May 2025 was a big month for Microsoft Copilot Studio and there are a ton of features to catch up on. In this edition of our monthly roundup, we’re recapping the biggest news from Microsoft Build 2025, giving a couple of important updates, and announcing new resources for Copilot Studio adoption and training. 

Microsoft Build 2025 roundup: Our biggest announcements 

Microsoft Build 2025 brought a wave of updates to Copilot Studio and Microsoft Dataverse, the operational database for agents, introducing powerful new tools for multi-agent systems, enterprise data access, and custom AI tuning. Here’s a quick overview of what dropped in Copilot Studio. 

Multi-agent orchestration: Copilot Studio now supports multi-agent orchestration, allowing agents built with Microsoft 365, Microsoft Azure AI, and Microsoft Fabric to collaborate by delegating tasks and sharing results to complete complex workflows. Copilot Studio will also support the open Agent2Agent (A2A) protocol, allowing agents to connect to those built on third-party platforms. 

Computer use in agents: The new computer use capability, currently available to eligible United States-based customers, allows Copilot Studio agents to perform tasks across desktop and web applications, automating repetitive processes like data entry and document processing through AI-powered UI interactions. 

Bring your own model and Microsoft Copilot tuning: Makers can access more than 11,000 models in Azure AI Foundry and fine-tune them using enterprise data for even more context-rich and valuable agent responses. 

Other updates include: 

• Model Context Protocol (MCP)’s general availability and updates.
• In-conversation agent recommendations and handoff.
• Code interpreter for Python-powered logic using natural language.
• Instant agent sharing across your organization.
• New maker controls for knowledge, including options for file collections, code interpreter, moderation, and user feedback.
• SharePoint and WhatsApp channels to publish agents to.
• Security and governance updates.

Get all the details on these announcements in Corporate Vice President Lili Cheng’s blog post. For an even more in-depth update, learn more about how Dataverse supports all these in Corporate Vice President Nirav Shah’s blog post from Microsoft Build 2025. You can also see a roundup of all the Microsoft Dataverse sessions presented at Microsoft Build 2025.

Build, publish, and monetize agents with the Agent Store 

Welcome to the Agent Store, your centralized, curated marketplace for agents built by Microsoft, trusted partners, and customers. Accessible through the left side navigation in Microsoft 365 Copilot Chat, the Agent Store makes it easier to browse, try out, and share agents for your business processes without having to build them from scratch. These agents work seamlessly across your Microsoft 365 ecosystem, so you can install an agent once and use it in multiple places. It’s all about speed, trust, and impact at scale. 

Right now, the Agent Store has more than 70 agents, ranging from knowledge assistants to complex multi-modal orchestrators. You’ll have access to more as makers and software development vendors build and share new agents in the coming months—and the store will offer personalized agent discovery based on your organizational context. For developers, the Agent Store also provides a platform to share your innovative agents with millions of Microsoft Copilot users and grow your user base. 

With robust support through Copilot Studio and the Microsoft 365 Agents Toolkit, the Agent Store includes both low-code and pro-code development options. Whichever way you prefer to build and deploy your agents, this marketplace helps you reduce development time and costs and get them out there faster. 

Learn more about finding and publishing agents through the Agent Store on the Microsoft 365 Developer Blog. 

Publish custom engine agents to Microsoft Copilot Chat: Now generally available 

The ability to publish custom engine agents built in Copilot Studio directly to Copilot Chat is now generally available and automatically enabled. This means all customers can now unlock powerful new ways to customize and extend Copilot experiences with rich, domain-specific intelligence, right inside the tools people use every day. 

Previously announced in public preview, this feature allows makers to publish agents built in Copilot Studio to Copilot, with full access to the features that make agents intelligent and useful. That includes topics, orchestration selection, autonomous triggers, analytics, and Azure AI integrations. These custom agents surface seamlessly across Microsoft 365 apps, including Microsoft Teams, Word, Excel, PowerPoint, and Office. 

Custom engine agents in Copilot support messages, quick replies, Adaptive Cards, multi-turn interactions, and multi-message responses—all backed by robust governance and analytics in the Microsoft Power Platform admin center. Now you can confidently scale custom Copilot experiences across your workforce, without changes to existing agents. 

General availability brings simplified deployment and seamless integration, turning every custom agent into a first-class participant in the Microsoft 365 Copilot experience. Read more about publishing and deploying agents on Microsoft Learn. 

