Agents play a significant role in how organizations are transforming their business process with AI. Soon agents created in Copilot Studio agent builder and Copilot Studio will be available right from within Copilot Chat. Let’s review how you can pay for agents with Copilot Studio.

Getting started with agent consumption 

Agents play a significant role in how organizations are transforming their business process with AI. Soon agents created in Microsoft Copilot Studio agent builder and Copilot Studio will be available right from within Copilot Chat. Let’s review how you can pay for agents with Copilot Studio. 

Usage of agents is measured in “messages” and total cost is calculated based on the sum of messages used by your organization. You can purchase messages though the Copilot Studio meter in Microsoft Azure, a pay-as-you-go option, for $0.01/message, or via pre-paid message packs priced at $200 for 25,000 messages/month.  

The Microsoft Power Platform admin center is used to set up billing and assign message capacity to Copilot Chat and individual agents. Agent message usage varies with an agent’s complexity, frequency, and the use of specific features. These features have been categorized into five groups, including three new ones introduced today. 

Classic and generative answers 

Answers are how agents communicate with users and are core to the prompt and response interaction model. Answers are charged for every agent response, not for user prompts. As makers build agents, they can define conversational topics, create branching logic flows, and apply generative AI to create responses based on knowledge sources. To support this range of capabilities, we provide two options: 

1. Classic answers, used for predefined responses that are manually authored by agent makers. These are static, do not change unless manually updated, and are typically used when precise responses are required. Classic answers cost one message. 

2. Generative answers, used for dynamically generated responses based on knowledge sources and context. These provide more flexible and natural interactions because they build on a conversation’s context and available knowledge. Generative answers cost two messages. 

Note that users licensed with Microsoft 365 Copilot can use classic and generative answers at no cost as part of their per user license. 

Tenant Graph grounding for messages 

Tenant Graph grounding for messages provides high quality grounding for agents with relevant information from Microsoft Graph, including files stored in SharePoint and external data synched via Graph connectors. It does not include personal Graph data such as emails and chats. Tenant Graph grounding for messages costs 30 messages for each knowledge retrieval. 

This paid capability is optional and you can decide whether to turn it ‘on’ or ‘off’ in Copilot Studio. If this capability is enabled, each time an agent responds with a generative answer, it will utilize knowledge from the tenant Graph and tenant Graph grounding for messages will be billed. This will roll out in phases—existing agents that enabled this feature during preview, along with new agents built in Copilot Studio, will be billed starting on February 1, 2025; and new agents built in Copilot Studio agent builder using this feature will be billed starting today. 

Note that users licensed with Microsoft 365 Copilot can use tenant Graph grounding for messages at no cost as part of their per user license. 

Autonomous actions enter paid preview 

Autonomous agents understand your work, act on your behalf, and can automate complex business processes. We’ve seen significant interest in these capabilities since public preview launched in November 2024, and starting February 1, 2025, we are transitioning to a paid preview program. 

To enable autonomous agents, we are introducing the concept of autonomous actions. Autonomous actions are generatively orchestrated triggers, topics, data connectors, and workflows and are visible in the activity map displayed in generative orchestration mode. Autonomous actions cost 25 messages per action. 

Calculating agent cost  

Agent costs are calculated based on the capabilities from the table above. Here are a few example cost calculations: 

• A hypothetical agent might answer questions from customers on a website. Yesterday, it consumed 500 classic answers and 2,000 generative answers. Therefore, it would cost 4,500 messages, equivalent to $45 for that day. 

• A hypothetical agent in Copilot Chat uses data stored in Microsoft Graph to answer employee questions about HR policies. Yesterday, the agent consumed 200 generative answers and 200 tenant Graph grounding for messages. Therefore, it would cost 6,400 messages or $64 for that day.  

• A hypothetical autonomous agent responds to and routes inbound sales orders from customers. Yesterday, it consumed 100 generative answers, 100 tenant Graph grounding for messages, and 800 autonomous actions. Therefore, it would cost 23,200 messages or $232 for that day.  

Of course, every agent will be different, and the number of messages consumed will depend on usage frequency and complexity. You can learn more about these features and billing. 

We recognize how critical it is to provide you with appropriate governance tools to manage agent costs within your organization. Within Microsoft Power Platform admin center, admins can assign agents to environments, monitor agent usage, and allocate message capacity to ensure you stay in control of billing. 

See a quick walkthrough of agent management within Microsoft Power Platform admin center and learn more about agent management.

The post Enabling agents in Microsoft 365 Copilot Chat  appeared first on Microsoft Copilot Blog.

Whether you’re a user, developer, or IT professional, Microsoft Copilot Studio offers a comprehensive platform for creating, managing, and deploying Copilot agents.

Broadly, an agent uses AI to automate and execute business processes, working with you and on your behalf. Agents can build capacity for every individual, team, and organization—from sales to marketing to customer service, and more—enabling you to scale impact like never before.

Agents come in all shapes and sizes. They help you retrieve information from grounding data and reason over it to summarize or answer questions. More capable agents take actions when asked and the most advanced agents are autonomous, operating independently to create and perform plans, orchestrate other agents, and learn when to escalate to an employee for help.

