Prompt Columns in Dataverse
Introduction In this blog, I’m going to share about a new capability in the Power Platform: The Prompt Column (Preview) in Dataverse. This feature brings the power of generative AI directly into your data tables, allowing makers to create AI-driven text outputs based on other columns within the same record. Traditionally, if you wanted to generate summaries, categorize records, or draft responses, you’d rely on Power Automate flows, plugins, or external AI connectors. That meant extra steps, more configurations. With the Prompt Column, you can embed intelligence directly in your data model. You define a prompt a natural language instruction and the system dynamically generate text output based on the values in other columns of the record. Problem Statement One of the challenges in most business apps is context generation. Data often exists in isolation descriptions, titles, and notes are stored separately, and users must interpret meaning manually. This disconnect means that insights are locked behind manual work or external processes, slowing down decision-making and reducing the real-time value of your data. Solution The Prompt Column (Preview) helps bridge this gap by letting you define AI prompts directly within Dataverse. Using natural language, you can instruct the system to generate text based on other columns — no flow, plugin, or external integration required. For example, you can create a prompt like: “Summarize the case title and description in 3 bullet points.” and the column will automatically produce an AI-generated summary whenever the record is viewed or refreshed. This makes your data tables smarter and your forms more informative — enabling use cases such as: Steps to Create and Test a Prompt Column in Dataverse Define the PromptWrite your natural language instruction Add Input ColumnsSelect which columns should be used as input (like Title, Description, Priority, etc.) You can always filter the attributes as well so have more precise data according to your needs. Save and Add to FormAdd the prompt column to a form in your model-driven app so you can visualize the output. Test the OutputOpen or create a record, populate your input fields, and let the prompt generate text automatically. You can always play with the available models and see which suits best. Refine or IterateAdjust your prompt for tone, detail, or format. For example, you can make it formal, concise, or bullet-style depending on your use case. So that’s pretty much about it , for now the prompt column feature only gives you text as the default data type. You can further play around with the feature and always try new things eg: I tried generating a Json format with some attributes in my table which could be used in power automate flows or further processing Conclusion: As this feature matures, it’s likely to evolve beyond record-level prompts, potentially opening doors to contextual AI summaries across relationships and tables. For now, it’s a great opportunity to experiment, learn, and rethink how you make your data tell its own story. Thank you Aslin, for your valuable inputs to this blog!
How to generate Model-Driven and Canvas Apps with Copilot
Introduction In this blog, I’m going to share about an exciting capability in the Power Platform: generating Model-Driven and Canvas Apps with Copilot. Traditionally, creating apps required a lot of setup defining tables, building forms, and wiring up relationships before you could even start testing your idea. This process often slowed down makers who wanted to quickly translate business needs into working solutions. With Copilot, Microsoft has introduced a smarter way to begin. Instead of starting from scratch, you can describe your app in plain language, and Copilot will generate the core structure tables, forms, views, and layouts for you. It’s not meant to replace customization, but it gives you a strong starting point so you can spend less time on repetitive setup and more time shaping the features that matter most to your business. Problem Statement One of the biggest challenges with Model-Driven and Canvas Apps is the amount of upfront work required before you even have something usable. You need to define tables, set up relationships, and design forms and views. While this structure is powerful, it often slows down innovation. For organizations that want to quickly test ideas and turn them into business solutions, this initial setup can feel like a hurdle rather than a starting point. Solution Copilot helps bridge that gap. By using natural language, you can describe the kind of app you need, and Copilot will generate the basic structure for you. It cuts down the setup effort and lets you jump straight into refining and extending your app. Steps to Generate a Model-Driven App Using Copilot Step 1: Navigate to the Maker PortalGo to make.powerapps.com. Select Create → Start with Data. Step 2: Describe Your AppYou will be prompted to describe your app in around 200 characters. For example, try this prompt: “Create a model-driven app for managing projects, tasks, and approvals with entities for Projects, Team Members, Status, and automated workflows for notifications and reporting.” Copilot will generate a draft app plan for you. Step 3: Refine the PlanAfter the first iteration, you can keep adding details in natural language to refine the entities, relationships, and features. For instance, you might add requirements for resources, deadlines. Step 4: Save and Choose Your App TypeOnce satisfied with the generated plan, select Save and Open App. The dropdown gives you an option to choose between a Canvas App and a Model-Driven App. For this walkthrough, we’ll select a Model-Driven App. Step 5: Review and ExtendYour model-driven app is now ready. While Copilot generates the core entities and relationships, it might not cover every required field or customization. You can easily extend the app by: Final Thoughts Copilot doesn’t replace the need for thoughtful design, but it dramatically reduces the time and effort required to get started. Instead of spending hours on setup, makers can focus on building value-driven features, refining user experiences, and aligning apps with organizational goals. As the feature matures, it will become an assistant in the low-code toolkit making app creation faster, smarter, and more accessible for everyone. In the meantime, makers are encouraged to experiment with its limits and capabilities to fully understand its potential. Thank you, Aslin for your inputs to this blog.