Microsoft Graph connectors are now Copilot connectors

Microsoft Graph connectors are now called Copilot connectors, a name that better reflects their role in powering the Microsoft 365 Copilot experience. 

Copilot connectors bring external data into Microsoft 365 so Copilot and Copilot Studio agents can retrieve, apply reasoning to, and act on knowledge beyond the Microsoft 365 ecosystem. These connectors eliminate the need for duplicative uploads or clunky copy-paste workflows. 

For developers and makers, Copilot connectors are the bridge between your existing systems and your AI-powered solutions. Whether you’re supporting sales teams to query customer relationship management (CRM) system records, surfacing insights from product documentation, or building custom agents grounded in real enterprise data, connectors make it possible to create truly contextual and intelligent experiences. 

The change in name reflects a broader shift: AI isn’t just reading data anymore—it’s working with it. More than 40 Copilot connectors are already generally available or in public preview, including key sources like Gong, PagerDuty, and Unily, so connect your agents and systems in the Microsoft 365 admin center. Read more about building Copilot connectors on Microsoft Learn. 

Accelerate agentic operations with new adoption resources

We’re excited to introduce two new resources designed to help your organization get started with Copilot Studio quickly and effectively. Whether you’re launching your first agent or scaling across teams, these tools are built to simplify the building process and drive measurable impact across your organization. 

Microsoft Copilot Studio Adoption page 

This centralized hub offers comprehensive guidance for seamless integration across teams. It includes: 

• Step-by-step setup and deployment guidance.
• Role-based training for business users, developers and admins.
• Best practices and support documentation.
• Tools to help developers and leaders build and scale agents with confidence.

This page is your go-to destination for enabling success from day one. Explore the Copilot Studio AI Agents Hub. 

Copilot Studio scenarios in the Microsoft Scenario Library 

Explore 35 new custom agent scenarios across seven functional areas—each designed to showcase real-world value and accelerate adoption. Every scenario includes: 

• A clear use case with key performance indicators (KPIs) and key users.
• Agent functionality and flow breakdown.
• Architecture and key considerations.

These resources are crafted to help you unlock the full potential of Copilot Studio—empowering your teams to innovate, automate, and scale with ease.

Free Microsoft Copilot Studio training for Microsoft Power Platform makers

If you or members of your team are already familiar with Microsoft Power Platform, you may be wondering how the skills you have built using Microsoft Power Apps or Microsoft Power Automate translate to the world of agents. Microsoft worked with Shane Young, a Microsoft most valuable player (MVP) of 20 years, as part of a paid collaboration to bring you more than four hours of free, hands-on training on YouTube.

This series of videos will help you get started with Copilot Studio at your own pace so you can walk away with your own agents, ready to use. The training series includes demos, step-by-step builds, and deep dives into product-specific features, broken down into four sections: 

1. Introduction and demos (7 videos)
2. How to build a conversational agent (8 videos)
3. How to build an autonomous agent (10 videos)
4. Reusing your Microsoft Power Platform skills (4 videos)

Thousands of Microsoft Power Platform makers have already gone through the training, and we encourage you to spread the word and join in. Start watching or share with your team. You may be the makers who create the next best agent in the Agent Store. 

More ways to 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.

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. 

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

Microsoft Build 2025 is here—our annual showcase of the most exciting innovations shaping the future of development and AI. For engineers, makers, and subject matter experts, it’s the moment to see what’s next across the Microsoft ecosystem. This year, Microsoft Copilot Studio has a number of powerful new agent-related features to show you. From multi-agent orchestration to more maker controls, computer use in agents to code interpreter, read on for a first look at Copilot Studio’s exciting announcements.

Recap of major Microsoft Build 2025 announcements

Jared Spataro, Corporate Vice President, Microsoft, announced some of the biggest news from the Copilot Studio and Microsoft 365 Copilot agents teams. In case you missed it, here’s an overview of a few features we’re particularly excited about.

Multi-agent orchestration

Rather than relying on a single agent to do everything—or managing disconnected agents in silos—organizations can now build multi-agent systems in Copilot Studio (preview), where agents delegate tasks to one another. This includes those built with the Microsoft 365 agent builder, Microsoft Azure AI Agents Service, and Microsoft Fabric. These agents can now all work together to achieve a shared goal: completing complex, business-critical tasks that span systems, teams, and workflows.

