Many organizations use SharePoint to power their employee-facing websites, delivering experiences that streamline the way employees interact with the organization and with each other. SharePoint is also the content management platform behind OneDrive, Teams and other Microsoft 365 services.

In 2023, we announced Generative AI features in Microsoft Copilot Studio that transform the traditional model of bot development and allow makers to build copilots that respond to questions, simply by pointing the copilot at knowledge sources like public websites or content stored in SharePoint and OneDrive. Given all the content that is already managed in SharePoint, the Generative Answers capability makes it easier than ever to create an employee-facing, conversational AI experience, that can answer questions on topics like personal time-off, perks and benefits or company policies.

Copilots created with Copilot Studio can be easily published to Microsoft Teams and other channels. However, many use cases would benefit from copilots deployed directly on SharePoint sites, allowing a conversational experience grounded in the sites’ pages and documents. For example, think about a SharePoint site consolidating HR related information, with an embedded copilot answering employee questions and referencing the relevant HR policies.

This can be achieved using the new code sample: the component included in the sample allows copilots created with Microsoft Copilot Studio to be wrapped and published to SharePoint sites as a floating widget. The component also supports SSO, so users would do not have to provide their credentials or use the validation code required by the standard copilot canvas.

How does the new code sample work?

This sample includes a SharePoint Framework Extension (SPFx) component which acts as a wrapper for copilots created with Microsoft Copilot Studio.

A user accessing a SharePoint site has already signed-in using their Microsoft Entra ID credentials. The SPFx component, embedded natively in SharePoint sites, acquires a token for the user, and exchanges the token with the copilot, allowing the copilot to access protected data sources, like SharePoint and OneDrive, on the user’s behalf.

For example, a user with access to a SharePoint site dedicated to Perks and Benefits will be able to interact with an embedded copilot, by asking questions like “do we get reimbursed for professional training?”. The copilot will answer the user’s questions based on the site’s pages and documents, but only those to which the user already has access. Most of this flow is made possible by the Generative Answers capability, with the SPFx component handling single sign-on, so users do not have to enter credentials or a validation code.

How can I deploy the component on my SharePoint site?

Creating a wrapper for Copilot Studio that can be deployed in SharePoint, with SSO support, can be somewhat of an involved process. It requires an understanding of the SPFx framework, as well as setting up the required permissions in Azure.

Luckily, the code sample comes with a step-by-step guide, with detailed instructions on how to:

• Set up the app registration configurations required for SSO.
• Set up a Generative Answers node for your copilot, over a SharePoint or OneDrive data source.
• Build the SPFx component from scratch and bind it to your copilot.
• Upload the component to the tenant app catalog and deploy on a site.

Suggest feedback or report issues related to the sample here

The post Deploy a custom copilot to SharePoint, with a seamless single sign-on experience 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.

This involves testing user utterances to confirm that the bot understands them correctly and triggers the appropriate topics. It also entails verifying that the full conversation leads to the intended outcome, such as resolution or escalation. Customers might also want to ensure that their chatbots meet quality requirements before deploying to production, which can be done automatically using Continuous Integration/Continuous Delivery (CI/CD) approaches like Azure DevOps.

The Power Virtual Agents teams have recently released new code samples to help automate chatbot tests, including testing utterances, validating topic triggering, intent candidates (multiple topics matched), playback of full conversation transcripts, and integration into a CI/CD pipeline.

What can be tested with the PVA Test Framework sample solution?

The PVA Test Framework is a sample solution available on GitHub that showcases how to execute tests against a Power Virtual Agents chatbot through APIs, using the Direct Line channel. It verifies that the bot performs as expected in various scenarios, such as:

• Testing the Natural Language Understanding model (topic triggering)
• Validating the multiple topics matched options (“did you mean…”)
• Performing scale load testing
• Testing full end-to-end conversations
• Testing adaptive cards
• Including a CI/CD test step in the deployment pipeline to prevent deployment if tests fail

How does the PVA Test Framework sample solution work?

The PVA Test Framework tool is a console application that can run tests against the Power Virtual Agents Direct Line API. It uses JSON as the format to play conversations back and verify outcomes, and it enables you to connect to Dataverse to download past conversation transcripts to run them again.

How to use the PVA Test Framework tool

There are different ways you can use the PVA Test Framework sample solution. The easiest one is to run it locally with the Command Prompt in Windows.

