We are thrilled to announce the public preview of Copilot chat extensibility for model-driven apps. This new capability empowers partners and customers to tailor and extend the in-app chat, making it more context-aware and more aligned with organization’s unique needs.

By harnessing the capabilities of Copilot Studio, you can incorporate additional topics, knowledge sources, connectors, custom prompt guide and more, greatly enriching your Copilot chat experience. A dedicated agent is provisioned when customizing the Copilot chat to ensure that each model-driven app has a tailored and context-specific AI assistant. This extensibility approach ensures that your AI solutions are not only more pertinent but also scalable in tackling your unique business challenges.

It’s easy to get started. Go to https://make.preview.powerapps.com in any early release environment. Open the model-driven app whose Copilot chat you want to customize. Click on the ellipsis (…) in the left navigation bar and then select Configure in Copilot Studio. You will be directed to Copilot Studio with the appropriate agent ready for customization.

The animation below demonstrates a use case where, with just a few clicks, makers can enhance Copilot chat capabilities to answer any question from the Power Apps official documentation. Additionally, they can easily customize the Copilot UI to assist end users through prompt guides.

For more information about the capabilities being made available with this release, please refer to the Power Apps documentation under Customize Copilot chat using Copilot Studio. Please use Power Apps Pro Dev forum or reach out via LinkedIn for any feedback or questions.

The expansive potential of extensibility is truly exciting. We look forward to this journey with our partners and customers, as we incrementally roll out additional features.

Note: This feature is currently available in early release environments and will be gradually rolled out to all makers over the coming weeks.

The post Unlock new possibilities by customizing Copilot chat in your apps with Copilot Studio (Preview) appeared first on Microsoft Power Platform Blog.

All of these announcements are entering preview by December 2024: 

• Plan designer is ready for preview. In September 2024, we opened early access for select users to a new AI-powered workspace for turning requirements into a robust Microsoft Power Platform solution—including user stories, data model, apps, and automations. In the next weeks, we’re expanding access to a full preview. Designing a solution plan with Microsoft Copilot will make it easier than ever to upgrade existing apps and processes into intelligent applications.   

• Makers can generate custom AI agents directly from Power Apps using the knowledge, logic, and actions built into existing apps to jumpstart the building of a Microsoft Copilot Studio agent. These custom agents will get work done on behalf of employees, which can reduce repetitive work, supercharge individual productivity, and drive overall business efficiency.¹ Makers will also be able to tune the out-of-the-box agents in Power Apps with custom knowledge and actions using Copilot Studio.

• Introducing managed security and managed operations in Power Platform. Just as we have simplified governance with managed environments, we are now making it easier than ever for organizations to apply advanced security to their Power Platform solutions and manage mission-critical workloads at scale. A completely redesigned admin experience now features focused capabilities for managing security, deploying solutions, monitoring telemetry, and more. 

Together, these advancements represent a major disruption to the traditional “build versus buy” tradeoff of business apps. By generating intelligent applications on a fully managed platform, technology leaders can get the best of both worlds—solutions that are purpose-built for exactly their needs but without the long-term costs of maintaining full stack projects. Forrester’s John Bratincevic argues that this is the beginning of a substantial shift.

“AI-powered enterprises will “build” software instead of “buy” it—and many applications in enterprise portfolios will consolidate onto low-code AppGen platforms.”

John Bratincevic, Principal Analyst, Forrester

Let’s dig into the details of how Power Platform is leading the AppGen transition with new capabilities rolling out now.

Build enterprise solutions, start with a plan 

In September 2024, we opened early access to a new Copilot-powered workspace in Power Apps that enables makers to design and generate a robust solution to nearly any business problem. With highly positive feedback from customers, we’re excited to bring the plan designer capabilities to preview.

Now developers will be able to start working on a business problem in an iterative process with Copilot, and keep better connection between the business requirements and the solution they are building.

The entire process of building a plan and generating solution components is iterative and collaborative. At any point makers can make changes to defined user roles, requirements, data model, or the proposed user experiences. The plan will live alongside the solution, changing with it and ensuring the understanding of the problem and requirements persist.  

The new plan designer experience will make a powerful tool for creating well-structured, adaptable, and collaborative solutions using Power Apps and Power Platform. 

Generate custom AI agents from existing app capabilities  

Makers can now easily generate agents from existing apps using the logic, knowledge, and actions built into those apps. Makers can leverage Copilot Studio capabilities directly in Power Apps to build custom agents that get work done on behalf of employees. Once these agents are deployed, users can review activity, manage complex cases, and focus on higher value work.

For instance, in a reimbursement management app, a maker takes existing process—categorization, compliance check, or rejecting requests—and builds an agent to execute these tasks. Makers can start from an existing app, and agent builder will suggest actions based on the app’s construction, like activating flows or running Power Fx functions. This significantly shortens the time to get to user value and makers can continue expanding agent functionality in Copilot Studio. For example, they can add the ability to process receipt images using the pre-built prompt with GPT-4o. 

For users, the benefits are clear: instead of requiring each request to be reviewed by a person, an agent handles it. Makers can also allow users to see which rows have been recently modified by the agent and view previous agent sessions. This transparency ensures that users can intervene when necessary, maintaining visibility and control. This functionality will be available to makers starting next month.

Improved in-app agents for data entry and summaries 

In addition to generating new custom agents, we’re also improving the out-of-the-box agents that end users leverage within Power Apps to get work done more efficiently.

Data entry is one of the tasks that many people consider tedious, and it’s no surprise that the Power Apps data entry agent, which helps users fill out forms, is highly valued by customers. At Power Platform Community Conference 2024, we announced the ability to copy text and let AI suggest form inputs from the clipboard. In a study with information workers, this Copilot assistance enabled 29% faster form filling, with 95% preferring it over manual entry.² Now, users in model-driven apps can also directly add an email or file and get field suggestions from them. The new context control lets users see what data is used to predict fields, giving them more control. In canvas apps, entering long text input with Copilot now allows for custom prompts and presents multiple options to choose from—just like people are used to from Microsoft Word.

Quickly find what you need and understand a summary of complex records. Searching, sorting, and filtering of records using natural language with the help of the Power Apps data exploration agent is now available to all users in preview. And to give users easy insights, makers can add custom AI summaries to apps with a summary card—the performance of which they can review in the monitoring page.   

Copilot chat in apps can also now be customized—starting from the app designer, makers can open Copilot Studio, provision an agent responsible for the app chat experience and add new topics, knowledge grounding, domain-specific glossaries, and actions. A customized chat agent is then ready to help users with more relevant and helpful answers. 

Introducing managed security and managed operations 

In 2022, we introduced managed environments, a suite of governance capabilities that brought more visibility and control to administrators of Power Platform. We see every day how these capabilities allow IT teams to efficiently govern hundreds of thousands of assets, making well-governed use of Power Platform available to millions of users around the world, including for customers like Deutsche Bahn, Lerøy, and Lumen. 

Today, we take another step forward. We know that large-scale app modernization and the transition of existing business processes onto intelligent solutions in Power Platform and Dynamics 365 will require even more than great governance. That’s why we’re introducing two additional, closely related capabilities: managed security and managed operations. This means that Power Apps, Power Automate, Microsoft Copilot Studio, and Dynamics 365 are now delivered on a fully managed platform. 