This evolution reflects a broader shift in how organizations are scaling their use of agents across Microsoft. Imagine a Copilot Studio agent pulling sales data from a customer relationship management (CRM) system, handing it off to a Microsoft 365 agent to draft a proposal in Word, and then triggering another to schedule follow-ups in Outlook. Or, envision agents coordinating across IT, communications, and vendor systems to manage an incident from detection to resolution. Whether it’s executive briefings, customer onboarding, or product launches, agents can now operate in sync—bringing greater connectedness, intelligence, and scale to every step. This feature is currently in private preview with a public preview coming soon.

See how different organizations are employing their agent ecosystems and get inspired for how you could connect yours in Microsoft Corporate Vice President Srini Raghavan’s blog post.

Computer use in Copilot Studio agents

Computer use moves us closer to a more connected, intelligent world where agents collaborate seamlessly with people and systems. Agents can now interact with desktop apps and websites like a person would—clicking buttons, navigating menus, typing in fields, and adapting automatically as the interface changes. This opens the door to automating complex, user interface (UI)-based tasks like data entry, invoice processing, and market research, with built-in reasoning and full visibility into every step. Computer use is currently available through the Microsoft 365 Copilot Frontier program for eligible customers with at least 500,000 Copilot Studio messages and an environment in the United States.

Bring your own model and model fine-tuning

Copilot Studio continues to integrate deeply with Microsoft Foundry, and now you can bring your own model for prompts and generative answers. Makers can access more than 11,000 models in Microsoft Foundry, including the latest models available in OpenAI GPT-4.1, Llama, DeepSeek, and custom models, and fine-tune them using enterprise data. This fine-tuning helps agents generate even more domain-specific, high-value responses.

Model Context Protocol

Now generally available, Model Context Protocol (MCP) makes it easier to connect Copilot Studio to your enterprise knowledge systems. With growing connector support, better tool rendering, evolving scalability, and faster troubleshooting, it’s never been simpler to bring external knowledge into agent conversations.

Developer tools to build agents your way

Microsoft empowers developers to build agents with the tools they prefer—Copilot Studio, GitHub, Visual Studio, and more. With Microsoft 365 Copilot APIs, developers can securely access Microsoft 365 data and capabilities to create custom agents or embed Microsoft 365 Copilot Chat into apps, all while respecting organization-wide permissions.

The Microsoft 365 Agents Toolkit and Software Development Kit (SDK) make it easier to build, test, and evolve agents over time. Developers can swap models or orchestrators without starting from scratch, use SDK templates to jumpstart projects, and deploy to Azure with smart defaults—all now generally available.

Copilot Studio enhancements

New agent publishing channels: SharePoint and WhatsApp

Copilot Studio has exciting updates to available channels, including that publishing agents to Copilot is now generally available. In addition to this highly anticipated update, we’re also adding two additional channels: SharePoint and WhatsApp. These key channels make it easier than ever to bring custom agents to the places where your users already work and communicate. This helps you extend the reach and value of your agents, from serving your teams inside Copilot and SharePoint to engaging customers around the world.

The SharePoint channel, now generally available, lets makers deploy custom agents directly to a SharePoint site with a single click. With authentication and permissions handled automatically, anyone with access to the site can immediately start using the agent. This extends the full capabilities of custom agents into one of the most widely used collaboration hubs in the world.

Starting in early July 2025, makers will also be able to publish Copilot Studio to WhatsApp. This will allow organizations to provide conversational support and engage global users directly within the familiar, mobile-first platform—no separate website or app required.

Additional maker controls for knowledge

Now in public preview, new controls in the Generative AI agent settings give makers more ways to shape how agents respond, reason, and interact with users. In addition to toggles for generative orchestration and deep reasoning, you’ll see multiple categories to further ground and tune your agents.

First, in response to maker feedback, we’re pleased to announce that you can now upload multiple related files into a file collection and use the collection as a single knowledge source for an agent. You can also include natural language instructions to help your agent find the most relevant document in the collection to ground each response.

In the Responses section of the Generative AI tab, you can now choose your agent’s primary response model, provide response instructions, adjust response length, and turn on advanced options like code interpreter (see below) and Tenant graph grounding with semantic search.

Moderation settings control how flagged responses—that is, generated responses detected to possibly have harmful content—are handled. These controls allow you to set a custom response to send when potential responses get flagged. A User feedback section, meanwhile, gives you the option to allow users to provide feedback on the agent, along with a custom disclaimer. This provides you a qualitative assessment of how users perceive your feature—enormously valuable in planning and honing your agent roadmap.

