

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

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

Test and debug faster with an improved activity map

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

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

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

Manage and govern at scale

Control org-wide sharing of agents in Copilot Studio lite

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

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

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

Stay up to date on all things Copilot Studio  

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

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

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

Today, we are announcing the public preview of Agent Evaluation in Microsoft Copilot Studio, bringing rigor directly into the agent-building tool you already use, backed by Microsoft’s end-to-end approach.

Introducing Agent Evaluation

Agent Evaluation enables structured, automated testing directly in Copilot Studio, providing makers with a direct and seamless way to create evaluation sets, choose test methods, define success measures for the agent, and then run the test—maximizing the power of model choice that Copilot Studio offers by evaluating agent performance across multiple agent-level models.  

Create evaluation sets

Makers can now upload predefined test sets, reuse recent Test Pane interactions, and add test questions manually. We are also enabling AI-powered generation of test queries from the agent’s metadata, knowledge sources, and more—delivering makers with quick visibility into agent quality without requiring the manual work for expected answers. This allows for early testing, while additional Q&A sets can be manually added for deeper evaluation. 

Makers can also mix AI-generated queries with manual or imported test sets to expand coverage, helping to evaluate both breadth (common scenarios auto-generated by AI) and depth (organization-specific queries) of agent behavior.

Choose flexible test methods

Makers can choose from a wide rage of test methods—whether it is exact or partial matches, advanced similarity metrics, intent recognition, or relevance and completeness, makers can choose the test methods that work for them based on the type of agent they are deploying. This allows makers to mimic how different users judge the agent—from strict checklist compliance to overall helpfulness—giving a comprehensive view of performance.

Define measures of agent success  

Agent Evaluations allows you to define what constitutes success for your business, whether it is strict keyword matches (lexical alignment) or conceptual, meaning-based matches (semantic alignment). You can also set custom thresholds to ensure your agent meets your organization’s unique standards for accuracy and relevance.

Execute evaluations

Once the dataset is prepared, test methods are chosen, and thresholds are configured, evaluations are executed with a single click. Results are displayed with clear pass or fail indicators, numeric scores on answer quality, and details around the knowledge sources used by the agent. No more guessing as to why an answer failed.

Transforming agent quality: From build to continuous improvement 

Agent Evaluation transforms agent development into a full lifecycle of build, test, and improve. We want makers to have the same rigorous and streamlined quality process for agents as they do for traditional software. By launching evaluations in Copilot Studio, we’re ensuring that every agent can be tested and continuously improved, leading to well-tested agents deployed across the organization. This also enables makers to test agents using different agent-level models for agent orchestration, to find the model that best suits the business process being transformed. You can go from building an agent to testing it in the same interface, all while being confident in Microsoft enterprise-grade permission controls, compliance, and governance capabilities.

Next steps 

To learn how to get started, visit Agent Evaluation in Copilot Studio. 

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

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

We look forward to sharing more about Agent Evaluation at the Power Platform Community Conference 2025.

The post Build smarter, test smarter: Agent Evaluation in Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.

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

Build richer agent experiences in Copilot Studio 

Automate UI tasks with computer use, now in public preview 

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

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

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

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

Engage customers on WhatsApp, now generally available 

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

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

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

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

Test and enrich prompts in the prompt builder 

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

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

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

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

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

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

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

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

Create reusable component collections 

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

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

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

Enable end users to upload files during agent interactions 

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

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

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

Extend and customize with advanced tools 

Unlock advanced scenarios with code interpreter, now generally available 

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

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

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

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

Integrate Copilot agents into native apps with the Agents Client SDK 

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

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

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

Create MCP connectors directly in Copilot Studio 

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

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

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

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

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

Manage and measure agents at scale 

Manage agent billing with a dedicated environment in Copilot Studio lite 

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

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

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

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

Analyze agent performance and measure impact with new metrics 

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

Themes for generative AI questions in public preview

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

Insights for unanswered generative AI questions in public preview

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

Agent monthly consumption limits (general availability) 

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

Active users metric (general availability)

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

ROI analysis for agent runs (general availability)

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

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

Upskill with agents 

Build your skills with Copilot Studio Agent Academy 

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

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

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

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

Stay up to date on all things Copilot Studio  

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

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

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

This capability enhances security for AI agents by enabling organizations to connect their own monitoring system such as Microsoft Defender as well as security platforms by other providers, or their own custom-built tools. These integrations allow for real-time evaluation and control of agent behavior during runtime.