You first need to download or build the PVATestFramework.Console.exe file.
It then works as a console application, with command lines.

To run tests, you need conversation files in a .JSON format. You can either easily create these files from scratch, by writing your test cases in a .CHAT file format and converting them to .JSON, or you can download conversation transcripts from Dataverse.

For Natural Language Understanding testing, where you test many user utterances and verify that the bot answers as expected, it’s usually easier to start from your own set of user and bot utterances in a .CHAT format.

This command transforms a .CHAT file into a .JSON file:

.\PVATestFramework.exe convertChatFile --path test-set-sample.chat --outputFile test-set-sample.json

Here is what conversations look like a .CHAT format:

Each test conversation is separated by the <EOC> tag (end of conversation).
Messages following the user: tag are sent by the tool to the bot, and the messages received back from the bot are compared with the expected response, documented after the bot: tag, to determine if the test passes or fails.

user: Good morning
bot: Hello, how can I help you today?
<EOC>
user: When are you closed
bot: I'm happy to help with store hours.
<EOC>
user: Find me your nearest location
bot: I'd be glad to help find a store near you.
<EOC>
user: Where can I find your address?
bot: I'd be glad to help find a store near you.
<EOC>
user: I'd like to order a product
bot: I am happy to help you place your order.
<EOC>
user: what are you store hours and locations?
suggested: Lesson 2 - A simple topic with a condition and variable|Lesson 1 - A simple topic||None of these
bot: To clarify, did you mean:
user: Lesson 1 - A simple topic
bot: I'm happy to help with store hours.
<EOC>
user: What is weather today?
bot: I'm sorry, I'm not sure how to help with that. Can you try rephrasing?
<EOC>
user: What is weather today?
bot: I'm sorry, I'm not sure how to help with that. Can you try rephrasing?
<EOC>

Once converted to .JSON, you can run tests by using the below sample command. You can obtain the chatbot token endpoint from the Mobile app channel in Power Virtual Agents.

.\PVATestFramework.exe test --path test-set-sample.json --tokenEndpoint https://c53bf00279234d1cb5ae3265093d59.e1.environment.api.powerplatform.com/powervirtualagents/botsbyschema/cr507_testChatbot/directline/token?api-version=2022-03-01-preview --log --verbose

Test outcomes are then available in a CSV format that you can then use for further analysis.

Example analysis of the outputs of the PVA Test Framework:

You can learn more about the PVA Test Framework sample solution’s different settings and deployment options in the GitHub documentation.

Frequently Asked Questions

What is the cost of using the PVA Test Framework sample solution?

Conversations generated using the PVA Test Framework sample solution would typically generate billed sessions. See: Power Virtual Agents pricing.

How is the PVA Test Framework supported by Microsoft?

Although the underlying features and components used to build the PVA Test Framework are fully supported, the code itself represents a sample implementation of these features.

Our customers and community can use and customize these features to meet their requirements. Any issue with the PVA Test Framework sample solution should be raised on the Power Virtual Agents Samples GitHub repository and not through Microsoft Support.

The post Automate testing of your Power Virtual Agents chatbots with the PVA Test Framework sample solution appeared first on Microsoft Copilot Blog.

What is the Center of Excellence Starter Kit?

The Microsoft Power Platform CoE Starter Kit is a collection of components and tools that are designed to help organizations develop a strategy for adopting and supporting Microsoft Power Platform, with a focus on Power Apps, Power Automate, Power Pages, and Power Virtual Agents.

What is new for Power Virtual Agents in this release?

The CoE Starter Kit in its current version already included an inventory of bots across environments. This release introduces new capabilities that allow tenant administrators to:

• Keep track of the number of conversations per bot over time, with daily aggregates. While conversation transcripts are kept for a default duration of 30 days in Dataverse, the CoE Starter Kit generates aggregates for each bot, every day. A ‘last month’ aggregate is now also available at the bot and environment levels.
• Allocate a number of conversations per environment, as part of the environment add-ons.
• Receive capacity email alerts when environment add-ons get near (above 80%) or over their allocated number of conversations.
• Get an overview dashboard of Power Virtual Agents usage in their tenant over time as well as an all-up conversation consumption versus allocation.
• Identify bots that have been created using the new unified authoring canvas, now available in public preview.

Screenshot of the Power Virtual Agents dashboard in the CoE Starter Kit.