In the Knowledge and User input sections, you decide what the agent draws from: your specific knowledge sources only, foundational model knowledge, or even Bing web search. You can also choose to let users add images during agent interactions.

These new controls, along with improved analytics and testing tools, empower makers to deliver more relevant, responsible, and high-quality agents—leading to greater impact and better user experiences across the board.

Additional knowledge sources for agents

Copilot Studio now supports several new knowledge sources, providing an even broader range of enterprise content for custom agents to access and reference. OneDrive files and folders, SharePoint lists, and Microsoft Teams chats and channels are all supported. Outside this internal data, agents can now employ unstructured data from platforms like Salesforce, ServiceNow, and Zendesk, as well as structured data from platforms like Snowflake, Databricks, and SAP.

Knowledge from Microsoft Azure AI Search is also generally available. Agents can now reference this data more effectively, whether the goal is analyzing sales pipeline trends, identifying churn risks, or supporting role-specific insights across business systems.

As you connect these new sources, note that Microsoft Graph connectors are now called Copilot connectors, a name that better reflects their role in powering the Copilot experience. More than 65 Copilot connectors are already generally available or in public preview in the Microsoft 365 admin center, including Gong, PagerDuty, and Unily. Read more about building Copilot connectors on Microsoft Learn.

Code interpreter

Bring Python-powered logic to your Copilot Studio agents using natural language. Now in preview, code interpreter lets developers extend Copilot Studio agents with Python—enabling advanced logic, dynamic visualizations, and structured data operations directly within runtime or prompt workflows.

There are two ways to use code interpreter. The first, with agents, is dynamic: Python code is generated and executed live at runtime. Agents can analyze uploaded CSV or Excel files, generate pie, line, or bar charts with downloadable outputs, and solve complex math problems in context.

The second, with Prompt Builder, is more static—makers define and edit Python code at design time. When the prompt runs, it executes the same preconfigured logic—ideal for repeatable tasks like Create, Read, Update, and Delete operations on Dataverse tables.

This feature unlocks new abilities in data analysis, reporting, and visualization within agents. Users can get richer and more insightful agent responses, automate calculations, and streamline repetitive processes. By bridging natural language prompts with real code execution, code interpreter helps teams improve quality, reduce turnaround time, and support innovation—while staying inside Copilot Studio’s managed environment.

Pro-developer enhancements

Visual Studio Code extension for Copilot Studio

The Copilot Studio Visual Studio Code extension is designed with professional developers in mind, bringing familiar tooling and workflows to the world of agent development. Now available in the Visual Studio Marketplace, this extension lets you connect directly to Copilot Studio and edit agents from within Visual Studio Code, enabling a modern experience outside the web UI.

For developers and teams, this means you now have new get IntelliSense color-formatting, “find all references,” and the structured clarity of working over a file system—all while building on a fully managed software as a service (SaaS) platform. Copilot Studio handles the infrastructure, compliance, and runtime complexity, so your team can stay focused on delivering value.

The Copilot Studio Visual Studio Code extension is about meeting developers where they are. Whether you’re integrating agents into your broader developer ecosystem or scaling collaboration with GitHub, the Copilot Studio Visual Studio Code extension brings the control and confidence developers expect. No new tools to learn, and no trade-offs.

Embedded agent builder enhancements

Share agents instantly across your organization

The new agent sharing experience in Copilot Chat makes it easier than ever to share agents across your organization. Makers and developers worldwide can now generate and distribute shareable links directly from the right sidebar in Copilot Chat, which streamlines collaboration and increases the discovery of your agents. Once you’ve shared your agent, others can then start using it instantly.

This feature eliminates the extra steps previously required to find and share an agent—no switching tools or hunting for links. Agent sharing reduces friction, speeds up internal adoption, and helps teams get more value from the agents already in use. Easier sharing allows for consistent, cross-platform experiences, whether you’re building with Copilot Studio, the embedded agent builder in Microsoft 365, or Teams Toolkit.

In-conversation agent recommendations

As makers and developers build more specialized agents, it becomes harder for users to know which one to use and when. With in-conversation agent recommendations, Copilot bridges that gap by dynamically suggesting the most relevant agent based on what the user is trying to do.

As the user describes their need in natural language, Copilot determines if an installed agent is better suited to handle a request. It recommends a handoff and carries over the full conversation context so the agent can respond intelligently, access enterprise data, or take action in downstream systems. From the user’s perspective, this process is seamless, effortless, and improves the quality of their experience using AI tools to assist with or accomplish their work.

