Agentic AI in Power BI and Fabric, Part 1: Concepts, Terminology, and How to Think About It

It has been a while since I published my last blog and YouTube video. Life got a bit busy, and to be honest, finding enough focused time became harder than I expected. But here I am, on the very last day of 2025.

I do not really see this blog as the final post of 2025. I see it more as an opening for what is coming next. In a couple of hours, we will be in 2026. Looking back, 2025 was a year full of ups and downs. Some very good moments, some sad ones too. But all in all, as Brian May from Queen once said, “The Show Must Go On”.

So let us start the next year with a topic that has been on my mind a lot recently. Agentic AI, and how it can realistically help us in Microsoft Fabric and Power BI projects.

If you like to listen to the content on the go, here is the AI generated podcast explaining everything about this blog 👇.

Why this topic needs a series, not a single blog

Before we go into any definitions, I want to explain why I am turning this into a multi-part series.

Agentic AI is a broad topic. It touches tooling, process, safety, productivity, and also mindset. Trying to cover all of this properly in a single blog post would either make it too shallow, or too long and hard to follow. Neither is useful.

So I decided to break it down into a series:

  • This first blog is about concepts and terminology
  • The next blog will cover initial setup and tools
  • The following one will focus on hands-on Power BI scenarios

This first part intentionally stays away from tools and demos. The goal is to build a solid mental foundation first.

What this series is and what it is not

Agentic AI is one of those topics where expectations can easily go in the wrong direction. So it is important to be very clear.

This series is not:

  • A story about replacing engineers, analysts, or architects
  • A full AI or machine learning theory course
  • A generic prompt list without context

This series is:

  • About improving productivity in real delivery projects
  • About assisting people, not replacing them
  • About using AI in a controlled and responsible way
  • Focused on Microsoft Fabric and Power BI implementations

If you are expecting magic or shortcuts, this series is probably not for you.

Where Agentic AI fits today in the Microsoft Fabric world

Before going further, one important clarification is needed.

At the time of writing this blog, Agentic AI is not available in the built-in Copilot experiences in Microsoft Fabric or Power BI. Copilot today is mainly a conversational assistant. It does not plan tasks, use external tools freely, or execute multi-step workflows in the way Agentic AI does.

Everything discussed in this series is about agentic setups, for example using tools like VS Code, external agents, and Model Context Protocol servers, which we will cover later in the series.

This distinction is important, otherwise expectations will be wrong from the start.

Continue reading “Agentic AI in Power BI and Fabric, Part 1: Concepts, Terminology, and How to Think About It”

Microsoft Fabric: Use Copilot to Generate Data Model Synonyms

Microsoft Fabric: Use Copilot to Generate Data Model Synonyms

One of my older posts explains how to enable Copilot on Fabric and how to use Copilot to generate Power BI reports. In this post, I aim to explain yet another use case for Copilot that can help us to make a better and more useful semantic model in Power BI using synonyms. In an old post published in May 2016, I explained how to use Power BI synonyms to take our Power BI Q&A experience to another level. In that post, I explained how we could use synonyms to translate data model objects in different languages so the end-user could ask questions in their native language and get the results in Power BI. That was such a cool use case for synonyms, I suppose, wasn’t it? Fast track to December 2023, I believe the Q&A is still one of the coolest Power BI features that stands out when demoing the solutions to the customers; therefore, it makes absolute sense to use synonyms to improve the Q&A‘s efficiency and accuracy. This blog post explores the possibility of using Copilot to define synonyms in Power BI Desktop.

Prerequisites

As explained here, we first need to enable Copilot on Fabric Service. Please note that the technique explained in this post requires either Power BI Premium Capacity or at least F64 Fabric capacity and won’t work on PPU, Embedded capacities, Fabric capacities smaller than F64 or Fabric Trial (FT) capacities.

We also need to have the latest version of Power BI Desktop installed on our machine. With that, let’s begin.

Using Power BI Copilot to generate synonyms

While defining synonyms for the semantic model objects significantly helps with the Q&A experience, it is still a cumbersome process if done manually. So, if we meet the prerequisites, we can summon Copilot to the rescue. Follow these steps after opening a Power BI file in Power BI Desktop:

  1. Ensure you’re signed into Fabric service with your account
  2. Click the Insert tab
  3. Select the Q&A visual
  4. On the Q&A visual, click the Q&A Setup button shown with a gear icon
  5. On the Q&A Setup window, you must see a message offering to “Improve Q&A with synonyms from Copilot” on top of the window; click the Add synonyms button

The following image shows the preceding steps:

Improve Q&A with synonyms from Power BI Copilot in Microsoft Fabric
Improve Q&A with synonyms from Copilot
Continue reading “Microsoft Fabric: Use Copilot to Generate Data Model Synonyms”

Microsoft Fabric: Generating Reports with Copilot

Microsoft Fabric Generating Reports with Copilot on Fabric

In Nov 2023, Microsoft announced Microsoft Fabric’s general availability and Public Preview of Copilot in Microsoft Fabric. In a previous post, I explained what Copilot means to Power BI developers, which is valid for other Fabric developers such as data engineers and data scientists as Copilot for Fabric helps with those experiences as well. But the main focus of this blog post is to discuss the requirements, how to enable Copilot, and how to use it from a Power BI development point of view. So, this blog will not discuss other aspects of Copilot in Microsoft Fabric. With that, let’s begin.

