Sign up

Practical Power BI expertise for people building semantic models, reports and AI-ready analytics

Power BI expertise for the real world

Models that perform, measures that agree and reports people actually use. Power BI is also becoming the semantic layer that Copilot and data agents rely on, so model quality has never mattered more. 

Practical Power BI skills you can put to work

DAX and performance, semantic model design, Direct Lake, governance and deployment, report design and advanced visuals. Plus how coding agents and MCP servers are changing how models get built. 

Learn from the people who wrote the book

SQLBits regularly hosts the authors, MVPs and Microsoft product and Customer Advisory teams who define how Power BI is built and used. Bring your hardest problem. 

Because your SQLBits pass includes virtual, you don't have to choose between sessions. Watch sessions live, catch up on anything you miss and revisit the content afterwards when you need it.

The challenges we’ll help you solve 

If any of these sound familiar, you will find people at SQLBits who have already been there. 

  • Our DAX is slow and nobody can say whether the problem is the model, the measure or the visual. 
  • Every team has built its own ‘Revenue’ measure, and the numbers never agree. 
  • Hundreds of near-duplicate semantic models, with no clear owner or certified source of truth. 
  • Reports take ages to load because pages are crowded with visuals and heavy interactions. 
  • Shadow BI: business users publish unmanaged content outside governance. 
  • Capacity costs are unpredictable, and we can’t tell which workloads are burning capacity units. 
  • Row-level security is complicated and brittle across models, workspaces and now AI agents. 
  • Deployment pipelines and Git CI/CD for PBIX, PBIR and TMDL still feel immature. 
  • Premium P SKUs are no longer sold, and migration deadlines are firm: throttling from day 31 and rejection from day 91 after term end. 
  • Power BI Q&A retires in December 2026, so teams must move to Copilot and Prep Data for AI. 
  • Copilot gives vague answers because our models have no descriptions, synonyms or clean naming, and it needs a paid Fabric F2 or higher. 

Using Power BI to strengthen your company’s AI capability

Prepare data for AI

Authors set an AI data schema, AI instructions and verified answers so Copilot and agents know your business terms. Prep Data for AI is still labelled preview. 

Verified answers

An approved visual is tied to trigger phrases and stored in the model, so common questions return a vetted answer. Data agents check these first. 

The semantic model as grounding for agents

Agents use the model’s schema, synonyms and AI settings, so business logic is defined once and reused. 

Fabric IQ in Microsoft 365 Copilot and Cowork

Answers are grounded in Power BI reports and the models behind them, and run as the signed-in user, so row-level security still applies (Microsoft Learn lists GA, October 2026). 

MCP for custom agents

Fabric IQ is the recommended endpoint for Copilot Studio, Foundry and custom agents. The Authoring server is for builders only. 

Copilot consumption and cost control

Copilot needs a paid Fabric F2 or higher (or Premium P1 or higher). Usage is billed by token and visible in the Capacity Metrics app. 

Distribution where people work

Org apps with audiences went GA in July 2026, and Copilot in apps (preview) can use author-provided verified answers. 

Where agentic AI can help

Eight places agents are already earning their keep in Power BI, and where SQLBits sessions will show you how. 

Semantic model authoring and DAX generation

The Power BI Authoring MCP server (local version GA, hosted version in preview) lets an agent create and edit tables, measures, relationships, calculation groups and RLS roles, and run DAX. 

Coding-agent skills for models

The semantic-model-authoring skill (preview) packages instructions so coding agents such as GitHub Copilot, Claude Code and Cursor can build Import, DirectQuery or Direct Lake models, optimise DAX and deploy. 

Report building

The Power BI Report Authoring skill (preview, PBIP projects) lets an agent create, edit, re-theme and fix broken visuals in PBIR report files. 

Closing the loop on a running Desktop

Power BI Desktop Bridge (preview) lets an agent reload the model and take screenshots to check its own visuals. 

TMDL and Git workflows

Agents edit text-based TMDL and PBIR files that sit in source control. PBIR is now the default and GA report format. 