• Managed governance helps organize and administer professional and citizen development with more visibility, more control, and less effort on the part of central teams.  

• [New] Managed security makes it easier than ever before to apply advanced threat protections across the platform, helping security professionals assess and improve the security footprint of their business applications. Managed security includes industry-leading capabilities for proactive threat detection, access management, compliance, and more. Learn more in the Power Platform security and governance blog. 

• [New] Managed operations makes it easier for advanced development teams to deploy and operate mission critical applications to maximize an organization’s productivity. This suite of capabilities is designed to safeguard and tune your production workloads with the ability to safely deploy updates, detect service degradations, and provide recommendations to improve production health. Learn more about managed operations.  

All managed capabilities are benefits of existing licenses and surface directly in existing products. This includes the Power Platform admin center (PPAC), which has now been completely re-imagined around a set of new highly productive workspaces for specific tasks—including reviewing inventory in managed environments, configuring and monitoring managed security, and leveraging managed operations capabilities for deployment and oversight.

These workspaces will also now be visible in focused ways in maker experiences. For example, developers will be able to observe and improve on the active usage of their applications in the monitoring workspace. They will see apps with low app open success rates and drill down on reasons why users can’t open the app, or they can see high latencies for showing the initial screen or data and understand what’s contributing to the problem. This will help makers find and address apps that require attention for improved performance.  

Today, we’re also making an important clarification to the licensing requirements for managed environments. Managed platform capabilities are a benefit of existing premium licenses, and any environment with managed features requires the users of any of the assets in that environment to have a premium license. We’re clarifying that as long as each individual user in the environment is appropriately licensed with at least one premium license—Power Apps or Power Automate—managed features will work and customers will be compliant.

Learn all about the updates to governance, scale, security, and data management capabilities in the breakout session Enterprise Scale: The Future of Power Platform Governance + Security. 

Apps that help users with line-of-business tasks 

Power Platform boasts a massive 1,400+ connector ecosystem, many of those connecting to the line-of-business data, giving options to business leaders and teams to build functionality they are missing to run business smoothly.  

We’re happy to announce two advances for building line-of-business apps. First, the SAP OData connector is now generally available, allowing access to SAP’s modern product stack, improving productivity and innovation with Power Platform’s low-code capabilities. Professionals building solutions over SAP will also benefit from a new whitepaper dedicated to architecting of SAP extensions.

And second, new bi-directional integration between Microsoft Dataverse and Snowflake allows makers to build end-to-end apps that act directly on Snowflake data, including the ability to create Dataverse virtual tables from Snowflake data. Coming soon, Dataverse data will be accessible in Snowflake so that customer service teams using Snowflake can leverage powerful analytics over their data in Dataverse, gaining deeper insights into customer behavior and enhancing service quality.

Join us at Microsoft Ignite 2024

Power Apps solves thousands of problems for tens of thousands of customers in almost every industry. With agents working alongside users, greater productivity from AI in apps, and expanded enterprise-grade tools for management at scale, Power Apps is the place for organizations to drive tangible AI impact. 

Join us at Microsoft Ignite 2024 to see the newest announcements firsthand and understand how you can leverage them. Embrace the era of Copilot-first development and accelerate your company transformation into the age of AI with Power Apps. 

Microsoft Ignite 2024

Experience the latest innovations for AI transformation

Explore the event

¹ New autonomous agents scale your team like never before.

² Internal Microsoft testing conducted in November 2024 on sample of 22 subjects.

The post Intelligent apps: Now created with a plan, optimized with agents, and scaled on a fully managed platform appeared first on Microsoft Power Platform Blog.

Introducing smart paste

Smart paste is the latest capability of Copilot form fill assistance for model-driven apps, designed to make the time-consuming and frustrating task of form filling easier. Imagine this: you have some text in an email, document, or note that you need to enter into a form. Instead of manually typing it all in, you can now simply copy the text to your clipboard. Without selecting any specific field, just click the smart paste button or use the standard paste shortcut (CTRL+V or CMD+V). Copilot will reason over the form and the pasted text to suggested what text could be used to fill specific fields, and provides suggestions inline in the form. You can review and accept the suggestions that work for you—as always, nothing gets saved until you confirm. Ignoring suggestions will automatically discard it, and we are also introducing a new capability to clear all suggestions in the form.

And if you prefer the traditional way, you can still paste directly into a specific field by clicking on it first and then pasting.

You can use smart paste in your model-driven apps by updating the following two settings in Power Platform admin center, under Settings > Product > Features > AI form fill assistance section:

1. In the Enable this feature for field, make sure that All users immediately is selected.
2. Set Enable smart paste (Preview) to On.

Discover the suggestion source using new citations

We are introducing a new capability that adds even more transparency to Copilot’s suggestions. With the new citations, you can now learn more about the source of the suggestions provided by Copilot. These citations clearly identify the source, for example “Records you have updated recently” or “Clipboard”, giving you more clarity and confidence in the suggestions you receive.

Form fill assistance now available in quick create forms

Form fill assistance, including the new smart paste capability, is now available in quick create forms as well. This means you can enjoy the same time-saving benefits across even more of your forms.

Expansion to 21 languages

Form fill assistance in model-driven apps is rolling out in the following 21 languages in addition to English (US):

1. Arabic
2. Chinese (Simplified)
3. Czech
4. Danish
5. Dutch
6. Finnish
7. French
8. German
9. Greek
10. Hebrew
11. Italian
12. Japanese
13. Korean
14. Norwegian (Bokmål)
15. Polish
16. Portuguese (Brazil)
17. Russian
18. Spanish
19. Swedish
20. Thai
21. Turkish

We want to hear from you

Learn more about this feature in the documentation. We look forward to you trying out these capabilities in your model-driven apps and sharing your feedback through the form fill assistance survey in your model-driven app.

The post New smart paste makes filling forms as easy as copy & paste appeared first on Microsoft Power Platform Blog.

Enhancing your AI business strategy with Microsoft Copilot Studio and Microsoft Dataverse enables organizations to simplify the complex data integration, third-party data extensibility, and security guardrails organizations must have in place to assist in the implementation and adoption of AI.

At Microsoft Build 2024, we are excited to unveil Microsoft Copilot connectors. Microsoft Copilot connectors provide seamless and secure integration with your productivity, analytical, and operational data as well as empower users to activate existing business processes. Copilot Studio and Dataverse allow organizations to create actions, build knowledge, and integrate grounded data into their copilots with ease, all while easily meeting their compliance requirements with a rich set of security features.

Bridge the gap between enterprise data and Microsoft Copilot

The concept of enterprise knowledge in Copilot Studio is a groundbreaking addition that allows copilot makers to add specific contextually relevant knowledge sources to their copilots, thereby improving the reliability and accuracy of responses. Knowledge supports a wide range of data types, including public websites and Microsoft Dynamics 365 (powered by Dataverse) and brings simple discoverability and understanding of enterprise data, which is critical to scaling the delivery of agent copilots across an organization.

Figure 1: Makers can select enterprise data sources as their copilot’s knowledge.

Many Microsoft customers are seeing the benefits of adding grounded enterprise data into their copilot experience. From supply chain management, customer relationship management, and productivity insights, customers can increase the efficiency of business processes, make their workforce more productive, and provide rich customer experiences. Read below how Peppermint, EY, and Docusign have developed impactful solutions.