In the Power Virtual Agents Dashboard, administrators can see the volume of conversations over time, per bot or per environment, and keep track of actual usage versus allocation at the environment level.

Screenshot of a Power Virtual Agents bot in the CoE Starter Kit

When looking at an individual bot, an administrator can also access usage history, with a number of conversations per month.

Screenshot of an Environment Add-on record in the CoE Starter Kit

At the environment level, administrators can leverage the ‘Environment Add-on’ record to set an allocated number of conversations for it. This allocation isn’t technically enforced but is used to trigger capacity email alerts.

Screenshot of a capacity email alert notification

When an environment goes near or over their monthly allocated number of conversations, an email is sent to the configured administrators.

Frequently Asked Questions

Does the CoE Starter Kit cover bots that are created in the Power Virtual Agents Microsoft Teams app?

No, this doesn’t cover bots created in the context of PVA for Teams (https://aka.ms/PVAforTeams). This is because these bots reside in Dataverse for Teams environments, and data in these types of environments can’t be accessed from Power Automate, which the CoE starter kit uses to gather inventory data.

Are conversations the same thing as billed sessions?

This extension doesn’t use the concept of ‘billed sessions’ but counts the number of conversation transcript records instead. Billed sessions are still available to customers as part of their bot analytics, in Power Virtual Agents.

How can I deploy the CoE Starter Kit in my tenant?

Installation instructions are available here.

I have setup the CoE Starter Kit but only see aggregates for the past day

By default, the CoE Starter Kit only starts creating daily aggregate records for bot conversations the day the latest version is set up. If you need to rebuild aggregates for past conversation transcript records data, you can install the CenterofExcellencePVAUsageFirstRunAllData_1_0_0_0_managed.zip solution, available here, and run its flow once.

How is the CoE Starter Kit supported by Microsoft?

Although the underlying features and components used to build the CoE Starter Kit (such as Microsoft Dataverse, admin APIs, and connectors) are fully supported, the kit itself represents sample implementations of these features. Our customers and community can use and customize these features to implement admin and governance capabilities in their organizations. If you face issues with:

• Using the kit: report your issue here: https://aka.ms/coe-starter-kit-issues. (Microsoft Support won’t help you with issues related to this kit, but they will help with related, underlying platform and feature issues.)
• The core features in Microsoft Power Platform: use your standard channel to contact Microsoft Support.

The post Center of Excellence Starter Kit with Power Virtual Agents: Govern, Monitor and Manage appeared first on Microsoft Copilot Blog.

This year at Microsoft Build 2022, we announced that Power Virtual Agents Customer Lockbox support is coming soon. Today, we are excited to announce the preview of Power Virtual Agents Customer Lockbox support.

Customer Lockbox enables administrators to control access to their organization data from Microsoft personnel during troubleshooting. Administrators can turn on the Customer Lockbox feature for their tenants from the Power Platform admin center, view Microsoft personnel’s data access requests, and approve or deny them as the final gatekeeper.

Watch below to learn how to enable the Customer Lockbox feature and approve or deny Microsoft personnel data access requests.

To learn about the Customer Lockbox feature, see the documentation here.

We’d love to hear about your experience with this feature! Please visit our community forum at https://aka.ms/PowerVirtualAgentsForum and share your feedback.

If you have any idea requests, please submit them at https://aka.ms/PowerVirtualAgentsIdeas.

Disclaimer

This feature is in preview, which means it is made available to you before general availability so you can test and evaluate them and provide feedback to Microsoft.

Preview may employ reduced or different privacy, security, or compliance commitments than commercial versions. As such, previews are not meant to be used with any “live” or production Customer Data, Personal Data, or other data that is subject to heightened compliance requirements. Any use of “live” data is at your sole risk, and it is your sole responsibility to notify your end users that they should not include sensitive information with their use of the Preview.

This preview, and any support Microsoft may elect to provide, are provided “as-is,” “with all faults,” “as available,” and without warranty.

The post Announcing the preview of Power Virtual Agents Customer Lockbox support appeared first on Microsoft Copilot Blog.

Today we’re announcing the general availability of Microsoft Power Virtual Agents for US Government customers in Government Community Cloud (GCC) and Government Community Cloud – High (GCC High). These environments support compliance with US government requirements for cloud services, including FedRAMP High, and requirements for criminal justice.