With Copilot Studio, you can create and publish Copilot agents to all kinds of channels, including Microsoft Teams, websites, or mobile apps. We have already seen incredible customer adoption, with over 50,000 organizations having used Copilot Studio to-date.

We are excited to announce two new capabilities for Copilot Studio:

• First, Copilot agents built in Copilot Studio can now be published directly into Microsoft 365 Copilot, surfacing right in the user’s flow of work.
• Second, we’re unveiling a new Copilot Studio experience that empowers users of any skill level to create Copilot agents from within SharePoint and Microsoft 365 Copilot Business Chat (BizChat).

These new features will be rolling out in general availability to all Microsoft 365 Copilot customers over the coming weeks. 

Publish Copilot agents to Microsoft 365 Copilot

Copilot agents enable you to enhance Copilot’s capabilities by connecting to your organization’s knowledge and data sources. These agents can draw from valuable data in SharePoint, Microsoft Dynamics 365, or your line of business systems, and help Copilot become significantly smarter about your business and its processes. You can also expand the capabilities of agents by equipping them with new skills, such as sending emails, updating records, or creating support tickets. And Copilot agents can integrate with your existing line of business systems, enabling your employees and customers to easily take action in their flow of work. 

Users can find Copilot agents in a new store in Microsoft 365 Copilot Business Chat, Teams, and the Microsoft 365 app, and they can use them by @ mention in a chat or by interacting directly with them. IT admins can curate the store catalog from the Microsoft 365 admin center.

Empower users of any skill level to create Copilot agents

When it comes to building Copilot agents, we are introducing a new, lightweight Copilot Studio experience that makes it simple for users of any skill level to build Copilot agents directly within BizChat and SharePoint. We think everyone will need to be able to create agents in the future, much like how everyone can create spreadsheets or presentations in Microsoft 365. This new experience will roll out in general availability to all customers through October.

With the new experience, you can tell Copilot Studio what you want your Copilot agent to do using natural language, and easily choose which knowledge sources you’d like to integrate from across your organization’s data, whether it’s specific documents or entire databases. When you are ready, the Copilot agent can be used by you, shared with a select group, or deployed to an entire organization. Building a Copilot agent in SharePoint is even easier with a few clicks and no coding skills required.

You can continue to customize any Copilot agent in the full Copilot Studio editor, adding more advanced capabilities including autonomy. As we announced at Build 2024, we believe autonomous agents will fundamentally change business processes. We’re actively working with enterprise customers who are aleady building autonomous agents in Copilot Studio as part of our early access program, and and we look forward to sharing more later this year.

Manage Copilot agents with centralized controls

We believe organizations that embrace AI will create and use many Copilot agents. There will be as many agents as there are documents or SharePoint sites in an organization. Copilot Studio provides a trusted environment that delivers confidence through comprehensive policies, access controls, and agent management, all available within a centralized admin center. This includes the ability to control agent creation, sharing, and use, which allows organizations to meet their security, compliance and governance goals.

Furthermore, the data used to ground agents remains securely within the Microsoft 365 trust boundary, adhering to your organization’s labeling and policy guidelines. When extending your agents through Copilot Studio, your data remains in the Microsoft Azure tenant boundary with security layers to prevent invalid authentication and authorization and data loss prevention (DLP) policies for additional control. And all of this is built on Microsoft’s Responsible AI and Enterprise Data Protection standards.

Ultimately, in a world where AI is rapidly transforming how we work, Microsoft 365 Copilot and Copilot Studio offer new opportunities for applying AI to your unique business needs. By empowering users to create, tailor, and deploy Copilot agents of all types, Microsoft is making advanced AI accessible and valuable to everyone.

• Learn more about Microsoft Copilot Studio.
• Learn more about Microsoft Copilot Studio governance.
• Read the Microsoft 365 blog post about Copilot Wave 2.
• Join us at the Power Platform Community Conference to see how Microsoft is transforming the developer experience. 
• Get in touch with a Microsoft representative today.

The post Unveiling Copilot agents built with Microsoft Copilot Studio to supercharge your business appeared first on Microsoft Copilot Blog.

For instance, consider the potential of a copilot that can react when an email arrives, look up the sender’s details, see their previous communications, and use generative AI to trigger the appropriate chain of actions in their response. From understanding the intent of the email, to looking up the sender’s details and account, seeing their previous communications, checking inventory, responding to the sender asking for their preferences, and then taking the appropriate actions to close a ticket—orchestrating and shepherding an entire process over days. 

With such capabilities, copilots are evolving from those that work with you to those that work for you. They can be designed to handle specific roles or functions, such as IT, marketing, sales, customer success, and finance across various industries, including travel, retail, and financial services. 