Peppermint reimagines legal business processes with Copilot

Law firms are challenged with optimizing workflow efficiency and delivering effective client services. Achieving this entails implementing a range of services, including case and matter management, document management, and client engagement. How can law firms, who are primarily focused on legal expertise, utilize technology to overcome this challenge and achieve their goals?

Peppermint Technology, a leading global independent software vendor (ISV) revolutionizing legal firms and departments, has built solutions that easily ground copilots with enterprise data stored in Dataverse and SharePoint to provide more relevant and secure business insights. Peppermint has been using Microsoft Power Platform to model their legal case process and storing their business data in Dataverse. With their existing integration, allowing Peppermint’s copilot to access enterprise knowledge and processes from Microsoft Power Platform, while maintaining user context security, requires minimal effort and allows rapid adoption of modern AI workloads for increasing productivity and automation

Figure 2: Use natural language to retrieve matters stored in Dataverse.

Lawyers can now use LARA (Legal Analysis and Research Assistant for Peppermint) to efficiently prepare for upcoming meetings by identifying internal contacts for new accounts, accessing pertinent information, and taking necessary actions ahead of their meetings.

Figure 3: Use natural language to identify connections with new accounts.

“At Peppermint Technology, we are excited to utilize Copilot Studio’s enterprise knowledge to not only extract maximum value from corporate data but also significantly enhance our law firm clients’ ability to engage with their clients and increase billing efficiencies. This strategic adoption aligns perfectly with our business priorities of reducing risk and boosting client engagement, enabling our clients to offer superior service and achieve better outcomes.”—Mike Walker, Chief Technology Officer (CTO), Peppermint Technology

Take your enterprise business processes further with Copilot connectors

With Copilot connectors in Copilot Studio, organizations can easily expand their copilot knowledge and actions with their business data. Copilot connectors allow organizations to bring together data from Dynamics 365, Microsoft Power Platform, SharePoint, OneDrive, Microsoft Fabric OneLake, public websites, and many other systems of record.

When incorporating Copilot connectors into your custom copilots, Copilot will work in the background on your user’s or organization’s behalf, and reason across structured and unstructured data to execute your business processes.

Figure 4: Microsoft Copilot connectors diagram.
Copilot connectors are part of the broader Copilot ecosystem, which includes Copilot Studio and Microsoft Copilot. They play a crucial role in the extensibility of Copilot, allowing developers to create custom AI solutions that are deeply integrated with Dataverse and Microsoft Power Platform. Some key benefits of Copilot connectors are:

• Semantic search: Allows the connector to understand and interpret the text data, enabling more relevant and context-aware responses.
• Data syncing and caching: Ensure your data is synchronized and cached efficiently, allowing for quick access, and reducing potential latency issues.
• Extensive third-party service integration: With a few clicks you can access the ecosystem of more than 1,400 connectors so that even non-Microsoft data can be included.
• Support for complex data types: The connectors can handle a variety of data types, including relational data and unstructured data, making them versatile for different business needs, and come with production-grade service levels.
• Low-code and pro-code: Whether you want to create custom application programming interface (API) or existing prebuilt connectors, the choice is up to you.

Docusign expedites the workforce with Copilot connectors

By enabling the Docusign Copilot connector within Microsoft Copilot, Docusign delivers greater value to their customers by not only surfacing document details, steps, and processes, but also allowing users to ask queries with natural language, and drive results faster than before. Docusign’s integrations with Microsoft Copilot for Microsoft 365 and Microsoft Copilot for Sales provide AI-powered agreement insights to help drive employee productivity, close deals faster, and manage renewals at scale. Customers across human resources (HR), sales, procurement, legal, and more can now use natural language to ask Copilot for agreement status and summarization, extract key information, send reminders to others, and more.

Figure 5: Activate Docusign Copilot connector and find agreements with natural language.

“Through our partnership with Microsoft, we are revolutionizing the way organizations do business. Docusign’s integrations with Copilot for Microsoft 365 and Copilot for Sales harness the power of AI to drive intelligent automation and innovation, leveraging Microsoft Power Platform plug-ins and Microsoft Copilot Studio. Meeting people where they work, these integrations empower organizations to accelerate revenue, reduce risk, and create better experiences from the agreements that run their business. Together, we’re not just streamlining processes, we’re redefining what’s possible in the digital era.”—Janine Grasso, General Vice President (GVP) of Partner Development and Alliances, Docusign

Gain visibility and increase your security posture

As organizations increase the complexity of their solutions and incorporate data from multiple systems of record through Copilot connectors, gaining and maintaining visibility of the security of that data is critical. Previously, fragmented experiences created barriers to customers assessing risks, and a lack of clear, defined guidance in achieving the defense in depth that organizations strive to maintain. Without security tools for both proactive and reactive governance of both citizen and pro developers’ applications, administrators may resort to solutions that stifle modernization, productivity, and business growth.

The Security Hub is designed to solve these challenges and more, with intuitive experiences, and strategic guidance, administrators can navigate the complexities of managing security at scale. This centralized hub provides administrators with tools to assess the security posture of their tenant, identify and act on impactful recommendations, and proactively set policies to safeguard against vulnerabilities and threats all through the Microsoft Power Platform admin center.

The Security Hub for Microsoft Power Platform, in public preview, offers several benefits, including:

• Enhanced security posture: Providing administrators with tools to assess and improve the security posture of their tenant, ensuring that data and applications are protected against vulnerabilities and threats.
• Actionable recommendations: Identify impactful recommendations that administrators can act on to strengthen security measures.
• Proactive policy setting: Proactively set policies to safeguard your environment, preventing potential security incidents before they occur.
• Centralized security management: One centralized platform for managing security across Microsoft Power Platform, streamlining the process, and making it more efficient.

These features are designed to provide a comprehensive security solution that aligns with an organization’s security practices, contributing to the overall success of digital transformation efforts. For example, Security Hub identifies if minimum safeguarding is in place and guides you to set up the appropriate data loss prevention policies (DLP) around Copilot connector usage in your organization. In addition, administrators can expect to utilize the following generally available in the Security Hub: vNet for Dataverse plugins, privileged identity management (PIM), tenant isolation, IP firewall, IP cookie binding, and environment security groups, while the following features will be available in public preview: client application control and Dataverse audit enhancements.

Additionally, Copilot Studio makers can now ground generative answers to SharePoint site content—enabling copilots to surface labeled resources as labeled responses in Teams chat with Microsoft Purview Information Protection sensitivity labels.

Microsoft Purview Information Protection sensitivity labels are widely adopted by enterprises today to label and protect sensitive information in Microsoft 365 apps and Fabric, and they are coming soon to Microsoft Power Platform.

Watch our latest overview of Microsoft Power Platform and Dataverse security features.

EY prevents data exfiltration at scale with Microsoft Power Platform security controls

Data exfiltration prevention protects the unauthorized transfer of sensitive data from an organization to external parties. This allows a business to maintain business continuity, comply with regulatory requirements, and keep up with competitive advantage. This feature allows the security officer to allow or block what apps that their authorized users can run in a Dataverse environment.

