Bill Gates had the vision to put a computer in every home almost 30 years ago and since then, technology has become ubiquitous in modern society. As seen at Microsoft Build, Microsoft Copilot is on a journey to become more ubiquitous with work and life with its ability to assist us in typical tasks, boosting productivity and creating efficiency.

Copilot Studio is at the forefront of this technology, where copilots are not just doing work for you, but also with you, such as copilots being mentioned within Microsoft Teams, just as a person would be able to be mentioned. Copilot Studio has been used by 30,000 organizations across the world, and with these latest features and improvements to the Conversational AI Platform, including Copilot Connectors, Analytics and Templates, there has been tremendous adoption of this technology across numerous industries where it enables organizations to achieve and demonstrate value that supports their objectives and organizational goals.

Student and Education Support

Within the education industry, Victoria University of Wellington realized students are bombarded with information when they begin their journey at university. Despite having access to numerous resources, it is hard for students to navigate the large amount of information—when they search, the students were given links and not actual answers. Victoria University of Wellington has the ambition to create a ‘single pane of glass’ experience whereby students can answer questions using the Copilot Studio built-in Generative AI capabilities through Knowledge, using the University’s data sources to provide natural language responses to questions. The feedback from our Pilot was overwhelmingly positive with over 90% of the students reporting a positive experience and 95% saying they would use it again. The University is now looking to utilize this technology to expand support for students.

BYU Pathway Worldwide had a manual Copilot Studio support bot in place for years, but as soon as they infused generative AI, they saw an immediate time savings of over 150 human hours per week. This savings allows the team to provide better customer service, spread support across other areas, and focus on higher-value-add efforts.

Financial Services Innovation

Financial services organizations have been at the forefront of innovation, where organizations like Rabobank and Paypal have been utilizing Copilot Studio. Virgin Money’s Copilot, ‘Redi’, was featured at Microsoft Build, their Credit Card Copilot experience that recently won an award at the Card & Payments Awards for the ‘Best application of AI in Financial Services’ where it supports credit card customers 24/7 within the Virgin Money Credit Card app.

Local Government & Services

There has been similar innovation in local government with City of Burlington and City of Kelowna utilizing the Copilot Studio platform.  City of Burlington created ‘CoBy’ and are using it in production today. The digital assistant demonstrates the ability to discover, digest, aggregate, and abbreviate information-heavy content and provide the City’s residents with easy-to-understand and human-friendly responses. Questions regarding City services and/or regulatory requirements are answered, based on the content published on Burlington.ca. The addition of CoBy is expected to enhance customer service by providing 24/7 support and more opportunities for the public to engage with the City. The City of Kelowna have also utilized Copilot Studio to provide outcomes for their citizens helping build homes faster within the province together with the integration with Azure OpenAI, where ‘Using Copilot Studio and Azure OpenAI Services as tools to improve our building permit application process supports the work the City of Kelowna is doing to address the housing crisis by delivering more homes, faster’ (John Brennan, Director of IT, City of Kelowna)

Transportation

London Heathrow Airport runs a passenger experience program called “Here to Help” where non-operational colleagues spend time in airport terminals to assist customers with commonly asked questions. Using Copilot Studio, they have enabled “Here to Help” colleagues with a collaborative custom copilot to provide real-time answers to customer questions in Microsoft Teams. Copilot Studio enabled developers to quickly pull together information from a range of sources – the public website, internal FAQ documentation and even bus timetables – to support colleagues using AI instead of relying on manual searches, other colleagues or phone calls. This will enhance passenger experience and the confidence of the “Here to Help” team who may only work in the terminals 4 or 5 times a year.

Supporting Non-Profit Vision

In the non-profit industry, there are numerous use cases being identified to help bring innovation to benefit the world such as through making volunteer management easier or for nonprofit organizations like Centro de la Familia, who 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.

Enterprise Transformation Journeys

Copilot Studio is also being used inside Microsoft itself. Microsoft’s HR teams create a lot of content in service of employees and the organization. HRWeb, a portal that hosts this wide-ranging content, receives an average of 8 million visits per year. But even with all this information at employees’ disposal, the HR team still received 800,000 service tickets that needed to be addressed manually. The custom copilot deflects 60% of incoming queries enabling employees to gain 21,000+ hours of productivity and reduce 27% of incoming service tickets.

Accenture has also been on a journey working with Copilot Studio that has been transformative, where Karen Odegaard, Managing Director, shares they are ‘leveraging generative AI-powered solutions and democratizing custom copilot creation. Streamlining mundane tasks like checking status to multi-turn agentic conversation with scoped knowledge is now easier than ever.”

What’s next?

It is clear to see that innovation is happening across industries and Copilot Studio is at the center.

We even saw what is on the horizon, with themes such as multi-modal interfaces and users being able to share context of what is being worked on or even show real life objects in the space with you. Additionally, the ability to use context and memory to delegate work using asynchronous agents that keep the personalization of an interaction.

For more information about the Microsoft Build 2024 sessions on the latest announcements and custom copilot demonstrations, check out the blog and read about Partners delivering customer impact with Copilot Studio.

The post Delivering Organizational Value with Microsoft Copilot Studio 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.

With this announcement comes some big updates to Power Virtual Agent’s supporting materials and documentation covering the latest functionality.  Customers and partners can now use the latest content including Power Virtual Agents in a Day (PVAiaD) student and instructor content.

What is a Power Virtual Agents in a Day event?

Power Virtual Agents in a Day is part of Microsoft’s In a Day (XIAD) program that is a one-day hands-on Partner led workshop for end users that provides new skills to help customers use and adopt Power Platform products, and advocate within their organization. Organizations can also choose to take the content and run their own events internally within their company and can be used generally by anyone who wants to use it for learning and training.

