{"id":132104,"date":"2025-08-04T09:30:00","date_gmt":"2025-08-04T16:30:00","guid":{"rendered":""},"modified":"2025-08-04T19:24:52","modified_gmt":"2025-08-05T02:24:52","slug":"prompt-columns","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/power-platform\/blog\/2025\/08\/04\/prompt-columns\/","title":{"rendered":"Enrich Your Dataverse Tables Using AI Prompt Columns"},"content":{"rendered":"\n
Microsoft Dataverse continues to evolve as a foundational platform for building intelligent, secure, and scalable business solutions. We are excited to announce the public preview of Prompt Columns, a new way to embed generative AI directly into your Dataverse tables. <\/p>\n\n\n\n
This capability will enable dynamic business logic, context-aware responses that can summarize, classify, extract, and generate content based on your data. <\/p>\n\n\n\n
A prompt column in Microsoft Dataverse is a specialized data column designed to hold textual inputs that serve as prompts for AI models. These prompts can be anything from simple commands to complex queries. The AI model processes these prompts to generate relevant responses based on the input provided. The result is immediately stored in the prompt column, ready to be used in apps, workflows, or reports. <\/p>\n\n\n This means you can bring generative AI directly into your data model without writing code or managing external services. Whether you are summarizing customer feedback, generating draft responses, extracting structured data from unstructured text, or classifying records based on context, prompt columns make it possible with just a few clicks. <\/p>\n\n\n\n Each prompt is fully customizable and can reference one or more input columns within the same table. This business logic is powered by natural language prompts, allowing you to tailor the AI behavior to your specific business scenario. <\/p>\n\n\n\n This feature is currently in public preview and intended for early exploration. It is an opportunity to evaluate the functionality, experiment with real scenarios, and provide feedback that will help shape future improvements. <\/p>\n\n\n\n
<\/figure>\n\n\n\nAvailable Now in Public Preview <\/h2>\n\n\n\n