“As an enterprise consumer of the Microsoft Dynamics 365 platform, I am thrilled to share my experience with the recent enhancements made by the Engineering team. Their diligent efforts have had a significant, positive impact on our Dynamics 365 launch with the necessary data controls to support our information security policies and data governance processes.
The introduction of data exfiltration permission controls was critical to comply with our Information Privacy and Data Governance policies. These controls allow us to grant permissioned access to the Dataverse while maintaining strict data security. Here’s why these features are crucial:

• Foundation for Data Governance: The ability to control data exfiltration is at the core of our data governance strategy. With these controls, we can confidently manage how Dynamics 365 data is accessed and shared beyond our system boundaries.
• Enterprise Data Controls: Microsoft Dynamics 365’s permissioned access ensures that sensitive information remains within authorized boundaries. We can now define granular permissions, restricting data flow to only those who need it. This level of control empowers us to safeguard our data assets effectively.
• Privacy Compliance: Our member firms operate under stringent privacy agreements. The Engineering team’s work aligns perfectly with our commitment to data privacy. By enforcing permissioned access, we uphold our privacy standards and protect our enterprise information.

The Engineering team’s dedication to building robust permission controls has enabled our data landscape. We can confidently deploy Dynamics 365 and navigate the complexities of data sharing, knowing that our privacy agreements remain intact and grant access to only approved systems and usage.”—Erick J. Kirchner, Associate Director, Markets and Business Development, Ernst & Young LLP

Looking ahead

As we continue to innovate and push the boundaries of what is possible with data and AI, Dataverse remains committed to providing businesses with the tools they need to succeed in an ever-evolving digital world. These new features are just the beginning of what is to come, and we cannot wait to see how organizations will leverage them to achieve new heights of productivity and security.

Join us at Microsoft Build to learn more about these exciting developments and how they can transform your business.

The post Unlock new levels of productivity with Microsoft Dataverse and Microsoft Copilot Studio appeared first on Microsoft Power Platform Blog.

Form fill assistance in your favorite Dynamics 365 model-driven apps

Copilot assistance for form filling uses AI to generate suggestions for fields in main forms, based on your app usage and data patterns and what’s already in the form. You can simply accept the suggestions that suit your needs. And don’t worry, nothing gets saved until you confirm it.

This feature is now available in your favorite Power Apps and Dynamics 365 model-driven apps. See it in action below in Dynamics 365 Customer Service and Dynamics 365 Sales:

Manage form fill assistance in admin center

Admins can manage whether form fill assistance is available or not in their model-driven apps through Power Platform admin center using the AI form fill assistance setting rolling out worldwide this week.

The post Copilot assistance for filling forms is now in all model-driven apps appeared first on Microsoft Power Platform Blog.

• There were several live sessions (now available on-demand) for participants to learn about the Copilot and AI features of Power Platform.
• Participants followed a Learn Collection for help in getting started.
• Over 100 project submissions were received with 4 winners chosen across the different categories.

Summary of the participants and project submissions from around the world.

The categories for the hackathon were:

Grand prize winner – The best of the best! Rewards the solution that meets all judging criteria, wows judges, and has potential real-world value for Power Platform Users.

Best AI-powered solution – Rewards the solution that integrates AI in an innovative way.

Best Better Together Use Case – Rewards the solution that uses the Power Platform and other Microsoft products in an interesting way.

Best Diversity, Equity, and Inclusion (DEI) Use Case – Rewards the solution that helps make the Power Platform community more diverse, equitable and inclusive.

The submissions were innovative and demonstrated how AI can be helpful across numerous use cases. Be inspired this year in building AI-powered solutions with Power Platform by checking out these community submissions below:

• Education – Teaching Accelerator
• Family Support – Make Life Easy | Parents Advisor
• Healthcare – Romão’s Homecare | Medical Assistant
• Human Resources – The Relocation Game | Seeker
• Not-for-profit – Migrant Worker Case Management
• Information Technology – Prompt Wagon | CodeScribe

Education

Teaching Accelerator

Teachers spend thousands of hours each year planning the curriculum for their students. Elliot Fraser developed a Power Platform solution, known as the Teaching Accelerator, to expedite the process for teachers in creating a curriculum for their students. The solution utilizes OpenAI’s ChatGPT service where teachers can interact with it through a Copilot embedded in the model-driven app to create lessons, modify the lessons created, and create an entire curriculum of lessons for a topic.

Teachers can interact with a Copilot within the model-driven app for creating lessons and a curriculum for students.

The solution consists of the following main features:

• Model-driven app which is the primary end user interface for the teachers to plan their lessons and a curriculum for students.
• Custom pages built using Power Apps canvas apps are embedded in the model-driven app to help guide teachers to create a curriculum of lessons, create lesson plans and view, modify and assign existing lessons.
• Teachers enter their questions into a Copilot that was built using Microsoft Copilot Studio to receive AI-generated suggestions for a curriculum and lesson plans. The Copilot appears in a pane within the model-driven app through a custom page.
• Power Automate cloud flows in the background interact with OpenAI’s ChatGPT service to relay the suggestions to the teacher.
• When the teacher is satisfied with the suggestions from Copilot, they can ask Copilot to generate the curriculum and lesson plans in the model-driven app. Depending on where the teacher executes this in the app, Copilot calls a function in OpenAI to create an array of the curriculum or lesson plans as a JSON object. This output is then saved in Dataverse using a cloud flow by transforming it into rows of data which the teacher sees as the curriculum or lesson plans in the model-driven app.

What we loved

Elliot’s Teaching Accelerator solution won the Grand Prize winner category of the hackathon due to the impact it would have in the education space by reducing the hours teachers spend annually. Teachers can quickly create a curriculum and lesson plans for students in minutes with the help of generative AI and Power Platform.

Since the hack, Elliot has an updated version of the Teaching Accelerator where he’s made enhancements based on feedback from teachers who have been testing the solution. For an overview of the updated solution version, watch Elliot’s presentation from a previous The Low Code Revolution episode.

Family support

Make Life Easy

To provide everyday support for parents of autistic children, Raghav Mishra developed a Power Apps canvas app to create structured daily routines. As a parent to an autistic child, Raghav recognized their son thrived when steps of their daily routines were illustrated visually by his wife with the corresponding written text. Inspired by his wife’s dedication in helping their son, Raghav turned to the Power Platform combined with OpenAI’s services to develop a Power Apps canvas app that uses generative AI to help create the text-based steps of the tasks and design the corresponding images of the steps. The Make Life Easy app can be used by parents to establish routines the children can follow.

Parents interact with generative AI in a canvas app to create written and visual steps for tasks children follow.

The solution consists of the following main features:

• Parents use the canvas app to interact with OpenAI’s ChatGPT service to generate a list of text-based steps for tasks, such as the steps children follow to put their shoes on.
• The text-based steps for each task are saved in Dataverse, which are displayed in the gallery of the app.
• Parents can select a step from the gallery and interact with OpenAI’s DALL-E service to create the corresponding visual images for all steps, such as asking for an image of a child sitting on a chair as a step the child follows to tie their shoelaces.
• Once all images of the steps for the tasks are created, they can be added to the schedule board for children to follow. Parents can then assign the tasks to their children.
• Children see their assigned tasks in their personal daily schedule board within the app. They can follow each of the steps through the visual and written instructions generated by AI.