When connected, the external systems become part of the agent’s decision-making process. They can block unsafe actions, even if the agent plans to execute them. For example, if the external system determines that the agent is planning to send an email that is oversharing information, it can block the email from being sent.

Admins can apply these protections across multiple agents and environments using the Power Platform Admin Center – no code required.

Copilot Studio agents: secure by default

AI agents face unique threats. One major risk is injection of prompts to the agent from an external source (also known as cross prompt injection attacks, or XPIA), where malicious prompts trick agents into leaking data or misusing tools. Copilot Studio includes default protections against both XPIA and user prompt injection attacks (UPIA). These defenses block suspicious prompts in real time, reducing the risk of data loss or unauthorized actions.

However, for organizations with advanced security needs, built-in protections may not be enough. That’s where the real-time protection comes in with an additional layer of defense.

Real-time protection in action

With advanced runtime protection, Copilot Studio calls the connected security system during the agent’s runtime. The system reviews the agent’s planned actions and decides whether to approve or block them. If it detects a threat, it stops the agent immediately and notifies the user. If the action is safe, the agent continues without delay or disruption.

This setup gives organizations stronger control over agent behavior while preserving a smooth user experience. It supports a “bring your own protection” model, allowing integration with:

• Microsoft Defender (available today – learn more)
• Third-party security providers
• Custom-built monitoring tools

This flexibility helps organizations align security for AI agents with internal policies, industry standards, and regional compliance.

Instant alerts, actionable logs

In addition to the ability to block threats before they happen, Copilot Studio creates detailed audit logs for every interaction with the external system. Admins can use these logs to track attempted breaches, identify vulnerable agents, and improve future deployments.

These logs also help evaluate how well the external monitoring system performs. Admins can analyze trends, refine policies, and guide agent creators in building more secure agents. This feedback loop strengthens overall security for AI agents.

How advanced real-time protection works

When a user sends a prompt, the agent formulates a plan to respond. This plan includes the tools and actions it will use. Before the agent begins execution, Copilot Studio sends this plan to the external monitoring system via an API call. The data includes:

• The user’s prompt and chat history
• Tool details and input values
• Metadata like agent ID, user ID, and tenant ID

The external system has one second to respond. If it approves the action, the agent proceeds. If it blocks the action, the agent stops and informs the user. If no response arrives in time, the agent assumes approval and continues.

Setup and management

Admins can configure external monitoring in the Power Platform Admin Center. They can apply settings to one environment, multiple environments, or specific environment groups. Different environments can use different monitoring systems. If needed, admins can disable the integration with a single setting.

Data sharing and compliance

To enable split-second decisions, Copilot Studio shares specific data with the external system. This includes prompts, chat history, tool inputs, and metadata. This data sharing is not customizable. Organizations should only enable the feature if they’re comfortable with the data being shared.

External providers may handle data differently than Microsoft. Some may store or process data outside your region. It’s important to review your provider’s policies and ensure they meet your compliance standards.

Why this feature matters

Advanced security for AI agents is no longer optional. As agents are increasingly equipped with autonomous triggers and take on more complex and sensitive tasks, organizations need real-time oversight. External monitoring gives them the tools to enforce compliance, detect and block threats, and gain visibility – without compromising performance.

This new, groundbreaking capability in Copilot Studio empowers organizations to take control of their AI agent security strategy. It’s a critical step toward safer, more reliable AI deployments.

Next steps

The public preview is rolling out worldwide, with availability to all customers by Wednesday, September 10th. To learn how to get started, visit the Microsoft Learn documentation for advanced real-time protection during agent runtime.

Resources 

• Learn more in the feature’s public documentation
• Link to the developer documentation
• Learn about Microsoft Defender’s solution for agent threat protection 
• Configure the feature in the Power Platform Admin Center PPAC

The post Strengthen agent security with real-time protection in Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.