Agencies can now use Microsoft Power Virtual Agents to address many major issues with chatbot building in the industry today. It eliminates the gap between subject matter experts and the development teams building the chatbots and the long latency between subject matter experts recognizing an issue and updating a chatbot to address it. It removes the complexity of exposing teams to the nuances of conversational AI and the need to write complex code. It also minimizes the IT effort required to deploy and maintain a custom conversational solution by empowering subject matter experts and departments to build and maintain their conversational solutions.

Below is a quick demo of Power Virtual Agents in GCC High.

For more information on how to get started, refer to the documentation here on Power Virtual Agents for US Government customers. To learn more about the supported compliance offering, visit the Power Virtual Agents compliance offerings.

We’d love to hear about your experience with this feature! Please visit our community forum at https://aka.ms/PowerVirtualAgentsForum and share your feedback.

If you have any idea requests, please submit them at https://aka.ms/PowerVirtualAgentsIdeas.

Happy bot building!

The post Announcing the General Availability of Microsoft Power Virtual Agents for US Government customers appeared first on Microsoft Copilot Blog.

We are happy to announce that the feature enabling Power Virtual Agents bots to be used as skills with Bot Framework bots has reached General Availability.

If you have Bot Framework bots deployed in your organization, you can now easily extend them with Power Virtual Agents functionality using this capability.

When you add a Power Virtual Agents bot as a skill, the Bot Framework bot will determine if anything the bot user says matches with any of the trigger phrases in the Power Virtual Agent’s bot.  If there is a match, the Bot Framework bot will automatically invoke the Power Virtual Agents bot and pass the entire user utterance to it to extract any entities and trigger a matching Power Virtual Agents topic.

Additionally, from a Bot Framework bot, you can invoke a Power Virtual Agents bot’s topic with inputs and utilize the outputs it returns.

With this new feature in Power Virtual Agents, you can:

• Explicitly control which Bot Framework bots are allowed to connect to your Power Virtual Agents bot.
  

  Control which Bot Framework bots are allowed to connect to your Power Virtual Agents bot

• Easily download Test or Published bot’s skill manifest, enabling you to test changes in your Power Virtual Agents skill bot before publishing them.
  

  Download Power Virtual Agents Test and Published bot skill manifests

• Connect to a Power Virtual Agents skill in Composer using Power Virtual Agents skill manifest.
  

  Add a Power Virtual Agents bot as a skill in Composer

• Call a specific Power Virtual Agents skill topic from a Composer bot.
  

  Use Activity to invoke a topic in a Power Virtual Agents skill.

• Pass an input variable to a Power Virtual Agents skill topic from Composer bot.
  

  Pass inputs to a Power Virtual Agents bot skill topic in Composer

• Receive an output variable from a Power Virtual Agents skill topic in Composer bot.
  

  Get outputs from a Power Virtual Agents bot skill’s topic in Composer

Learn more

For more information, visit the documentation on using a Power Virtual Agents bot as a skill.

Join our Power Virtual Agents community to share your ideas, provide your comments, and help drive the future direction of our product development.

The post Power Virtual Agents bots as skills with Bot Framework bots – General Availability appeared first on Microsoft Copilot Blog.

If a Bot Framework bot matches a user utterance to Power Virtual Agents bot skill’s trigger phrases at runtime, it will automatically pass this user utterance to the Power Virtual Agent bot to handle. The Power Virtual Agents bot will then evaluate the user utterance, extract the Entities for any slot-filling and kick off a matching Power Virtual Agents Topic.

Add your Bot Framework bot to Allowlist in Power Virtual Agents

All Bot Framework bots intending to use a Power Virtual Agents bot as a skill must be added to the Allowlist of this bot first. The Allowlist can be found under the Manage tab on Skills page in Power Virtual Agents:

Manage allowlist for Power Virtual Agents bot

By default, no Bot Framework bots can use your Power Virtual Agents bot as a skill. To enable some Bot Framework bots to establish a skill connection to your Power Virtual Agents bot , add them to your bot’s Allowlist by their App ID. 

Add Bot Framework bot’s App ID to the Allowlist

Download a Power Virtual Agents skill manifest

Every Power Virtual Agents bot now has a skill manifest, a JSON file that describes skill’s name, interface, and skill’s trigger phrases. Bot Framework bots will use this manifest to configure a skill connection to the bot. At runtime, the manifest data will be used to identify when a skill should be triggered in response to a user utterance.