What we loved

Raghav’s Make Life Easy solution won the Best Diversity, Equity and Inclusion (DEI) Use Case category for designing a solution that supports parents of autistic children and their daily routines. Parents can interact with generative AI in a Power Apps canvas app to define the steps of a task and create the corresponding visuals. Children can follow these AI-generated steps through written and visual comprehension in the app.

Parents Advisor

To help parents encourage and teach children every day, Richard Li created a Power Apps canvas app known as Parents Advisor, where parents can seek additional support for advice on educating their children. Several Azure OpenAI services and OpenAI services were used together with Power Platform to provide tailored recommendations based on the individual in-app user profiles. Children can also have one-on-one interaction with AI, where the AI-generated answers are verbally read to them from the app itself. The Parents Advisor app can be used daily by both parents and children for written and aural comprehension.

Parents and children interact with generative AI to create tailored learning experiences in the canvas app.

The solution consists of the following main features:

• Parents can select from built-in prompts in the canvas app such as how to encourage their child to sleep independently. They can also enter their own custom prompts directly in the app, where Azure OpenAI’s ChatGPT service will respond with an answer which the parent can save for future reference.
• Parents also have the option to provide their prompt verbally through the built-in microphone control of canvas apps. Their verbal prompt is then transcribed to text using OpenAI’s Whisper speech-to-text service and can also be translated to more than 50 languages.
• All responses from Azure OpenAI’s ChatGPT service can be transcribed from text-to-speech using the Speech service from Azure AI. The style of the voice can be altered using Speech Synthesis Markup Language (SSML) such as the effect, style and multilingual voices. This means the AI advisor can “talk” to children by reading the responses to prompts through the built-in audio control of canvas apps.
• Most of the parent end-user features are also replicated for the children end-users where they too can interact with the Parent Advisor app and access the list of built-in topic prompts. Or they can enter their own custom prompts and have the app read the responses generated.
• One of the fun features of the app is using Azure OpenAI’s ChatGPT service to author bedtime stories for children based on pre-selected criteria of the character (e.g. Cinderella), language, genre, length and the requested story details. The parent or child also has an option to create their own bedtime story by adding their own prompts. Based on the prompts selected, the app will generate a bedtime story which can be read by the parent or child, or the app can read it to them through the native audio control of canvas apps.

What we loved

It was very cool to see the solution utilize the Speech service from Azure AI to transcribe the responses from text-to-speech in relation to the prompt entered by the parent or child. We also liked it was diverse and inclusive in providing multi-language support to cater for different languages of families.

Healthcare

DISCLAIMER: Applications built using Microsoft Power Platform are not designed or intended to be a substitute for professional medical advice, diagnosis, treatment, or judgment and should not be used to replace or as a substitute for professional medical advice, diagnosis, treatment, or judgment.

Romão’s Homecare

To assist doctors and nurses with scheduled visits to patient’s homes, the Romão brothers – Douglas and Renato, built several apps by combining low code and pro-code techniques. A Power Apps canvas app, known as the Romão’s Homecare mobile app, is used by the doctors and nurses for visibility of daily scheduled in-home patient visits and to record details of their assessment from their devices. The information entered in the Romão Homecare app is saved in Dataverse and is accessible through a Power Apps model-driven app.

Doctors and nurses capture their assessment of patients during in-home visits with assistance from generative AI in a canvas app.

The solution consists of the following main features:

• The canvas app is the primary end user interface for doctors and nurses where they can see a list of their upcoming scheduled in-home visits. The built-in interactive map control displays the location of their patient visits.
• The native camera control of canvas apps enables them to capture photos during their assessment with the patient. These photos are uploaded into Azure Blob Storage and a sentiment score based on the images uploaded is generated using a Python web app via Azure App service.
• Audio recordings can also be captured using the native microphone control in canvas apps where the audio is transcribed to text using OpenAI Whisper’s speech-to-text service.
• A simple Yes/No checklist is used which is submitted to OpenAI to provide a score of the visit.
• On completion of the visit, the overall score calculated by OpenAI indicates the wellbeing of the patient with a high score being good and a low score requiring further attention.
• A model-driven app displays the stored patient data in Dataverse where information can be modified if needed.

What we loved

Doctors and nurses taking notes during or after a patient visit takes time and the solution reduces this administrative effort by capturing audio recordings and transcribing them to text using OpenAI Whisper’s speech-to-text service. There’s no duplicate time spent re-entering their notes by typing into the app. The data being accessible through Dataverse is also convenient for the information to be modified if additional details need to be edited.

Medical Assistant

To help the medical industry interpret computerized tomography (CT) scans and magnetic resonance imaging (MRI) scans, Yevhenii Dementiev, Valentin Gasenko and Surkho Salamov built an app, known as the Detect Cancer app, to support physicians with reviewal of patient scans. The aim of the solution is to help physicians to distinguish between possible tumors and other anomalies, improving the precision of diagnosis and identifying tumors at various stages.

AI technologies used in their solution identifies potential tumors and anomalies to help physicians with diagnosis.

The solution consists of the following main features:

• Physicians use a canvas app where images from the CT and MRI scans can be uploaded using the built-in attachments control of canvas apps.
• Using AI Builder Object Detection Model, the uploaded images are analyzed and highlight the detected possible cancer regions on the CT scan and MRI scan.
• A Power Automate cloud flow sends the detected information from the AI model to OpenAI’s Completions service to generate medical conclusions for the physicians to predict the recovery of the patient.
• The physician can also dive further into the regions detected for analysis and comparison from previous CT and MRI scans of the patient. Based on the historic data, OpenAI can provide a prediction of the patient’s recovery from cancer.
• Dataverse is used to store all information about the patient scans and conclusions of the detected cancer regions.

What we loved

This is an incredible solution that supports a healthcare use case by assisting detection of cancer regions and medical conclusions using AI Builder Object Detection Model combined with OpenAI services. It was also nice to see the team include feedback in their video submission from their target audience of physicians. Their solution has demonstrated how Power Platform and AI together can be of secondary help to healthcare professionals.

Human Resources

The Relocation Game

Employee relocation can be overwhelming for employees in two ways: understanding what their organization’s local policies are and adjusting to a new city – especially if the employee is unfamiliar with the local surroundings. Denisa Mihai built a Power Apps canvas app known as The Relocation Game, to help employees with their move by interacting with a Copilot to learn about the local policies and help identify the city’s landmarks through AI Builder.

Employees interact with a Copilot embedded in a canvas app to learn more about their work benefits, the required documentation for relocation and can be connected to the HR team.

The solution consists of the following main features:

• A Copilot is embedded in a Power Apps canvas app which uses the built-in boost conversation capabilities where natural language processing is applied to find, collate and parse relevant information from the sites and summarize the search results into plain language for the employee.
• Employees interact with the Copilot within the Relocation app where they can ask about the company benefits, documentation required for their move to a new country, and request to be connected to the HR team for additional questions.
• An AI Builder object detection custom model was developed and trained to recognize city landmarks for employees to become familiar with their city’s surroundings. The trained object detection custom model is embedded into the Relocation app.
• Using the built-in camera and image controls of canvas apps, the employee takes photos and uploads these into the object detection custom model for it to recognize and present the name of the landmark to the employee.
• Employees can also create their own collection of landmarks by taking photos and adding them to their list of landmarks in the Relocation app.