PVAID includes specific lab content for students, and for instructors, materials for them to run the event for their students. Microsoft Partners can become an XIAD Partner by reviewing the material on how to sign up as a XAID Partner, the program requirements and follow the process to create Microsoft affiliated events on the Microsoft Events page for people to sign up.

Power Virtual Agents in a day – Reimagined

As a result of the new release and the feedback we have received for both Power Virtual Agents latest features and pilots we have run across the last 6 months in the XIAD Communities, the product group have taken the time to review the opportunity we have to serve all the areas that the product operates in, including Low Code, Data and AI, Business Applications and Modern Work and create flexible material that can be catered for all these different areas and domains, especially where Microsoft Partners also have different specialisms and areas of expertise that should be promoted and utilized within the events they run.

To take this feedback into consideration, we are excited to share the latest version of Power Virtual Agents in a Day has been refined with the following updates:

• Labs are no longer dependent on each other and instead have ‘recommendations’ on pre-requisite labs that are not mandatory. Students can move to the next lab without finishing the lab if required and would not be ‘stuck’ as there are no dependencies in an environment to complete a lab.
• We have created a format where foundational product content that covers fundamentals can be covered in approx. half a day and extended using elective modules based on the type of event and expertise of the Partner. There will be upcoming guidance on a ‘standard’ or ‘typical’ format if the Partner did not want to customize the agenda themselves.
• By providing flexibility for extensive modules, these will be published within an elective library with the instructor material and within Microsoft Learn when the content is created and updated. Catering for the extensibility of the product to support additional applications.
• We have expanded on the fundamental content and created brand new fundamental content to highlight key features including NLU, Generative AI Features and Labs, including Generative Answers and Copilot, and Power Automate, in addition to “how to plan for a PVA project” using the Power CAT PVA Playbook
• The Lab material is now on Microsoft Learn to help distribute content easier for students.

The new Instructor material includes:

• The main instructor deck that is used to walk through the labs with the students now includes a brand new introductory session that the instructor presents which includes Conversational AI fundamentals, approaches, and considerations when working with Power Virtual Agents and a core introduction to PVA to help set the scene for the day and educate on key terminology that students may not be familiar with
• The initial Train the Trainer deck has been updated and covers the latest updates and how to run a PVAIAD event.
• Instructions on setting up environments and users (unchanged from previous material)

Next steps:

Get started with Power Virtual Agents in a Day and ensure you are signed up to be a PVAIAD Partner. As a Microsoft Partner, you can generate interest and thought leadership in the latest AI features for customers within Power Virtual Agents. If you’re a customer, either consider joining a Partner led event or run your own internal event using this content!

• As a student, check out the Microsoft Learn Power Virtual Agents in a day NEW Lab Content here
• Review the latest Instructor material.
• Microsoft Partners to check out the latest content on the Power Platform Hub
• Provide feedback on PVAIAD – Power Virtual Agents in a Day Updates – Feature Requests | Product Roadmap

For more information reach out to xiadevents@microsoft.com

The post Power Virtual Agents in a Day Update – New Canvas, New Content! appeared first on Microsoft Copilot Blog.

We heard from our community that you want to be able to try out Power Virtual Agents’ new features before buying. Well, now you can by combining Microsoft’s 365 Developer plan, Power Apps Developer plan, and the Power Virtual Agents trial.

Follow these four easy steps below to get set up and try out all the new features like advanced topic management, interactive adaptive cards, multi-media responses (images, videos, quick replies), PowerFX, variable management, and more! 

Getting started:

1. Obtain a personal account

Use a personal account that you’re happy to use for signing up for the Microsoft Developer Account. If you do not have a personal account, you can create a new one with Outlook.

2. Sign up for a Microsoft 365 Developer Account

Use the personal account to sign up for the Microsoft 365 Developer Program.

By signing up for the Microsoft 365 Developer Account, you will receive new credentials ending with ‘onmicrosoft.com’. This account is not to be confused with your company’s login. These will be your credentials for the next step.

The Microsoft 365 Developer program provisions the tenant, Office and other supplementary apps.

Tip: Incognito/InPrivate browsers work best when logging in to prevent login conflicts between any accounts already logged in.

Note: When making a new Microsoft 365 Developer Account from a brand new personal account, you may need to wait a few hours for your account to be completed.

3. Attaching the Power Apps Developer plan to your account

This Microsoft 365 Developer account is used to attach both the Power Apps Developer Plan and the Power Virtual Agent Trial to.

What’s included in the Power App Developer plan?

• Free development and testing of Power Apps/ Power Automate – Easily share and collaborate with others. (Step 4 adds Power Virtual Agents)
• Developer-friendly – Utilize Power Automates’ 900+ data sources, including premium connectors like Azure, Dynamics 365, and custom APIs.
• Dataverse included – A fully managed, scalable, Azure-backed data platform. 

To attach the Power Apps Developer Plan, follow the instructions outlined here – Create a developer environment using the ‘onmicrosoft.com’ work credentials from the previous step.

4. Get creating with Power Virtual Agents

Once you have set up the Power Apps development environment, go to the Power Virtual Agents trial, log in with your new credentials and complete the sign up.

Since the Power Apps Developer Plan includes Microsoft Dataverse, it means you can use Power Automate and Dataverse to connect to Power Virtual Agents, which unlocks even more of the possibilities within your bots!

Now you should be all set up to create your first bot and get testing!

Don’t forget to share your creations!

Be sure to share your latest Power Virtual Agents creation with our Twitter and LinkedIn channels. As a reminder, please do not share any sensitive data via screenshots/videos.

Happy bot building!

The post Signing up for a developer plan for Power Virtual Agents appeared first on Microsoft Copilot Blog.