For developers and makers, this means your agents no longer sit idle, waiting to be discovered. They’re surfaced at the right time, in the right context, driving impact without the user needing to go search for them. It’s a lightweight way to boost discoverability, increase usage, and demonstrate value without changing how agents are built.

Security and governance enhancements

Copilot Studio continues to enhance and improve governance and security capabilities, giving IT teams and security admins control and clarity over every stage of agent creation and operation. Here are some recent updates in agent and platform-level controls as well as data and infrastructure protections.

Agent and platform-level controls

• Privacy controls to disable transcript recording and session downloads, apply real-time sensitive data masking and audio suppression in agent chats, and present a custom privacy notice.
• Automatically assigned identities for agents created through Copilot Studio, automatically listed in the centralized AI agents directory in the Microsoft Entra admin center.
• A separate shared environment for agents built in the Microsoft 365 agent builder, simplifying tracking and paving the way for more granular policies.
• Additional safeguards to prevent unauthorized use of Copilot Maker authentication, enforce Microsoft Entra ID (in public preview) for all interactions, and require explicit consent before agents are shared.
• Blocked role escalation in personal development environments.

Data and infrastructure protections

• Ability for admins to apply Data Loss Prevention to agents in Copilot (to prevent misuse of labeled content) and enforce auto-labeling with downstream inheritance in Dataverse.
• New Data Security Posture Management (DSPM) for AI-focused views, allowing security teams to track how sensitive data moves through apps and agents (including interactions from employees, partners, and anonymous users).
• Automatic connector management enforcement that aligns Copilot Studio with the rest of Microsoft Power Platform—no PowerShell scripts required.
• Network isolation (public preview) to help lock down connectors and App Insights through firewalls and virtual networks (VNETs).
• Federated Identity Credentials to remove stored secrets or certificates from registration.

Together, these enhancements help keep Copilot Studio secure, compliant, and enterprise-ready without slowing down innovation. Learn more about these announcements in Microsoft Corporate Vice President Vasu Jakkal’s blog post.

To dive deeper into these new capabilities, join us for some of our relevant sessions at Microsoft Build 2025:

• What’s new in Copilot Studio
• Architecting your multi agent solutions with Copilot Studio and Microsoft 365 Agents SDK
• Build Microsoft Teams collaborative agents as virtual colleagues with Visual Studio Code​
• Building secure business apps: Best practices from design to deployment
• Fine-tune models for task-specific agents in Microsoft 365 Copilot​
• Building agents in Copilot Studio using Model Context Protocol, open standards and more​

The post Multi-agent orchestration, maker controls, and more: Microsoft Copilot Studio announcements at Microsoft Build 2025 appeared first on Microsoft Copilot Blog.

Today we’re announcing new features in several categories:

• Drive collaboration with fusion bot development through Office-like collaborative comments that can be added directly inside the authoring canvas (preview)
• Build an all-in-one contact center supported by bots that can be connected to phone call interactions through interactive voice response (IVR) for Dynamics 365 Customer Service (generally available)
• Extend existing Bot Framework bots by adding Power Virtual Agents as a skill (preview)
• Several enhancements and updates with bots in Microsoft Teams including:
  • Microsoft Teams proactive messaging: Bot makers will be able to send a proactive message to a user or group within Microsoft Teams with full context, based on external trigger events (preview)
  • Sharing bots with colleagues via security groups, with easy management of who should and shouldn’t have access to the bot (generally available)
  • Direct mention/interaction capabilities with bots in Teams. Makers can create and add bots directly to a Teams channel while allowing other people in the channel to see the bot’s responses (coming soon)

You can begin your bot building journey with Power Virtual Agents and learn more about the Wave 2 releases through the Ignite sessions and the remainder of this blog.

Office-like collaborative comments in Power Virtual Agents (preview)

In a previous blog, I had shared about the future of bot building being driven by fusion teams. Since then, we are announcing office-like collaborative commenting in the Power Virtual Agents authoring canvas.

Comments let you contextually add notes, feedback, and have conversations with others directly in your bot, just like you would in Word, Excel, or PowerPoint.

Comment on a topic in your Power Virtual Agents bot to bring colleagues into the development process such as reminding them about a specific topic node that might need to be changed or ask a pro developer to add an advanced function through the Bot Framework Composer.

The experience is designed to align to the familiar controls in Microsoft Office today to make it easy to add or edit comments, reply to threads, and resolve or delete threads as appropriate – all to help everyone keep aligned whilst building your intelligent bots.