What we loved

Employees can feel supported for their relocation to another city by interacting with a Copilot with boost conversation capabilities enabled to help with HR related enquiries. We liked that there was an element of “discovery” built into the app for employees to take photos and verify a landmark of the city using the AI Builder object detection custom model.

Seeker

Recruiting new talent is often time-consuming during the phases of advertising, finding candidates and interviewing candidates. Isabelle Gaboc, Daniel Kerridge, and Jady Mulqueeney developed an end-to-end solution to reduce the administrative hours spent. A Power Pages site was built to handle the job listings and the initial interview process with candidates. Candidates can choose to have an automated interview within the Power Pages site where interviews are tailored to the candidate. Azure OpenAI’s ChatGPT capabilities in AI Builder generates open ended questions in alignment to the job description and information provided in candidate’s resumes, and OpenAI’s ChatGPT service is utilized during the interview for an ongoing conversational dialog with the candidate.

Open ended interview questions generated with the AI Builder connector in Power Automate are used in the AI-led interviews with candidates.

The solution consists of the following main features:

• An AI-generated Power Pages site was created using Copilot that enables candidates to review all available positions. They can apply by uploading their resumes and begin the automated interview process shortly after.
• Several cloud flows were built to extract text from the uploaded resume where the data is parsed and analyzed using the AI Builder text recognition prebuilt model to convert the resume to text.
• The automation continues by converting the job description to text using Azure OpenAI GPT capabilities in AI Builder to format the resume text from the previous step by removing unnecessary information and only keep the information aligned to the job description. As the last automation step, AI Builder’s OpenAI GPT capabilities are used again to generate open ended interview questions based on the refined resume text and job description.
• The candidate interviews are conducted within a webpage in the Power Pages site through a virtual call with a .NET bot integrated with Azure Communication Services. The interview questions generated by AI Builder from the cloud flow are retrieved by the .NET bot from the webpage using liquid, a markup language in Power Pages.
• Using Azure AI services text-to-speech, the .NET bot asks the candidate the interview questions generated by AI Builder.
• In return, the candidate can respond verbally to the .NET bot where the audio dialog is translated from speech-to-text using Azure AI services.
• The .NET bot will then send the translated text to OpenAI’s ChatGPT service with a prompt to respond accordingly for the interview. The output used for the response is translated once again to speech and relayed aurally back to the candidate. This enables a constant conversational AI dialog loop between the bot and the candidate.

What we loved

Their Seeker site solution won the Best AI-powered solution category of the hackathon due to the impact it would have for Human Resources in allowing candidates to use a Power Pages site to upload their resume for a job application and use OpenAI’s ChatGPT services to create a list of interview questions, followed by conducting the interview through a virtual voice call – all without any human intervention.

For a more detailed overview of the solution watch the Seeker team’s presentation from a previous Microsoft 365 & Power Platform weekly call.

Not-for-profit

Migrant Worker Case Management

Filipino citizens who work abroad sometimes face difficulties in understanding their rights in the country they work in. A case management solution was developed by Carmina Symaco, Marcos Antonio Abrematia and Jayson Espadero to support migrant workers in solving their issues by interacting with a Copilot embedded in a Power Pages site. All questions are created as a case in Dataverse where additional support personnel can review and respond to the person working abroad.

Migrant workers can paste an excerpt from their employment contract into the page in the Power Pages site to generate details that are more easily understood.

The solution consists of the following main features:

• A Copilot built using Microsoft Copilot Studio utilizes the built-in boost conversation capabilities where local websites of a country are associated to the Copilot to generate responses to questions asked by migrant workers.
• The Copilot is embedded in a Power Pages site where the user provides details of their role, the country they are working in and selects from a list of topics that resemble their issue to gain further assistance. Based on the information provided, Copilot returns the desired information extracted and collated from local websites of the country the Filipino citizen works in.
• Excerpts from their employee contract can also be parsed and analyzed using Power Automate cloud flows combined with OpenAI’s ChatGPT service to interpret the details and generate an answer that can be easily understood by them.
• All answers are captured as a case where support personnel can review them in a canvas app. An embedded Copilot in the app assists the support personnel to generate responses for the cases.
• AI Builder text recognition prebuilt model was used to classify the cases based on the description the migrant worker provided to the Copilot in Power Pages. In the app, there is a view for cases where the tag identified by AI Builder and the selected issue type by the migrant worker do not match. The administrator reviews the conversation history between the migrant worker and Copilot to correct the classification of the case.

What we loved

The solution was supportive of migrant workers by using a Copilot with boost conversation capabilities to answer queries and use OpenAI’s ChatGPT service to help them understand their employment contracts. Since it’s embedded in a Power Pages site, they’re able to access the Copilot 24/7 which is of benefit to workers across different time zones. The team also included some neat features for the support personnel and one that stood out was using AI Builder text recognition prebuilt model to verify the classification of the case was correct which will help with the long-term quality of the data.

Information Technology

Prompt Wagon

Artem Chernevskiy, Katerina Chernevskaya, and Nikita Chernevskiy recognized that prompt engineering is a growing new skill for organizations of all industries to utilize. Prompt engineering is natural language inputs or queries users provide to Large Language Models (LLMs) to produce the desired outputs or responses. To help organizations become skilled in prompt engineering, a Power Apps canvas app known as Prompt Wagon, was developed where users can select from a list of more than 100 pre-defined prompts and practice their knowledge of prompts by interacting with Azure OpenAI’s ChatGPT service within the app. The aim of the app is to help end users of all levels – beginners or advanced to learn how to construct their prompts and grow their prompt engineering skills.

Users can practice prompt engineering with the canvas app and gain more confidence in using generative AI.

The solution consists of the following main features:

• Users can select from 100+ pre-defined prompts across three categories of Business, Data and Education in the canvas app to help them exercise prompt engineering with the Azure OpenAI ChatGPT service. It also includes multi-language support in English, German and French.
• A custom connector was built to query the Azure OpenAI ChatGPT service from the canvas app. This enables users to interact with the services from within the app.
• Dataverse is used to store the text, images, prompts and translations of the German and French languages. All of these are surfaced onto the canvas app from Dataverse.
• Built-in app settings are available to modify the prompts and query parameters directly within the app. The updated settings are adhered to when end users next enter their prompts into the app.

What we loved

The app will help organizations be better equipped with prompt engineering through interacting with generative AI in the app. It was great to see the team build a custom connector to make the actions reusable across their solution that query the Azure OpenAI ChatGPT service from the canvas app. The use of Dataverse for the high volume of text, images, prompts and translations of several languages will support the solution to scale as the library of prompts grow over time with use.

CodeScribe

Developers often review code authored by others, with a common scenario being legacy code, where there can be little documentation or comments in the source code. To help automate code reviews, Robert Perillo built a Power Apps canvas app known as CodeScribe for developers to copy and paste code snippets into the app. A summary of the code is provided using Azure OpenAI’s Completions service to assist developers with understanding the code.

Developers can perform code reviews instantly by entering code snippets into a Power Apps canvas app and Azure OpenAI will summarize the code.

The solution consists of the following main features:

• Developers can paste code snippets into the canvas app and when they submit the code for review within the app, a Power Automate cloud flow executes to call the Azure OpenAI Completions service which analyzes the code snippet.
• Azure OpenAI then formats the code into two outputs, the first being a code summary that provides an overview of what the code does, and the second is a commented code block that explains each step of the code in detail for documentation purposes.
• The Power Automate cloud flow sends the formatted code to the canvas app for developers to review the summarized code and view a running commentary on the lines of code.