How to create a chatbot using Generative AI using MS Copilot Studio
Hello everyone, and welcome to the blog, In this blog, we are going to create a simple yet effective chatbot by using Generative AI by just providing the Website URL or a document with some information related to a Topic. Prerequisite: Login to Microsoft CoPilot Studio and sign in or sign up for a free Microsoft Copilot Studio instance. Let’s Start by creating a new CoPilot as shown below: Following this step, you will be able to configure the CoPilot Name and the language that you would like Copilot to speak. There are several languages available for selection. I’ll be sticking to English for the time being. You can see that there is a dialog box to enter the website URL that you want to use to generate the generative answers in the screenshot above. I’ve entered the Amazon URL for the time being. After completing the required fields, click Create to start a new CoPilot. And allow time for the CoPilot to be built. After giving some time to build Microsoft copilot you will get you Chatbot as shown in the screenshot below I’ve now included a website URL so you can get the response. So let us try posing a relevant question. As you can see in the screenshot above, I asked a question regarding the price of the iPhone 15, and it produced an answer based on the reference link I gave. As you can see, it provides the appropriate link for you to purchase the item. Let’s click the link to view the outcome. The same is shown in the screenshot below. Here’s how to enhance the intelligence and effectiveness of your chatbot and apply it to business solutions to utilize your customer experience in a low-code, no-code manner. Additionally, you can increase the number of website URLs that your chatbot cites. Navigate toward the Generative AI Tab, as indicated in the screenshot below, to add more website URLs. The Generative AI Tab overview is displayed in the screenshot below. You can add more website URLs in the places on the right that are highlighted. in order for your chatbot to respond to additional inquiries. You can also see that you may give your bot document references to generate extra answers in the highlighted section above. Let’s explore how we may upload a document and provide our bot with extra data. As seen in the screenshot below, I have a Word document with information about Shekaru, an Indian giant squirrel. The chatbot won’t be able to provide you with information about it if we ask it before uploading the documents. An example of this can be seen in the screenshot below. Fig. 1: Because we haven’t given the chatbot any information about Shekaru, it is unable to comprehend the inquiry. Fig. 2: A document with Shekaru-related information. Note: (This information I have taken from Wikipedia the link for the same Click here) We will now upload this document as it appears in the screenshot below. As seen in the screenshot below, once the document has been uploaded, it will appear in the Upload Document Section. And now that we’ve uploaded the document with Shekaru-related information, we’ll be asking the chatbot questions about Shekaru. We would rephrase the query that the chatbot was unable to respond to the first time. As we ask the same question, “What is Shekaru?” we can see that in the screenshot above. It is capable of providing answers and summaries for the data from the uploaded documents. For the blog, that was all. I sincerely hope you enjoy this blog. If you do, kindly let me know, and feel free to leave a comment with any recommendations. Thank you, Rasik for your valuable insights!