With these new capabilities, here are some examples of the kinds of copilots our customers can build

• IT help desk. IT support is complex, involving tickets, order numbers, approvals, and stock levels. Opening and closing a ticket can be a long-running task that spans days. A copilot can now handle this process, interfacing with IT service management applications, resolving IT tickets with context and memory, creating purchase orders for device refresh, and reaching out and getting managers approvals—all independently.
• Employee onboarding. Onboarding new employees is often expensive and slow. Now, imagine you’re a new hire. A copilot greets you, reasons over HR data, and answers your questions. It introduces you to your buddy, provides training and deadlines, assists with forms, and sets up your first week of meetings. Throughout all of this, the copilot is in touch, guiding you through the weeks-long onboarding and account set up processes.  
  
• Personal concierge for sales and service. Balancing exceptional customer experience while meeting ambitious revenue goals can be challenging. When a copilot serves guests, it can use the memory of previous conversations with guests to remember their preferences, make reservations, handle complaints, and answer questions related to the products and services on offer. The copilot learns from its interactions and proposes new ways of handling customer scenarios. By doing so, copilots can increase upsell and attachment rates, driving revenue for the resort while simultaneously enhancing guest experience, satisfaction rates, and repeat business.

Let’s dig deeper into a few of the underlying capabilities that make all this possible:

• Asynchronous orchestration of complex tasks. The first is the ability to use generative AI-powered planning and reasoning to manage complex, multistep, long-running tasks. For example, reacting to a new order means determining the need to verify inventory, triggering the right payment processes, pinging a supervisor for approval if the amount is above a certain threshold, and replying with a confirmation. Many of these events can take hours—or even days—to complete, but the copilot will run through them, maintaining the necessary state and context to do so.
• Memory and context. One of the frustrating things about support has traditionally been having to repeat information: who you are, what your policy number is, what your address is. There is no continuity of conversation. Copilots will now learn from previous conversations from the users and utilize this knowledge to continually personalize interactions. A copilot may not need to ask you for your laptop model or your address when you call again for the same issue. Conversations will thus become long-running, contextual, and deeply personalized.
• Monitor, learn, and improve. Copilots can now learn and adapt, offering monitoring and teaching capabilities to make their interactions better. Each copilot records a comprehensive history of its activities, providing transparency into its performance, including user interactions, actions taken, and feedback received, and you can see what decisions it made—and correct and teach them—with just a few clicks.

• Delegation with confidence and guardrails. When developing copilots with agent capabilities, establishing clear boundaries is paramount. Copilots operate strictly within the confines of the maker-defined instructions, knowledge, and actions. The data sources linked to the copilot adhere to stringent security measures and controls, managed through the unified admin center of Copilot Studio. This includes data loss prevention, robust authentication protocols, and more.

These advanced new capabilities in Copilot Studio are currently accessible to customers participating in an Early Access Preview where organizations such as Centro de la Familia are excited to explore agent capabilities that support teachers and case workers, allowing them to spend less time on administrative tasks and more time working with children, ultimately leading to better child outcomes. Based on feedback from program participants, we will continue to iterate and refine these capabilities for broader access in a preview planned for later this year. 

Additional innovations with Copilot Studio

There’s a lot more to share at Microsoft Build with Copilot Studio, and we’ll touch on just a few of our new capabilities here. To learn more—just sign up and try it out for yourself here.

It’s easier than ever to create copilots. With Copilot Studio, creating and testing copilots is now incredibly simple. You can create your copilot with our brand new conversationally driven experience—simply describe what you want it to do, and what knowledge you want it to have, and Copilot Studio will create your very own copilot. You can then immediately test it out, add additional capabilities, such as your own actions, APIs, and enterprise knowledge—and then publish it live with a few clicks.

Connect all your enterprise data with Copilot connectors. Customers want copilots connected with data from their own enterprises business systems and apps. Copilot connectors enable anyone to ground their copilot in business and collaboration data. This makes it possible for copilots to use various data sources, including public websites, SharePoint, OneDrive, Microsoft Dataverse tables, Microsoft Fabric OneLake (coming this calendar year), Microsoft Graph, as well as leading third-party apps. You can even create your own custom generative prompts to configure how a copilot handles a response from an API or connector.

Here are a few examples of how Copilot connectors can transform copilot experiences for specific personas or functions:

• Legal and Compliance. Navigate complex legal landscapes with a Copilot extension that queries specific legal datasets, ensuring controlled and compliant responses without overwhelming users with extraneous information.
• HR Helper. Assist employees with accessing essential resources for benefits and PTO policies, and even book time off directly through Copilot.
• Incident Report Coordinator. Workers can locate the right documentation, report incidents, and track them efficiently, all within the context of the chat.

Starting in June 2024, developers can access the public preview for Copilot connectors and stay informed on updates here.

Conversational analytics (private preview): One of the most common asks from customers has been the need for deeper insight into what their copilot is doing, how generative AI is responding, when it was unable to give the right answers and why—and recommendations on what to do to improve it.

Our new conversational AI analytics and insights will help to deepen makers’ understanding of their users’ satisfaction, provide insights into the kinds of questions users are asking, which generative answers are helpful and which are not—and where adding new and updated knowledge sources or creating custom topics can help.