Model review and documentation

An agent can inventory a model and report findings by severity, and add measure descriptions. DAX query view also supports measure descriptions with ///. 

Copilot in web modeling

Flags unclear structures and inconsistent naming, suggests best-practice design and refines DAX (preview). 

Natural-language questions over governed models

Copilot in reports is GA, and Fabric data agents (GA) route questions to a DAX-generation tool over a semantic model. Advanced multi-step DAX generation is in preview. 

Key Speakers

All of these speakers have appeared on the SQLBits stage – check our 2027 agenda when it’s announced for details of our 2027 Power BI speakers. 

Marco Russo, Co-founder, SQLBI

Microsoft MVP, SSAS Maestro, and author of Power BI and DAX books with Alberto Ferrari. 

 

Alberto Ferrari, Co-founder, SQLBI

Microsoft MVP, SSAS Maestro and author and trainer on DAX and data modelling. 

 

Valerie Junk, Data Analytics, Visualization & Storytelling, Wortell

Microsoft Data Platform MVP specialising in Power BI, data analytics and transforming data into actionable business insights.

 

Patrick LeBlanc, Principal Program Manager, Microsoft; Guy in a Cube

Author, former MVP and co-host of Guy in a Cube, one of the most-watched Power BI channels on YouTube.

Check out some of our recent PowerBI sessions

5 Design Patterns for Better Looking Reports
Designing great Power BI reports doesn’t have to be hard. Join us to explore clear, repeatable steps that make your reports consistent, functional, and user-friendly.
 
AI Beyond the Hype; Practical Solutions for Real Businesses
AI can feel overhyped and inaccessible. This session cuts through the noise, showing how practical AI solutions can be built using Azure AI, Copilot Studio, and AutoML. Ideal for data and tech professionals wanting real, usable AI.
 
Average Fail - Why Averages Can Be a Terrible Idea in Data Analysis
Averages can bite you - repeatedly. Come see how and why, and have a laugh and a cry at the same time!
 
Best Practices for Sharing Power BI Content with External Users
In this session, we will cover typical scenarios for sharing semantic models and reports with external users. We will explore different methods to grant access, considering ease of use, maintenance, and security and compliance perspectives. By the end of the session, the audience will have a clear understanding of the available options for sharing semantic models and reports with external users, along with the pros and cons of each method. This will enable them to make informed decisions on the best approach for their organization
 
Building Context, Not Vibes Pratical AI Augmented Data Engineering - Part 1
Many data professionals have experimented with AI coding assistants, only to find the results inconsistent. Stop relying on AI "vibes." Master Context Engineering. In this hands-on workshop, you will build a complete data platform from source to Power BI. Learn to architect context, configure personas, and leverage practical techniques to deliver production code faster.
 
Building Context, Not Vibes Pratical AI Augmented Data Engineering (Part 2)
Many data professionals have experimented with AI coding assistants, only to find the results inconsistent. Stop relying on AI "vibes." Master Context Engineering. In this hands-on workshop, you will build a complete data platform from source to Power BI. Learn to architect context, configure personas, and leverage practical techniques to deliver production code faster.
 
Choosing the Right Storage Mode: Import, Direct Lake, DirectQuery & Hybrid
Import? Direct Lake? DirectQuery? Hybrid? Learn the real-world decision framework for choosing the right storage mode in Power BI and Fabric.
 
CI/CD in PowerBI: For when just hitting publish isn't good enough
Deploying Power BI content can be more mature than just hitting the ‘Publish’. Discover better, scalable deployment methods using CI/CD principles, built-in features, and advanced tools like Tabular Editor, Azure DevOps, and Fabric APIs.
 
Copilot in Fabric - Explained for the Administrator!
How can admins manage and govern Copilot in Fabric: access control, data residency, security, capacity monitoring, and audit logs, giving you the knowledge to support governance and help your organization use Copilot effectively.
 

Take a tour of SQLBits 2025

Bring your Power BI questions to the people who can answer them. Book your SQLBits 2027 pass today.