You can get started with this feature in preview by simply creating a bot in Power Virtual Agents, navigate to the authoring canvas and open the “Comments” pane to add a comment to a topic or to specific nodes within a topic to truly collaborate on building complex bots.

In the coming months, we will enable @mentioning other bot makers in comments with notification emails to further enhance collaboration in the bot building process. In addition, we are also investing in adding office like commenting into the broader Power Platform.

Be sure to sign up to Building Bots using Fusion Teams roundtable session where you will have an opportunity to share your thoughts on the collaborative bot building process.

All-in-one Contact Center – bots can be connected to phone call interactions through interactive voice response (IVR) for Dynamics 365 Customer Service (generally available)

Conversational IVRs are state-of-the-art for phone interactions with callers removing the need to navigate tedious and never-ending phone prompts. Now, callers can describe what they need using their voice and the IVR will route them to the correct topic and solve their issue.

Power Virtual Agents can now be configured to work with Dynamics 365 Customer Service and provide your organization with these conversational IVR capabilities. With Microsoft’s state-of-the-art natural language and speech capabilities, you can quickly build and maintain a bot that answers your companies’ phone calls and has voice conversations with your customers on their phone, quickly answering their questions and lowering your cost to serve.

When a caller interacts with the bot, speech services recognize your callers utterances with high accuracy and talks to the user using neural voices which are almost indistinguishable from a human voice. Power Virtual Agents’ AI capabilities match your callers requests to your topics, providing a seamless voice experience.

Callers can interact with the bot naturally using their native language with support from Power Virtual Agents’ 19 languages. There is no need to have your customers dial a different number based on the language they speak – your bot can transfer to any other language bot as needed, allowing callers to communicate in the language they feel most comfortable.

If for some reason your caller needs to reach one of your human agents to resolve an issue, they can be easily transferred to your live agent in Dynamics 365 Customer Service using a simple escalation action in your topics.

With Dynamics 365 Customer Service, you can quickly get started by acquiring a new phone number to associate with your bot or bring your own existing number using Direct Routing. No matter if you are starting your IVR experience from the scratch or moving from an existing system, Power Virtual Agents can be your solution for intelligent, conversational IVR.

This new capability allows your callers to spend less time on the phone navigating prompts and more time getting their issues resolved, minimizing the need to escalate to a human agent.

Sign up to the Introducing Voice Channel for Dynamics 365 Customer Service breakout session for more information. Also, read these step-by-step instructions on how to use Power Virtual Agents bots to power your conversational IVR using Dynamics 365 Customer Service.

Power Virtual Agents as a skill for Bot Framework bots (preview)

Today, bot makers can use Microsoft Bot Framework skills in Power Virtual Agents. Announcing at Ignite, you can now easily extend any Bot Framework bot by adding Power Virtual Agents as a skill and invoking their functionality at runtime. This new feature is in Public Preview and allows bot makers to use the tools that work best for their needs by having the option to use both bots as skills bidirectionally.

Business users and subject matter experts can create Power Virtual Agents bots and make them available as skills to the developers, enabling the maker to easily expand the Bot Framework bot ecosystem with Power Virtual Agents functionality.

If a Power Virtual Agents bot is added as a skill, the Bot Framework bot will determine if the user’s query matches any of the trigger phrases in the Power Virtual Agent’s bot.

If there is a match, the Bot Framework bot will invoke the Power Virtual Agents bot and pass the entire user utterance to it to extract any entities and automatically start the right Power Virtual Agents topic.

Bot authors can download the Power Virtual Agents bot skill manifests and use them to create a skill connection in Bot Framework Composer and SDK. Power Virtual Agents bot skill manifests are automatically generated based on the bot content.

Bot Authors can also explicitly control which Bot Framework bots are allowed to connect to a particular Power Virtual Agents bot.

For more information and step-by-step instructions on how to get started, visit Power Virtual Agent bots as a skill.

Enhancements and updates with Power Virtual Agents in Microsoft Teams

There are several features that are included to improve the experience of making and consuming PVA bots within Microsoft Teams. You can see these features in action in the future of business is ​seamless collaboration​ breakout session.

Notify team users with proactive messages (public preview)

Power Virtual Agents can now send proactive messages and cards to users through personal chats in Microsoft Teams. This capability unlocks a rich set of scenarios from notifying users that their expense report has been approved to reminders to update their emergency contact information. The best part is you can include topics in Power Virtual Agents to reply to their follow-up questions such as “How is my emergency contact information privacy protected?”.