Templates: If simply describing your copilot to build it wasn’t easy enough, Copilot Studio will now also include a variety of pre-built copilot samples for departments and industries. Some templates—such as Safe Travels for comprehensive travel support, Organization Navigator for organizational clarity, Kudos Copilot for fostering recognition, Wellness for employee health insights—are available now, with many more releasing in the coming months.

Enhanced security and controls (public preview): Administrators can now configure advanced settings beyond the default security measures and controls. With Microsoft Purview, Copilot Studio administrators gain access to more detailed governance tools, including audit logs, inventory capabilities, and sensitivity labels. They will be able to review comprehensive audit logs that cover tenant-wide usage, inventory (with API support), and tenant hygiene (such as data loss prevention violations and inactive copilots), enabling them to effectively monitor business impact. Both creators and end-users will be able to view sensitivity labels when responses are generated using AI-powered answers based on SharePoint documents.

With all the amazing innovations, numerous organizations are using Copilot Studio to build transformative generative AI-powered solutions. Check out this story from Nsure on how they are using Copilot Studio:



Get started today with Copilot Studio

This is just a glimpse of all the exciting innovation around copilots and Copilot Studio—we have a host of exciting new capabilities to share in our sessions at Build. So, join us in watching the sessions below, and try out Copilot Studio yourself and build and share your very own copilot in minutes.

Watch the sessions at Microsoft Build:

• “Microsoft Build opening keynote”
• “Next generation AI for developers with the Microsoft Cloud”
• “Shaping next-gen development: the future of Copilot in Power Platform”

Deeper dives:

• Breakout: “What’s new with Microsoft Copilot Studio”
• Breakout with demos: “Build your own copilot with Microsoft Copilot Studio”
• Breakout with demos: “Build Microsoft Copilot extensions with Copilot Studio”
• Demo (live only): “Build your own Copilot extension with Microsoft Copilot Studio”

The post Microsoft Copilot Studio: Building copilots with agent capabilities appeared first on Microsoft Copilot Blog.

SOURCE: “IDC MarketScape: Worldwide General Purpose Conversational AI Software 2023 Vendor Assessment”, by Hayley Sutherland, Andrew Gens, and David Schubmehl; November 2023, IDC #US49988023.

Since its launch in November, Copilot Studio has introduced an enhanced conversational AI solution that includes the evolution of Power Virtual Agents, a new prompt and plugin designer, and several new generative AI capabilities, all integrated into a single SaaS experience.

Copilot Studio empowers IT teams to tailor copilots to the unique needs of their organizations, enabling the intuitive creation of generative AI experiences, manual topics, plugins, and custom GPTs, while offering flexibility and visibility throughout the process. Users can build, deploy, analyze, and manage Copilots all from within the same web experience. And users can even integrate Copilot Studio with Azure AI Studio, Azure Cognitive Services, Azure Bot Service, and other Microsoft conversational AI technologies.

Copilot Studio is already being used across entire organizations to enhance employee experiences with dedicated intelligent employee and HR copilots; to boost productivity with customized marketing and sales readiness copilots and to provide customer service at scale with customer facing copilots across websites and social media.

Thank you for the engagement and feedback from the community, customers, and partners. Your fresh ideas and feedback made Copilot Studio the transformational product it is today. We could not have done this without you.

We can’t wait to see what you create next!

Read the IDC MarketScape excerpt here
Copilot Studio resources to learn more:

• Website
• Product documentation
• Learning resources
• Ignite on-demand session
• Implementation guide
• Community page

 
IDC MarketScape vendor analysis model is designed to provide an overview of the competitive fitness of suppliers in a given market.  The research methodology utilizes a rigorous scoring methodology based on both qualitative and quantitative criteria that results in a single graphical illustration of each vendor’s position within a given market. The Capabilities score measures vendor product, go-to-market and business execution in the short-term. The Strategy score measures alignment of vendor strategies with customer requirements in a 3-5-year timeframe. Vendor market share is represented by the size of the circles. Vendor year-over-year growth rate relative to the given market is indicated by a plus, neutral or minus next to the vendor’s name.

The post Microsoft Named a Leader in the 2023 IDC MarketScape for Worldwide General Purpose Conversational AI Software appeared first on Microsoft Copilot Blog.

Following this feedback, we’re thrilled to announce the Copilot Studio implementation guide. This detailed guide is designed to help customers, partners, and Microsoft teams review copilot projects and architectures for a smooth and effective implementation journey.

Get ready for a comprehensive review of your Copilot Studio project

The Copilot Studio implementation guide provides a framework to do a 360-degree review of your project. Through probing questions, it highlights potential risks and gaps, aims at aligning the project with the product roadmap, and shares guidance, best practices and reference architecture examples.

Users of the implementation review are guided at each step of the journey with the side pane that provides more context on the questions or features, shares best practices, and includes links to additional resources.

Inspired by the Success by Design framework – a tried and tested Microsoft methodology used for Business Applications implementations – this review aims to detect bad patterns, identify risks, share best practices, and showcase example implementations.