Requirements

Right off the bat, Copilot is only available on Power BI Premium capacities or their equivalent Fabric capacities. So, NO it is NOT available on Power BI Pro or Premium Per User or Power BI Embedded Analytics. So the Power BI items you want to use Copilot on must be in a Workspace assigned to a Power BI Premium P1 or Microsoft Fabric F64 capacities or higher.

You also need to have a Contributor role on the premium workspace.

To use Copilot, your Microsoft Fabric Administrator must enable it from the Fabric Admin Portal. This setting is not available in all regions yet, but Microsoft is gradually rolling it out to more regions.

Useful links:

Enabling Copilot on Fabric Admin Portal

As mentioned before, your Fabric Administrator must enable Copilot features within the Admin Portal. Follow these steps to enable Copilot on your tenant after logging into Microsoft Fabric:

  1. Click Settings (the gear icon on the top right of the page)
  2. Click Admin portal
  3. Ensure that the Tenant setting tab is selected
  4. Scroll all the way down to the Copilot and Azure OpenAI Service (preview)​ section

Note

You can also use the search box and search for OpenAI to find the Copilot and Azure OpenAI Service (preview)​ section.

  1. Enable the Users can use a preview of Copilot and other features powered by Azure OpenAI
  2. Click the Apply button
  3. Enable the ​​​Data sent to Azure OpenAI can be processed outside your tenant’s geographic region, compliance boundary, or national cloud instance
  4. Click the Apply button again

That is it. You enabled the Copilot capabilities on your tenant.

The following image shows the preceding steps:

Enabling Copilot for Power BI in Fabric Service Admin Portal
Enabling Copilot in Fabric Admin Portal
Continue reading “Microsoft Fabric: Generating Reports with Copilot”

Microsoft Fabric: Terminologies and Personas Explained

In this blog post, I will explain some of the key concepts, personas, and terminologies related to Microsoft Fabric, a SaaS analytics platform for the era of AI. If you are not familiar with the basic concepts of SaaS analytics platforms and how Microsoft Fabric fits in, I recommend you read my previous blog post, where I explain them in detail.

Microsoft Fabric is an experience-based platform, meaning users can interact with it depending on their roles and personas. For example, a data engineer can use the Data Engineering experience to perform large-scale data transformation through the lakehouse. A data scientist can use Data Science experience to develop AI models on a single foundation without data movement. A business analyst can use the Power BI experience to create and consume interactive reports and dashboards. And a data steward can use the Data Activator experience to govern and secure data across the organisation.
The Data Activator experience is in private preview and is not available for public use yet!

Microsoft Fabric Terminologies

To understand how Microsoft Fabric works, it is crucial to know some of the terminologies that are used in the platform. Some of them are existing terms that are also used in Power BI or Azure services, while some of them are new and specific to Microsoft Fabric. Here are some of the key terms that you should know:

  • Tenant: A tenant is a dedicated instance of Microsoft Fabric that is provisioned for an organisation or a department within an organisation. A tenant has its own set of users, groups, permissions, capacities, workspaces, items, and experiences. A Fabric tenant is associated with an Azure Active Directory (AAD) tenant, which is a directory service that the organisations own when they sign up for a Microsoft cloud service such as Azure, Microsoft 365, Power BI, etc. AAD provides identity and access management for cloud applications. A tenant in Microsoft Fabric can only be accessed by users who belong to the same AAD tenant.
  • Capacity: Capacity is a term that refers to the amount of resources available to support a computing service. In the context of SaaS applications, capacity refers to the ability of the system to handle a certain amount of load or demand based on the required resources and infrastructure such as compute power (CPU, RAM, etc.), storage, network bandwidth and whatnot. As explained in my previous post, Microsoft Fabric is a SaaS platform. So, from a Microsoft Fabric perspective, capacities are sets of resources that are allocated to a tenant to run analytics workloads. The capacities sit in a tenant, and the available resources can be shared by multiple workspaces or dedicated to a single workspace for better performance and isolation. Microsoft Fabric capacities are available in various F SKUs that offer different levels of resources and features. For more information about capacities and SKUs, see Microsoft Fabric Capacity and SKUs.
  • Workspace: A workspace is a logical container that holds a collection of items and artefacts. A workspace can have one or more owners who can manage its settings and permissions and one or more members who can access its items. A workspace can also be assigned to a capacity to run its analytics workloads. In Microsoft Fabric, workspaces are based on Power BI workspaces.

The above terms also apply to Power BI, so they have been used within the community for a long time. The hierarchy starts with an organisation acquiring their potential Tenants, and then the purchased Capacities are available to tenants and the Workspaces that are assigned to capacities.

Continue reading “Microsoft Fabric: Terminologies and Personas Explained”