The integration is achieved with existing Microsoft Teams actions to post messages and cards in Power Automate. You can leverage all the rich trigger and actions in the Power Platform ecosystem and use your PVA bot to send messages to users at the appropriate step of the workflow.

PVA supports sending proactive messages and cards that takes a response from the user. Select ‘send as Power Virtual Agents (preview)’ in the Power Automate Microsoft Teams action to choose the PVA bot that will be sending the message. Learn more about this feature here: notify Teams users with proactive message.

Share bots with colleagues (generally available)

It is very common for departments or a sub-organization to build bots for a dynamic group of users that is not part of a specific team. For example, may have different field agents for different products that are spread across multiple teams, but they all share the same need to look up customer contact information. How can Contoso have a bot that is only accessible to field agents?

We are pleased to announce you can now share your bot with specific security groups. Users can find and install the shared bot directly from the Microsoft Teams app store in the “Built by your colleague” section, or directly install the bot via installation link and email notifications. There is no need to worry about data leakage as only members of the shared security groups will be able to install and chat with the bot. Learn more about the feature here.

@Mention bots in teams channels (Coming soon)

Bots built for Microsoft teams today need to be installed by each teammate as a personal app to chat privately in Microsoft Teams.

Power Virtual Agents will now allow bots built-in Microsoft Teams to be directly added to the team that the bot is created in. Team members can directly interact with the bot via @mentioning the bot’s name in their team’s channel where everyone can see the bot’s response. In a product design team and need to share product design best practices with your teammates? Simply ask the bot in channel and everyone can see the response!

While bots in channel provides amazing collaboration, there are also times where users want to interact with the bot in private without spamming their teammates. When adding a bot to a team, you can allow the bot to also greet every team member in personal conversation. This way your teammates can have personal conversations such as asking questions about how to install design software without needing to install the bot for themselves.

This feature is planned to go live in the coming months.

As some of these Power Virtual Agents features are in preview, we are eager to hear your feedback in the community forums at https://aka.ms/pvacommunity

Learn more

You will have the opportunity to learn more about these updates over the course of Microsoft Ignite, so be sure to check out all the sessions below.

Power Virtual Agents sessions:

• The future of business is ​seamless collaboration​ breakout session
• Building bots using Fusion Teams roundtable session
• Introducing Voice Channel for Dynamics 365 Customer Service breakout session

Other Power Platform sessions:

• Day 1 Keynote with Scott – Power Platform and Fusion Teams
• Day 1 Keynote with Charles and Alysa
• Day 2 session with Julie – Power Platform and Fusion Teams
• Day 2 session with Power Platform Leadership team – Into focus: Business applications
• On demand session – RPA and Process advisor
• On demand session – Build secure solutions in the Power Platform
• On demand session – Empower organizations to build apps faster with fusion teams
• On demand session – In-depth overview of what’s new for Power Apps
• On demand session – Add intelligence to your business with AI Builder
• On demand session – Return to the workplace confidently with low code solutions

Sign up to the Power Virtual Agents in a day events:

• Customer: Power Virtual Agents in a day events
• Partner: Train-the-trainer event for Power Virtual Agents in a day on Nov 30

The post What’s new with Power Virtual Agents at Ignite appeared first on Microsoft Copilot Blog.

In the last year, we have seen tremendous growth in the number of people working and living online, with over two-thirds (74 percent) of Chief Financial Officers planning to permanently shift employees to remote work once the COVID-19 crisis ends¹. As the workplace constantly evolves, workloads continue to grow and capacity constraints rise, organizations look to bot experiences powered by AI to manage the greater urgency to meet, and exceed customer and colleague demands. However, 68 percent of executives report a skill gap of developers and AI experts to reach those aspirations². As a result, tools like Microsoft Power Virtual Agents are being used to empower everyone to create intelligent bots, embedded with AI to provide human-like experiences, regardless of the makers’ AI or coding skills.

The approach to developing bots is evolving across organizations through a term coined “fusion development”, a topic increasingly popular with our customers and partners. Microsoft is invested in empowering all developers, from citizen developers and business users to professional developers as a means to implement bots across low-code and pro-code platforms.

What is fusion development?