All Power Virtual Agents skill manifests are automatically generated and updated according to version 2.2 skill manifest schema. A Virtual Agents bot has 2 different skill manifests, Test manifest and Published manifest.

Test manifest — allows to connect to the Test version of your Power Virtual Agents bot. The Test manifest is immediately available for every Power Virtual Agents bot. It is automatically updated every time you Save bot content. You can use the Test manifest to test out the changes in your skill  before Publishing them.

Published manifest — allows to connect to the Published version of your Power Virtual Agents bot. The Published manifest is only available for Power Virtual Agents bots that have been Published at least once. It is automatically updated every time you Publish your bot.

Both Power Virtual Agents bot’s skill manifests can be found on Manage allowlist panel and will be downloaded as .zip archives.

Download Power Virtual Agents skill manifests

Connect to a Power Virtual Agents skill bot in Bot Framework Composer

You can use the Power Virtual Agents bot skill Test manifest or Published manifest to create a skill connection for your Bot Framework bot in Composer.

In Bot Framework Composer project, use + Add button and choose Connect to a skill menu option.

Connect to a skill in Composer

On Add a skill screen in Composer, select a Power Virtual Agents manifest .zip archive and follow the Skill connection wizard in Composer:

Select manifest .zip archive in Composer

Your Power Visual Agents bot is added as a skill in Composer and now your Bot Framework bot is extended with Power Virtual Agents Topics:

Power Virtual Agents bot added as a skill in Composer

Current limitations – Public Preview

• This feature is not available to users who only have the Teams Power Virtual Agents license. You must have a trial or full Power Virtual Agents license.
• Power Virtual Agents bot skill Topics can only be invoked by a user utterance from a Bot Framework bot. Invoking Power Virtual Agents Topics as skill Actions is not supported in Public Preview.
• Only the Bot Framework bots that are deployed in the same tenant as the Power Virtual Agents bots can be added to the Allowlist.
• Power Virtual Agents cannot act as a skill for other Power Virtual Agents bots. Only Bot Framework bots can be added to Power Virtual Agents Allowlist. Trying to add a bot App ID that belongs to a Power Virtual Agent bot will result in error.
• Only user-created Topics and Composer intent triggers added to the bot will be added to Power Virtual Agents bot skill manifest. System Topics and Composer dialogs added to Power Virtual Agents bot will not be included in skill manifest.

Learn more

For more information, visit the documentation on using a Power Virtual Agents bot as a skill.

Join our Power Virtual Agents community to share your ideas, provide your comments, and help drive the future direction of our product development.

The post Power Virtual Agents bots as skills with Bot Framework bots – Public Preview appeared first on Microsoft Copilot Blog.

Last year, we launched the public preview of export and import chatbots using solutions, used by most Power Virtual Agents customers today. With this feature, customers can easily manage their Power Virtual Agents chatbot’s lifecycle to address change control, governance, data residency, and latency requirements by exporting and importing bots across environments. In addition, we also enabled Microsoft Teams users to export and import chatbots in Dataverse for Teams.

Today, we are excited to announce the general availability of Power Virtual Agents export and import chatbots using solutions.

Besides many bug fixes and backend improvements, we augmented this feature with the following:

• New bot’s components (topics, flows, etc.) are auto-added to the bot’s current solution. Previously, customers needed to add new components manually using the “Add required components” feature, which caused import failures if they forgot that manual step.
• Skills environment variables are auto-added when a chatbot is added to a solution.
• Show the bot’s current solution name under the bot picker panel for easy access to solutions and troubleshooting. This is only available on the web app and doesn’t show the Default Solution name.

See current solution name under bot picker

You can continue going to the Power Virtual Agents web app settings page to open Power Apps solution explorer to export and import bots using the solution, like at the public preview.

Furthermore, you can use the Power Apps personal app in Teams, select the Build tab of the team where you want to export and import your chatbots. More information: Install the Power Apps personal app in Microsoft Teams.

Export chatbot using Power Apps personal app in Teams

To learn how to use export and import bots using solutions, see documentation here.

We’d love to hear about your experience with this feature! Please visit our community forum at https://aka.ms/PowerVirtualAgentsForum and share your feedback.

If you have any idea requests, please submit them at https://aka.ms/PowerVirtualAgentsIdeas.

Happy bot building!

The post Announcing the general availability of Power Virtual Agents export and import chatbots using solutions appeared first on Microsoft Copilot Blog.