Key principles behind the review

The Success by Design framework, the backbone of this review process, is centered around three critical principles:

1. Early Discovery: Identifying and dealing with potential issues at the earliest stage.
2. Proactive Guidance: Giving robust advice ahead of issues emerging, preventing potential problems.
3. Predictable Success: Providing a roadmap for success, using tested strategies and methods, and avoiding common pitfalls and anti-patterns.

Areas covered by the review

The Copilot Studio implementation guide covers these chapters:

• An overview of the project
• Architecture overview
• Language
• AI functionalities
• Integrations & channels
• Security, monitoring & governance specifications
• Application lifecycle management
• Analytics & KPIs
• Gaps & top requests
• Dynamics 365 Omnichannel (optional)

How is the implementation review typically delivered?

While it was initially delivered by Microsoft, the Copilot Studio implementation guide can now be used autonomously by customers and partners. It is designed to be a living document that can be updated throughout the project lifecycle.

Get the Copilot Studio implementation review today!

Download the Copilot Studio implementation review and provide feedback directly on GitHub, using this issue template.

We are confident that this tool will be beneficial to those implementing Copilot Studio and eagerly anticipate your feedback. Here’s to empowering more successful transformations with Microsoft Copilot Studio!

The post New Microsoft Copilot Studio implementation guide appeared first on Microsoft Copilot Blog.

The excitement and anticipation soared as we unveiled new generative AI features which changed how you both create copilots and respond with them. However, organizations worldwide have been eagerly awaiting harnessing these powerful AI capabilities in their own regions.

Today, we are pleased to share that we have expanded Copilot Studio’s designated region availability for generative AI capabilities beyond the United States, complete with robust admin controls.

This expansion brings these cutting-edge capabilities to various locations, including:

• Europe
• United Kingdom
• Canada
• France
• Australia
• India
• Japan
• Asia Pacific
• South America
• Switzerland

What’s more, in the coming months we’re poised to introduce additional generative AI features across even more geographical areas, empowering users worldwide to fully leverage Copilot Studio’s potential.

You can keep up to date with the latest availability here: Enable copilots and generative AI features.

To build your own copilot with these latest generative AI capabilities, read this guide.

Admins have newfound control over data movement in non-US geographical environments through the Power Platform admin center controls. Learn more.

If you want to learn more about Microsoft Copilot Studio, visit these resources:

• Copilot Studio website
• Start a trial
• Try a demo
• Watch the video
• Product documentation
• Catch up on the Ignite on-demand session
• Join the community

I am looking forward to seeing your innovations come to life with Copilot Studio, which is available worldwide.

Thank you once again from the entire Copilot Studio team for your continued support and enthusiasm.

The post Microsoft Copilot Studio Expands Region Availability For Generative AI appeared first on Microsoft Copilot Blog.

Over the last year alone, Generative AI has changed chatbots in many ways, but one of the most significant is that it has enabled them to produce natural and engaging responses that go beyond simple pre-defined rules or templates. By using advanced natural language models, chatbots can generate context-aware and personalized answers that match the tone, style and intent of the user. Generative AI also allows chatbots to learn from data and feedback, improving their performance over time and adapting to changing user needs and preferences.  Generative answers in Power Virtual Agents is a great example of how generative AI has saved makers significant time, and also made the chatbot more useful and intuitive for users.

Microsoft Copilot, combining the power of large language models with your organizations data is already one of the most powerful productivity tools on the planet – and it’s just getting started.  And, to respond to our customers’ needs as they adopt Copilot within their organization to ensure they do this successfully, we are excited to share that Power Virtual Agents will now play an even more important role in Conversational AI.

Today, we are announcing Microsoft Copilot Studio, a low-code comprehensive conversational AI solution that unlocks new Copilot capabilities: connect copilot to your data using pre-built or custom plugins and GPTs, create and orchestrate workflows and manage your copilots in one central place and ultimately build standalone copilots for your organization. Copilot for Microsoft 365 customers will be able to use Copilot Studio for customization to provide tailored responses and workflows for unique scenarios. Power Virtual Agents has provided the foundations for and will become part of Copilot Studio, together with Microsoft’s leading conversational AI technologies.

You can read more about the announcement here.

We want to personally thank every Power Platform community member, customer and partner who has used Power Virtual Agents over the years, creating innovative solutions, transforming both employee and customer experiences for the better and enabling us to get to this point today.

For existing Power Virtual Agents customers, there will be no interruption to your experiences or solutions. You will be able to use the same capabilities now found within Microsoft Copilot Studio – and all your existing bots will light up within Copilot Studio, just as they did in PVA.

We’ve been inspired by so many of the innovative solutions that customers have built using Power Virtual Agents.

The Miami Dolphins, well known in the world of American Football, uses Power Virtual Agents on its web properties to streamline the thousands of requests it gets from fans for information on events and facilities. By resolving 97% of conversations with the bot, service agents can focus on providing exceptional customer service and increasing ticket sales.

When the world changed at the beginning of COVID-19, Kobe, a city in Japan started receiving a massive amount in calls from concerned citizens that they couldn’t handle.  Using Power Virtual Agents, in two weeks, they built a solution that reduced the number of calls by 90% and ensured that citizens received the critical information and support that they needed.