Gartner® describes digital fusion teams as “multidisciplinary digital business teams that blend technology and other types of domain expertise”³. With this growing trend, Gartner also claims that at least 84 percent of companies have set up fusion teams. This reinforces the importance of collaboration between IT and business for successful technology delivery.

The rise of fusion teams in many enterprises’ operating models today testifies to organizational boundaries blurring at an accelerated rate, with 43 percent of fusion teams in large enterprises already being led by team leaders who report outside corporate IT³.

The fusion development approach values the knowledge and abilities of different members across the multi-disciplinary team gaining significant synergies through efficient communication, autonomy, and development in an agile fashion.

The evolution of bot building

Conversational systems were, until recently, the exclusive domain of specialized vendors and data scientists. Organizations are now progressively opting in for bots to be built in-house by developers. With the shortage of technical skills and the need for subject matter experts to directly author the bot content, it has become even more critical to democratizes aspects of the bot development lifecycle to those closest to the process.

With this shift, fusion bot development has helped drive collaboration across pro developers and subject matter experts. As a result, the need for technologies to have the flexibility to support several personas to create and maintain bots has grown. In turn, the demand for unified bot-building platforms has intensified.

What is Microsoft doing to help?

Microsoft believes that the key to creating successful bots and delightful conversational AI experiences is through enabling and empowering such fusion teams to support all skill levels across low-code and pro-code platforms.

We started our journey in enabling fusion team development for our customers back in 2019 where we announced new integrations for low-code application development through Microsoft Power Apps.

With feedback from our customers, the next step was to support fusion teams for bot development. Power Virtual Agents provides the tools to achieve this through a simplified and scalable platform via a SaaS service. This provides the ability to build and host bots and fully support sophisticated capabilities for pro developer technologies such as Bot Framework Composer and SDK.

In May 2021, we announced the better together integration between Power Virtual Agents and Bot Framework Composer. This enables pro-developers, subject matter experts, and citizen developers to build and easily extend bots with code inside a single, hosted SaaS solution. This functionality has seen widespread adoption as pro-developers can accelerate their developer velocity whilst democratizing SME workloads without compromising quality. This SaaS service also provides a consistent infrastructure such as AI behind the scenes to enhance bot development, not possible in just developer-focused tools.

We have also announced capabilities to allow both Power Virtual Agents and Microsoft Azure Bot Service to be used as skills bidirectionally. For example, Azure Bot Service skills can be used with Power Virtual Agents hosted bots as well as in preview, the capability to leverage Power Virtual Agents bots as a skill to Azure Bot Service. This allows makers to ensure that they have the ability to use the tools that best work for their unique needs.

Customers accelerating their bot-building with fusion teams

Learn how City of Ottawa, Miami Dolphins, and Syngenta Group are accelerating bot building through fusion development.

With Power Virtual Agents, the real winner is this relationship between IT and the client that is harmonious and allows each party to do what they do best to make a good product without the workload of either party being shoved on to the other.”

Jeffery Kozera, Senior Automation Developer and Integrator, City of Ottawa

Our IT team put the framework in place, but from then on, employees from each part of the business can continually decide how the bot should answer questions related to their function. We can be a lot more productive and efficient with multi-authoring in Power Virtual Agents. It becomes a real team effort.”

Kim Rometo, Vice President and Chief Information Officer, Miami Dolphins

Even without a technical background…I helped to create a chatbot that legal team members now use to locate documents, FAQs, training materials, and videos. When Fady’s team (Process and Technology team) added Power Automate to its toolkit, team members’ ability to solve business issues leapt ahead.”

Marcus Holt, Legal Operations Trainee, Syngenta Group

Learn more

We are thrilled that more people are empowered to build intelligent conversational AI solutions to overcome the AI skills gap, drive better customer and colleague engagement, and enable AI skills for all.

Join us to discuss building bots using fusion teams at Microsoft Ignite.

You can sign up for the Building Bots using Fusion Teams customer roundtable (9:30 AM to 10:30 AM PT) and share your thoughts.

You can also get started with Power Virtual Agents and Bot Framework Composer to begin your fusion development journey.

¹Forbes—This Is the Future Of Remote Work In 2021

²Susanne Hupfer, Talent and workforce effects in the age of AI, Deloitte, March 2020

³Gartner, Fusion Teams: A New Model for Digital Delivery, 4 February 2021

GARTNER is a registered trademark and service mark of Gartner, Inc. and/or its affiliates in the U.S. and internationally and is used herein with permission. All rights reserved.

The post The future of bot building appeared first on Microsoft Copilot Blog.