AI · AIC-10

Power BI with AI, Claude Code and Cowork

12 hours 2 days

Last updated 25 Sep 2026

Power BI with AI, Claude Code and Cowork is a 12-hour training course by IT Genius Institute. In 2026, Business Intelligence has moved beyond simply building reports into the era of AI-Driven Analytics. Yet the reality most Thai organizations face is…

Training schedule

No public rounds are open right now — register your interest and we will contact you when the next round opens, or request an in-house session for your team.

Corporate training quote

Power BI with AI, Claude Code and Cowork In 2026, Business Intelligence has moved beyond simply building reports into the era of AI-Driven Analytics. Yet the reality most Thai organizations face is that AI features such as Copilot in Power BI require a Fabric Capacity of F2 or above, or Power BI Premium P1 or above. The Power BI Pro and PPU licenses most people hold cannot use Copilot, which turns many AI-for-Power BI courses into watching the instructor demo instead of doing the work yourself. This course solves that by choosing a path every learner can actually do from the first minute: using Claude Code, Anthropic's agentic AI assistant, connected to Microsoft's Power BI Modeling MCP Server through the MCP (Model Context

Protocol) standard, which runs directly on your own machine and needs no Fabric Capacity at all - the free Power BI Desktop download is enough. Across two days you will use AI to work on your own semantic model for real: reading the model structure live, writing and validating DAX, performing bulk operations across hundreds of items in a single command, generating documentation automatically, and having AI build and edit real report pages through Power BI Project files (PBIP/PBIR), finishing with automatic executive reports in Word and PowerPoint via Claude Cowork, together with an AI governance framework you can apply safely to organizational data. (Hands-on classroom training, 2 days, 6 hours per day, 12 hours in total.)

Objectives

Understand the big picture of AI-Driven Analytics and the direction of Power BI and Microsoft Fabric in 2026, including the real licensing conditions of each AI feature
Design a semantic model that AI can understand, following AI-Ready Modeling, without relying on Copilot
Use Power BI AI Visuals - Key Influencers, Decomposition Tree, Narrative, Anomalies and Q&A - for in-depth analysis, all usable with an ordinary Power BI Pro license
Understand agentic AI and MCP, and install Claude Code and connect it to the Power BI Modeling MCP Server yourself
Direct AI to do real modeling work end to end: reading the model, writing DAX, validating results, bulk operations, setting RLS, and generating documentation automatically
Understand the structure of Power BI Project (PBIP), TMDL and PBIR, and have AI create or edit report pages through these files
Use Claude Cowork to clean raw data and generate executive reports in Word, PowerPoint and Excel automatically
Design an agentic workflow that identifies which steps can be automated and which need human review (human-in-the-loop), and understand governance, security and the precautions of using AI with corporate data

Who this course is for

Data analysts and BI developers who already use Power BI and want to upgrade their skills for the AI era
Managers, planners and analysts who build Power BI reports regularly and want to work faster with AI
IT and data teams who need to define a safe approach for using AI agents with corporate data
Organizations without Fabric Capacity that want to start using AI for BI immediately on a controllable budget
Anyone interested in AI-Driven Analytics who wants to see Claude Code and MCP applied to real BI work

Prerequisites

Prior experience building reports with Power BI Desktop (Get Data, creating visuals and publishing reports)
Basic understanding of data modeling (tables and relationships) and experience writing simple DAX measures such as SUM and CALCULATE
Basic experience transforming data with Power Query and good working knowledge of Microsoft Excel
Basic use of Command Prompt or PowerShell (typing commands, changing folders, checking versions) - no programming required

Curriculum

Course Details

A 2-day onsite hands-on workshop, 6 hours per day (12 hours in total). Across both days you build one continuous project: Sales Intelligence 2026, a sales and customer behavior analytics system for executives, built entirely on a mock dataset with no connection to real corporate data. The hallmark of the course is that everyone can do the work for real from the first minute without any Fabric Capacity, because it uses Claude Code connected to the Power BI Modeling MCP Server running directly on your own machine - the free Power BI Desktop is enough.

Day 1: Power BI in the AI Era - An AI-Readable Semantic Model, AI Visuals and Connecting Claude Code

Section 1: The 2026 BI Landscape and the Truth About Licensing

Where Power BI, Microsoft Fabric and AI agents are heading in 2026 and what has changed
The agentic BI concept: when AI no longer just answers questions but does the work for you
The truth about licensing: which AI features need Fabric Capacity and which do not, and a decision map for organizations
Why this course chooses the MCP and Claude Code path as its core, so everyone can do the work for real with a Power BI Pro license

Section 2: A Good Semantic Model Is the Foundation of Intelligent AI

The key principle: AI does not read your data, it reads your description of the data, with an 8-point model checklist to pass before letting AI use it
Build a star schema, relationships, a date table and basic measures, and lay out the report pages used across both days
Get to know TMDL View and DAX query view, returning measures to the model, and writing many descriptions and formatStrings in a single script
The Three-Layer Verification principle (syntax, semantic, business) for checking everything AI creates, and the createOrReplace trap that silently drops properties

Section 3: AI Visuals in Depth (Usable with an Ordinary Power BI Pro License)

Key Influencers: finding the factors that drive your key metrics, with how to read the statistics
Decomposition Tree: multi-dimensional root-cause analysis with AI Splits
Narrative (Smart Narrative): automatic text summaries with Custom Mode
Anomalies: detecting irregularities in time series data with explanations of the cause
Q&A Visual: asking questions in natural language, with the transition path for when Microsoft retires it