And, Rabobank, a multinational banking institution in the Netherlands, made the innovative concept of conversational banking real, enabling connected customer engagement and continuous conversations across all channels, blending human and artificial interactions, with up to 80000 calls per month handled entirely through automation.

As Power Virtual Agents enters the era of Copilot, I am incredibly excited to see what amazing copilots you will build next, with Microsoft Copilot Studio.

Thank you again, the Power Virtual Agents team.

The post Microsoft Power Virtual Agents, now part of Microsoft Copilot Studio appeared first on Microsoft Copilot Blog.

Power Virtual Agents sessions 

• Vision of the Future of Bots and Bot Building 
• What’s New and Coming for Power Virtual Agents
• Best Practices Around Conversational AI Design Principles (How to Build Engaging Bots) 
• Bot Meets Knowledge Base – Secure and Intelligent Chat Bot with GPT in Power Virtual Agents 
• Unlocking the Power of Chatbots: An Introduction to Power Virtual Agents! 
• Bot Authoring Deep Dive – Advanced Bot Building Concepts 
• Power Platform Architecture Internals  
• Power Platform and Azure: Better Together 
• Transforming Bot Building Using Generative Actions 
• Unleash the Power of Virtual Agents! 
• An Espresso Shot of Being a Power Platform Admin and the Tools 
• Unlock the Power of Power Virtual Agents with Power Automate 

And more! 

Featured Power Virtual Agents speakers 

• Omar Aftab (Vice President for Conversational AI | Microsoft)
• Kendra Springer (Principal Design Lead for Power Virtual Agents and Conversational AI | Microsoft) 
• Bas Brekelmas (Partner Architect, Power Virtual Agents | Microsoft)  
• Gary Pretty (Principal Product Manager, Power Virtual Agents | Microsoft) 
• Dewain Robinson (Principal Program Manager | Microsoft) 
• Henry Jammes (Principal Program Manager, Power CAT | Microsoft) 
• Jack Rowbotham (Senior Product Marketing Manager | Microsoft) 
• Uday Adhikari (Power Platform Lead – North America | Accenture)  
• Dian Taylor (Dynamics 365 Goddess | RSM) 
• Laura Rogers (Microsoft MVP | CEO | IW Mentor) 

Don’t delay—sign up for the Microsoft Power Platform Conference today—we can’t wait to see you in Las Vegas! 
Click here to register: https://aka.ms/MPPC23/Agents/Register 
Click here for hotel reservations: https://aka.ms/MPPC23/Agents/Hotel 
 
 

The post Join us at the second Power Platform Conference this October in Las Vegas appeared first on Microsoft Copilot Blog.

Bot builders now have two ways of utilizing the Azure OpenAI Service within Power Virtual Agents. First, out of the box within Power Virtual Agents (SaaS) with features like Generative Answers/Actions and Copilot. Secondly, configure your own Azure OpenAI Service from the Azure AI Studio (PaaS) and connect it to PVA.

Keep reading to learn more about the scenarios and use cases for each technology.

What was previously announced?

At Microsoft Build, Power Virtual Agents showcased its latest generative AI feature, Generative Actions, that chains together requests using the Azure OpenAI Service to automatically detect and use plugins to best answer the questions being asked, with no prior topic building. It doesn’t stop there; the feature can generate clarifying questions to ask a customer or employee for additional information where it is missing from the selected plugins.

Power Virtual Agents has two additional features that utilize the Azure OpenAI Service;  Generative Answers, which allows for boosted conversational coverage by dynamically generating multi-turn answers based on an organization’s content in real-time and Copilot, which helps build, design, and modify bot topics through natural language. With all three features, companies can leverage these technologies together with the brand-new authoring canvas in Power Virtual Agents to get started creating and authoring meaningful conversational experiences in days.

The Generative Answers, Generative Actions and Copilot features use the Azure OpenAI Service and come ready to use in Power Virtual Agents. Azure OpenAI Service (AOAI) is a PaaS (Platform as a Service) offering by Microsoft that is provisioned and hosted by Microsoft Azure. Power Virtual Agents is Microsoft’s SaaS offering that takes a dependency on AOAI and by doing so creates a layered, managed feature set that works seamlessly. Both features work collaboratively together to solve those problems to provide superior conversational experiences for customers, agents, and internal employees.

What do both products do?

Both Power Virtual Agents (PVA) and Azure OpenAI Service aim to solve key business problems such as increasing deflection and reducing the cost to serve, while still providing detailed and accurate responses and reducing development time to allow organizations to quickly iterate and adapt to customer’s needs.

Power Virtual Agents is Microsoft’s modern and generative bot-building platform. Power Virtual Agents acts as a conversational and generative AI platform, making the process of creating, publishing and deploying a bot to any number of channels simple and accessible for every organization to use. From developers to business users, Microsoft Power Virtual Agents empowers everyone to create intelligent bots in a single experience.  Additionally, integration with over 1000+ Power Automate connectors makes integrating with your own enterprise services easy, including your own APIs, to provide contextual information within a bot experience. Power Virtual Agent utilizes the Azure OpenAI Services and provides extensive functionality in those features.