What we loved

Robert’s CodeScribe app won the Best Better Together Use Case category to help developers with the task of reviewing and documenting code by combining Power Platform and Azure OpenAI Completions service. We liked that the summaries are produced within minutes, reducing the time spent on code reviews. The solution breaks down what the code does by first summarizing it in a short paragraph, followed by a detailed explanation for each of the steps in the code.

Share your story with us!

Do you have a story or experience to share? We are excited to learn more about how individuals and organizations are using Power Platform with generative AI and Copilot capabilities! Submit your story at https://aka.ms/ShareAIStory

Learn more about Microsoft Power Platform and Copilot

• Understanding prompt engineering
• Create an app using AI Copilot
• Get started with Copilot in cloud flows
• AI-powered and Copilot features in Power Pages
• Build an AI-based Copilot with Microsoft Copilot Studio
• Quickstarts with Azure OpenAI Services

The post How Power Platform Global AI #HackTogether inspired AI-powered solutions for real-world use cases appeared first on Microsoft Power Platform Blog.

Today, we are announcing the availability of Copilot for users of model-driven apps and a major expansion of Copilot control’s capabilities in canvas apps. Now, all Power Apps can be intelligent apps. Makers can easily build apps to boost productivity for users, powered by next-generation AI in an intuitive experience.

Introducing Copilot in model-driven apps

Today, we are rolling out Copilot for users of model-driven apps. Copilot helps users get insights about their data and helps them navigate the app simply through conversation in natural language.

Copilot in model-driven apps is releasing as part of the Monthly Channel. This enables Copilot to evolve more rapidly based on your feedback, bringing value in smaller and quicker increments instead of making you wait for twice-yearly updates.

To learn more about Copilot in model-driven apps, please read: Add Copilot to model-driven apps

Major boost to Copilot control in canvas apps

Since the release of Copilot control in March, we have received a resounding and clear request: support larger datasets! We heard you, and today we are rolling out an important update: now when you connect the Copilot control to Dataverse, you can ask questions about really large tables – no size limits.

Pro tip: PowerFx can help you do more with Copilot control. In the example below, Copilot control’s ‘SelectedItems’ property is used to display details about Copilot’s answer in a gallery.

To learn more about Copilot in canvas apps, please read: Add Copilot control to canvas apps

Your feedback makes Copilot better

Are you curious about how to steer the future of Copilot? Do you have innovative ideas on how to enhance its capabilities? We want to hear from you! Your input plays a pivotal role in shaping the evolution of Copilot. In addition to the current ability for makers to provide feedback about Copilot control in canvas apps, today we are rolling out two new ways to share your voice:

1. Share your ideas and thoughts through this Power Apps community forum post
2. Share your feedback directly as you use Copilot in both model-driven and canvas apps

Availability

Today’s announcements are available in the United States and English language. While Copilot for app users in model-driven and canvas apps remains in preview, we are aware about the importance and urgency of equipping organizations to leverage these latest powerful capabilities in production. If you would like to use these capabilities in production today, please reach out to us with details about your use via Microsoft Support to request production support.

The post Copilot brings the power of intelligence to your favorite Power Apps appeared first on Microsoft Power Platform Blog.

In March, we announced a next-generation AI Copilot in Power Apps that will transform low-code development, building on the ability to generate Microsoft Power Fx from natural language and create apps from uploaded images. For the first time, Copilot in Power Apps gave developers the ability to create complex data tables and single-screen applications all from natural language.

Today, we take the next step in the journey of AI-assisted development:

• Copilot can create multi-screen applications and make real-time adjustments with the power of natural language.
• Copilot is adding data processing capabilities by helping you clean and prepare your data before you even start building the app. Copilot can now ingest any Excel file, no matter how loosely structured, and create robust structured tables with a variety of data types.
• Copilot control now brings the power of intelligence to your favorite model apps with its intuitive data understanding and convenient navigation. Copilot control in canvas apps also gets a major boost in understanding your Dataverse data.
• Copilot is making life easier for developers and admins alike with the ability to generate descriptions for complex applications and multi-component solutions with apps, data tables, and automations.

While Copilot is changing everything about the way we work, it’s not the only update we’re announcing to improve the lives of developers everywhere. One of the most important tools for any developer is the ability to reuse the components they create. Experienced developers accelerate their productivity by creating robust libraries of modules they can quickly deploy in new applications. Now, Microsoft Power Platform is enabling organizations to tap into those robust libraries with organization-wide component catalogs. These catalogs allow anyone to submit and install approved components that other developers at their company have created. This catalog is key to enabling any organization to scale its low-code practice company-wide.

Copilot can now create complex multi-screen applications

While the initial iteration of Copilot in Power Apps helped you get started with an app over Microsoft Dataverse, now you can go much further working side-by-side with AI. Makers have already seen the power of Copilot in creating and editing the data tables that underpin their applications. Now, Copilot will be able to create complex multi-screen applications through natural language conversation and design and update beautiful user interfaces. All of this means less time spent on mundane tasks like aligning buttons and more time spent on solving complex coding challenges.

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

• “Add a screen where users can submit and rank their favorite ideas from my existing screen templates.”
• “Add a button to my page that allows them to sort their data.”
• “Change the color of all my app’s buttons to blue.”
• “Center all buttons in their containers and turn them orange.”

Anyone with a Dataverse environment in the United States can get started using Copilot in Power Apps today.

Copilot control now enables developers to add the power of Copilot to their own applications

Copilot isn’t just for makers. With copilot control, we gave developers the ability to add the power of Copilot into their custom apps. Now, copilot control will be available to all Power Apps makers, whether they are building model-driven applications or custom apps. Copilot in model-driven applications understands and can reason over the Dataverse tables in your app—large or small and can even navigate through the data in your app. All of this is wrapped up in a new copilot control user experience with a brand-new look that follows you where you need it most. This copilot can maintain multi-turn conversations to navigate and derive insights about your application’s data.

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

• “How many high-priority tickets were created last month?”
  • “What is the breakdown of the current status for the tickets that were created last month?”
  • “Which types of tickets are most overdue?”
• “What are the most common budget items where actual spend exceeds estimated spend?”
• “During which months do our sales geographies generate the highest revenue?”
  • “How does that change for just our West Coast geographies?”
• “Take me to my support agents page.”

Learn more about how copilot control is putting the power of generative AI in every application to drive insights for users.

Copilot can now understand unstructured file inputs and turn them into structured data tables

To help speed up and simplify the creation of tables and apps from Excel, makers can now drop their Excel files into Power Apps, see a quick preview of the table that will be created and a preview of the data that will be imported. Makers can tweak the names, descriptions, data types, and other table properties before creating a brand-new app that is automatically connected to the new table and data.

Makers with Copilot enabled will get a helping hand in the creation of a great table for their data. Copilot will review the incoming data to come up with appropriate column names, ensure the right data types are selected, and even convert simple columns into choices if it sees a collection of repeating values. Copilot will also provide names and a description for the table based on the data. This can all still be achieved with Excel files that don’t group cells into a table and can even deal with tables that have no column headers present.