Section 4: Installing and Connecting Claude Code to Power BI

The AI-Ready Modeling approach that works with every AI agent: naming, description, synonyms, perspective and hiding fields
Install Claude Code on Windows and verify readiness
Install the Power BI Modeling MCP Server and connect it to the semantic model open in Power BI Desktop
Test Claude reading the entire model structure live and prove it truly reads rather than guesses
Workshop Day 1 (Sales Intelligence 2026): build an AI-Ready semantic model with a dashboard that drills in using Key Influencers, Decomposition Tree, Anomalies and Narrative, then install Claude Code, connect it to the model through the MCP Server and have Claude summarize the model structure into a document

Day 2: Claude Code, MCP and Cowork - Let the AI Agent Work for You, from Modeling to the Executive Report

Section 5: Getting to Know Claude Code, Claude Cowork and MCP

The Claude landscape in 2026: Claude Code, Claude Desktop, Claude Cowork and Claude for Excel, and choosing the right tool for the job
The settings you must know: CLAUDE.md, Permission Modes (default, acceptEdits, plan) and the settings file
What MCP is and why it became the common standard, and the MCP architecture: Host, Client, Server, Tools, Resources and Prompts
An overview of Power BI MCP servers: local modeling server vs remote server, and the security you must know before installing any server

Section 6: Power BI Modeling MCP Server - Hands On

Have Claude write DAX measures from natural language and validate them by running a real DAX query
Bulk operations: create and edit many measures at once, rename the whole model, add descriptions to every object and create Thai translations, using transactions so it can be rolled back
Set up Row-Level Security (RLS) and perspectives with natural language
Generate documentation automatically: Data Dictionary, Measure Reference and Model Handbook, and build your team's own Skill and Custom Slash Command

Section 7: Data Preparation and Building Reports with AI through Power BI Project (PBIP)

Always profile the data first: have AI survey data problems before touching anything, then clean the raw data - missing values, duplicates, date formats and Thai-specific issues such as Buddhist and Gregorian years mixed together
Merge files from multiple sources (CSV, Excel) ready for Power BI, and compare when to use Power Query versus when to use AI
Enable and save as a Power BI Project (.pbip) with the PBIR and TMDL formats, understanding the file structure: definition.pbir, pages, visual.json and page.json
Have Claude Code build new report pages from natural language or from a sample image (mockup), verifying the result in Power BI Desktop

Section 8: Executive Reports with Claude Cowork, Agentic Workflow and Governance

Use Claude Cowork to pull analysis results from Power BI into executive summary reports (Word), presentations (PowerPoint) and data files (Excel) automatically, and design templates the AI can reuse every month (reusable skills)
Principles of agentic workflow design: what can be automated and what needs human review (human-in-the-loop), and placing three gates - input, processing and output
AI governance and security: permissions, data privacy, PDPA, controlling MCP server permissions, prompt injection and the limits of AI such as hallucination and verifying numbers
Workshop Day 2 (Master Workshop - Sales Intelligence 2026): have Claude Code create a set of DAX measures in bulk (YoY, running total, RFM customer segmentation), organize the whole model and generate documentation, then receive a new dataset for AI to clean, update the model, build new report pages through PBIP, and generate the executive summary report and presentation automatically with Cowork, then present the work

Frequently asked questions

Who is Power BI with AI, Claude Code and Cowork for, and what background is needed?

Built for Data analysts and BI developers who already use Power BI and want to upgrade their skills for the AI era · Managers, planners and analysts who build Power BI reports regularly and want to work faster with AI · IT and data teams who need to define a safe approach for using AI agents with corporate data Background you should have: Prior experience building reports with Power BI Desktop (Get Data, creating visuals and publishing reports) · Basic understanding of data modeling (tables and relationships) and experience writing simple DAX measures such as SUM and CALCULATE Not sure the fit is right? Talk to our team on LINE @itgenius or call 02-570-8449.

How much does Power BI with AI, Claude Code and Cowork cost and how long does it run?

THB 6,500 (currently THB 5,850 on promotion). The course runs 12 hours. The fee covers course materials, lunch and refreshments throughout. Pay by bank transfer to the company account, confirm it on our payment page, and we can issue the receipt or tax invoice in your company's name.

Do I get a certificate?

Yes. Everyone who completes the course receives a Certificate of Completion from IT Genius Institute. Each certificate carries its own number, and anyone holding that number can verify it online on our certificate page, so you can add it to your portfolio or pass it to HR as evidence of training.

Where does the training take place, and is there an online option?

You can attend onsite at IT Genius Institute or arrange to join online, and we also run it as a private in-house session for your team. Ask about dates and venues on LINE @itgenius or call 02-570-8449.

What if I fall behind or miss a session — can I retake it?

Yes. You may retake the same course free of charge in a later round, under the institute's conditions. Tell our team which course and round you attended, and we will check it and offer you the rounds that still have seats. Ask us on LINE @itgenius or call 02-570-8449.

How do I enrol, or request a quotation for my company?

Enrol online with the registration form on this page. You can register several attendees at once and enter your tax ID and billing address for the tax invoice. Or request a company quotation straight from the quote button. For anything else call 02-570-8449 or reach us on LINE @itgenius.