Azure OpenAI Service (including the new On Your Data feature) allows professionals to utilize a GPT model and to be used alongside existing business technology. Using Azure OpenAI Service on your data feature, organizations can target their organizational data and provide the same deployment experience as web app or API. Today, IKEA and Volvo are two Azure customers experimenting with the new feature in public preview. For both product types, more advanced configuration and customization can be done through fine tuning, prompt engineering and chunking.

Each of these technologies has distinct benefits based on the use cases, potential future needs and maintenance to support those use cases. Generative AI ‘question and answer’ scenarios, also referred to as ‘Retrieval Augmented Generation’ (RAG), leverages data sources to provide background context or in some cases domain specific knowledge to ‘ground’ the question being asked to increase the likelihood of a more accurate response. ‘Grounded’ data is a term used so that the question is grounded to the content and configuration you have provided, therefore more relevant to your organization.

Discovery Guidance

With that in mind, the following questions can help provide guidance to support determining a path based on what data you as a company want to use to ‘ground’ the question:

•   Security model: how is this data secured and protected?
•   What level of control do you require: How much control is needed over the searching of the data, prompts and output format? Additionally, consideration in this section includes the ability to manage and buy additional cloud services and data pipelines.

Both Power Virtual Agents and Azure OpenAI Service on your data provide the capabilities for ‘grounding’ your queries and customer data are not used for training, and it is not retained. 

The diagram below provides an overview of three core Conversational AI services by Microsoft and outlines a comparison of features focused on the three themes highlighted above to help support these discussions within your organization or with your customers.

To further support the discussion within your organization or with your customers, let’s review possible implementations where Power Virtual Agents is used with out-of-the-box features and then also extended with Azure OpenAI services.

Using PVA with Generative Answers (utilizing Azure Open AI)

•   Datastores :
  • Public Websites
  • Internal Documentation on SharePoint and OneDrive
  • Specific documents to be uploaded and
  • File Upload
  • 3^rd Party Data at runtime based on connectivity with Power Automate and using GPT answers at node level (see below)
•   For data elsewhere, it would depend on where that is, access and if that data is going to be moved. Added complexity occurs with multiple data stores. Azure OpenAI on your Data offers more flexibility for use cases where that is a requirement.

You can use PVA together with the Generative Answers and additionally use the Azure OpenAI Service:

•   Azure OpenAI Service APIs
  • Trained on the internet, can use any data and not specifically your company’s data.
  • Can include fine tuning etc.
  • Requires organizations to build and manage their own data pipelines & cloud services.

Azure OpenAI APIs can be used with Power Virtual Agents as an API and built into workflow logic and data architecture, for example, to be used as a plugin/action within specific topics using Power Automate.

•   Azure OpenAI Service On Your Data
  • Not trained on the internet and only on data you specify (‘grounded’)
  • Can include fine tuning etc.
  • Currently available using direct files, Blob storage and Azure Cognitive Search
  • Can be used as an API and built into your workflow logic and data architecture for example, to be used as a plugin/action within specific topics.

Azure OpenAI Service on your data can also be used with Power Virtual Agents as an API and provides a distinct experience of only utilizing the grounded data specialized. As with all implementations of AI, Responsible AI principles are important, and you can utilize Microsoft’s Responsible AI guidelines and tools here.

Extending the generative AI experience within Power Virtual Agents in scenarios where organizations require customization and fine tuning provides Bot Authors with the capabilities to use the low code authoring canvas in Power Virtual Agents, out of the box generative AI features, and where there are organizational requirements that require more customization, we are making it even easier to leverage Azure OpenAI on your data to meet those requirements with the ability to connect Azure on your Data directly by adding the connection string from Azure OpenAI on your data service within the node, providing the capability to ‘directly deploy’ from Azure OpenAI on your data to Power Virtual Agents from within the Azure OpenAI Studio.

Get started building your Conversational Experiences today!

Get started today with Power Virtual Agents with generative AI experiences:

• Sign up for Power Virtual Agents
• Try Generative Answers directly in your browser!
• Review of the latest features in Power Virtual Agents in our latest training material
• Take a look at Azure on your Data in Microsoft Azure today here!
• Read how to connect Power Virtual Agents with Azure on your data.

Thank you to all the teams involved in making this interoperability possible between products to help drive positive customer outcomes including Jeff Derstadt, Jim Lewallen, Neta Haiby, Mai Nguyen, Jack Rowbotham, Andy Beatman, Pavan Li and Ben Ufuk Tezcan

The post Create Generative AI solutions with Power Virtual Agents and Azure OpenAI Services appeared first on Microsoft Copilot Blog.

Today, we’re unveiling a set of cutting-edge generative AI features within Microsoft Power Virtual Agents, designed to revolutionize the way bots are built using simple natural language prompts. This follows and builds upon our recent announcements of bots that can use generative AI to provide tenant-specific answers right out of the box. And the best part? You can preview these exciting new developments right now.