Learn more about how Copilot in Power Apps is automating the process of data preparation and ingestion.

Copilot can generate descriptions of your applications and solutions in seconds

Admins today rely on app descriptions to manage the hundreds of apps within their organization. Without descriptions, they have no way to know what the apps do without opening each one individually. This makes it hard to scale. Coming soon, Copilot will be able to help you generate a description of an app by ingesting the app’s metadata and returning an overview of what the app does in natural language. This alleviates the need for developers to manually write summaries and for admins to open individual apps every time they need to understand what each app does.

Solutions are complex, often containing dozens of components that are difficult to partition and summarize. In the case of pipeline deployments, admins and approvers currently must open every component in every solution to gain an understanding of what they do. By using AI to help generate useful solution descriptions, developers save valuable time and get high-quality descriptions of all their apps and solutions.

More information about Copilot’s ability to generate descriptions of applications and solutions coming soon!

Sharing reusable development components to achieve organizational level-impact

Modern software development works by building on components, packages, and libraries that other developers created as foundational blocks. A developer’s productivity is a function of how robust and efficient their tools are. With better tools comes faster iteration. With reusable tools comes scalability. As developers and administrators look to expand the reach and impact of their low-code applications, the need for a central repository of low-code components that anyone in an organization can leverage is clear. That’s why we’re announcing a brand-new catalog in Microsoft Power Platform that gives makers a place to publish, share, and reuse the best low-code components within their organization. We are also empowering administrators to ensure only components that meet the highest standards of quality and security are published through the catalog manager.

Submitting a component to the library is simple and requires just a few lines of code in the command line interface:

Once the component is submitted, the environment administrator is prompted to review and either approve or reject the component.

Installation of components from the catalog is easy in just a few lines using the command line interface.

Once you install the component, it will appear as a control in the maker studio. You can easily drag and drop it into your application to start building on the work of your organization’s best code-first developers.

Learn more about the new catalog in Microsoft Power Platform.

These advancements—significant improvements to Copilot and the release of the catalog—will accelerate the productivity of every professional developer who is building on Power Apps. Join the era of AI-assisted development and see how generative AI can amplify your impact.

Get started with next-generation AI capabilities

1. Learn more about the latest next-generation AI updates to Copilot.
2. Submit your first components to the catalog in Microsoft Power Platform.
3. Need a free developer plan? Get started at Power Apps Developer Plan.

Learn about Microsoft AI and other announcements across Microsoft Power Platform:

• The future of app development with Microsoft Power Platform.
• New ways to develop and orchestrate automation with Microsoft Power Automate.
• Revolutionize business websites with next-gen AI in Microsoft Power Pages.
• Reinvent your AI assistants with generative answers, actions, and more in Microsoft Power Virtual Agents.

Availability 

These features are currently available in the United States and English language by signing up. Note that these preview features are experimental, and accuracy and relevance cannot be guaranteed.

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 Power Apps is empowering coders with next-generation AI capabilities appeared first on Microsoft Power Platform Blog.

Today, we’re announcing a next-generation AI copilot in Microsoft Power Apps that will transform how we build and interact with software applications. With the power of large language models, we are advancing to the next step in the evolution of code abstraction—moving from custom code, to low-code, to natural language authoring where human and machine work side by side to build applications together.

We’re bringing the power of Copilot in Power Apps to both application makers and their end users. Now you can build an app, including the data behind it, just by describing what you need through multiple steps of conversation. What’s more, the apps you create now can have copilot-powered experiences built in from the very first screen—so your users can discover insights in conversation instead of clicks.

Watch it in action and learn more below:

The next step in AI-first development

Power Apps has been a pioneer in AI-centric app development since 2021 when we introduced the first GPT-based features for generating Power Fx from natural language. The product has evolved to generate apps based on uploaded images, format data based on examples, and suggest modifications proactively. Now, we’re bringing the next generation of AI technology to the very first step of application development. Developers will be able to build their business applications through an intuitive natural language conversation with Copilot in Power Apps.

With Copilot in Power Apps, makers can easily start creating an app with a few words in natural language. Imagine it, describe it, and watch Power Apps instantly generate your application, complete with a data table and back-end logic.

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

• “Create a time and expense application to enable my employees to submit their time and expense reports.”
• “Build an application to automate the manual process of creating and approving customer invoices.”
• “Generate an employee onboarding application to capture new hire information and share training content and learning modules.”

From there, a quick conversation with Copilot will make the adjustments your app needs. Need to add columns to your data tables? No problem, Copilot in Power Apps will suggest options and even help you populate them with sample data! Stuck and don’t know where to go next? Copilot will provide proactive recommendations for how you can improve your application.

Supercharging insights with copilot control in your applications

In the same way that conversational AI is transforming app development, next-generation AI is also revolutionizing how users query and interact with their data.

With the copilot control in Power Apps, app makers can give their users the ability to get intelligent insights about the data in their apps through a conversational chat experience. Users can use natural language to create queries and refine their analysis, all with the help of an AI assistant embedded directly in the running app.

Whether a user needs to understand changes in their inventory, estimate average time to complete a task, or explore which of their campaigns drove the most revenue, the copilot control is ready to listen, analyze, and report.

Here are a few examples of natural language prompts your users can use:

• “What are the most common reasons an inspection fails?”
• “Who are the most active inspectors for that type of issue?”
• “Which equipment is most often inspected?”

Native integration of Microsoft Power Virtual Agents chatbots in Power Apps

We are also announcing native integration of AI-empowered Power Virtual Agents into Power Apps. This means that developers can quickly and easily add a next-generation AI-powered Power Virtual Agents bot to their applications. Simply turn on the control, enter the Power Virtual Agents bot schema name, and your bot is ready to support your users.

Your Power Virtual Agents bot will have access to all the latest Power Virtual Agents features including conversation boosters and natural language bot building.

Learn more about next-generation AI across Microsoft

With the announcement of your personal next-generation AI Copilot, building low-code applications in Power Apps has never been this fast, modern, or intelligent. We are entering an unprecedented time where AI is transforming many aspects of our lives and work. From how we communicate, to how we collaborate, to how we learn, AI is empowering us to do more with less. Microsoft is leading the way on our journey toward empowering every person on the planet to build transformative software in a language we naturally understand.

Copilot features are in preview across Microsoft Power Platform and many more products. Are you ready to join the AI low-code revolution and build apps side-by-side with your personal AI Copilot in Power Apps? The future of low-code development starts today.

Imagine it. Describe it. Power Apps builds it. Sign up now to get access.

See all of Microsoft’s Copilot announcements on the Official Microsoft Blog, and learn about other next-generation AI announcements across Microsoft:

• AI across Microsoft
• Power Platform is leading a new era of AI-generated low-code app development
• Automate smarter than ever before with AI Builder and Copilot in Power Automate
• Now in public preview: Power Virtual Agents’ new advanced authoring canvas
• Copilot in Power Virtual Agents: Next-generation AI assists bot building with natural language
• Build solutions faster with Microsoft Power Platform and next-generation AI

Availability 

These features are currently available in the United States and English language by signup. Note that these preview features are experimental, and accuracy and relevance cannot be guaranteed.

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 Announcing a next-generation AI Copilot in Microsoft Power Apps that will transform low-code development appeared first on Microsoft Power Platform Blog.