Copilot in Microsoft Power Virtual Agents

Imagine simply describing what you would like your bot to do in natural language and having a complete conversational dialog appear—ready to use in seconds—without painstakingly having to build and curate dialogs step by step.

That future is here. Introducing Copilot in Power Virtual Agents, a new feature that uses the latest generative AI capabilities to make this possible. An author can simply state: “allow a user to start planning an event, collect user’s email address and phone number, and let them choose the event type from wedding, corporate, and social event,” and a dialog to do so will be instantly created—complete with trigger phrases, entities, variables, and appropriate branching. The author can then select part of the dialog and use additional natural language prompts to refine it—or use the Power Virtual Agents intuitive graphical user interface to tweak it manually.

The low-code user experience and Copilot assistant help make bot building accessible for everyone and makes creating conversations—which is already a key strength of Power Virtual Agents—easier than ever before.

Watch it in action and learn more:

Democratizing conversational AI has long been the mission of Power Virtual Agents. Creating bots in the industry has traditionally been a time-consuming process that could take months—or even years. The Power Virtual Agents end-to-end software as a service (SaaS) experience and intuitive user interface already transformed this by making building dialog incredibly easily—even for non-technical bot builders, shortening the development cycle to weeks. And now, with the new Copilot in Power Virtual Agents, bot building is simpler. Using natural language, anyone can create and iterate over topics in minutes.

Copilot in Power Virtual Agents can help:

• Create entire topics from a simple description, including relevant trigger phrases, questions, entity, messages, variables, and other logic.
• Add or update content in an existing topic, such as asking for additional questions to be added or updating existing nodes (example: providing message variations).
• Summarize information collected from a user in an interactive, graphical Adaptive Card, with all the JSON for the card generated automatically.
• Iterate over just part of a dialog—select one or more nodes to scope your request to that specific part of the dialog.

Here are just a few examples of natural language prompts you can use:

• “Let a user check the status of a flight, accepting the flight number and date. For each question, add two message variations.”
• “Accept a user’s name, age, and date of birth, and then repeat their responses back to them.”
• “Create a support ticket, including a title, severity (high/medium/low), description, and an email address to send update notifications to. Summarize the information in an Adaptive Card.”

Bot building, transformed with generative AI

Taken together, the two generative AI features we have announced for Power Virtual Agents transform the traditional model of bot development.

First, our new generative AI conversation boosters in Power Virtual Agents allow bots to chat over your company’s information with just a URL. When a user query (“how do I upgrade my meter”) doesn’t trigger a manually-created topic, Power Virtual Agents searches for relevant information over a knowledge source that you point it to (for example, your company’s website, internal knowledge base (KB), intranet). The results are filtered and passed to Microsoft Azure OpenAI Service, which summarizes a response for the user. Bots can then instantly answer hundreds of user questions, out of the box, by chatting over the specified content.

Here are some examples of bots answering company-specific questions, seconds after creation—with no manual intervention.

This addresses a set of long-standing challenges with bots:

• Bots historically need a lot of manual authoring to get started—now they are useful out of the box with no manual dialog creation.
• Most bots only have a few manually authored topics and just escalate to humans when asked about anything else. Now, they can chat over the entire corpus provided, dramatically improving topic coverage and significantly improving both customer chat experience and support deflection.
• Bot content needed to be continually updated and kept in sync with the company website and other knowledge sources as information changed—but now there is no separate bot-specific knowledge to maintain.

When combined with the Power Virtual Agents end-to-end SaaS infrastructure, conversation boosters make it possible to sign up, point to a website, deploy to the Power Virtual Agents SaaS, and have a useful bot live in the channel of your choice within minutes. That bot can then be expanded easily with manually built dialogs as needed using the powerful Copilot capabilities discussed earlier.

Want a customer bot that can chat over all the content on your website? An HR bot that can answer employee questions based on your internal HR site? Check out the videos for conversation boosters for both customer-facing bots and employee-facing scenarios, and for our Copilot features, see the preceding sections. Then try it out yourself today.

You can read more about our next-generation AI announcement on the Official Microsoft Blog. Happy bot building!

Availability

Both features are currently available in the United States and English language. Note that these preview features are experimental, and accuracy and relevance cannot be guaranteed. These features use the Azure OpenAI Service, managed through the Power Virtual Agents SaaS experience.

Try both features for free now

1. Go to the Power Virtual Agents webpage and log in to your existing Power Virtual Agents account or sign up for a free trial.
2. After you land in the product, click the ‘Create’ tab on the left navigation menu.
3. Click the option to ‘Try the unified canvas (preview)’ to create a bot with the new GPT capabilities.

Responsible AI

Microsoft is committed to creating responsible AI by design. Our work is guided by a core set of principles: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability. We are helping our customers use our AI products responsibly, sharing our learnings, and building trust-based partnerships. For these new services, we provide our customers with information about the intended uses, capabilities, and limitations of our AI platform service, so they have the knowledge necessary to make responsible deployment choices.

The post Copilot in Power Virtual Agents: Next-generation AI assists bot building with natural language appeared first on Microsoft Copilot Blog.