AI for your role

AI for BI Developers

Let the copilot write the measures so you can own the model that makes them trustworthy.

Get the BI Developer brief
The shift

How AI is changing the BI Developer role

In 2026, AI copilots inside Power BI, Tableau, and Looker draft the DAX, SQL, and calculated measures that used to fill a BI Developer's day, and generate dashboard layouts from a description. The defensible work moves up the stack: designing a semantic model people can trust, governing metric definitions so 'revenue' means one thing, and building experiences that actually get used.

What AI can take off your plate

  • Writing DAX, SQL, and calculated measures from a description
  • Generating standard dashboard layouts and visuals
  • Documenting data models and field descriptions
  • Building routine ETL transformations
  • Refactoring tangled measures into cleaner logic

What stays distinctly human

  • Designing a semantic model stakeholders can trust
  • Governing consistent metric definitions across reports
  • Performance-tuning at the model and query layer
  • Deciding what a dashboard should make someone do
  • Saying no to a report that hides more than it shows
Tools

Five AI tools for BI Developers

Microsoft Power BI Copilot
Generates DAX measures, builds report pages from a prompt, and explains what an inherited measure is calculating.
Try it →
Tableau Pulse / Einstein
Surfaces metric changes in plain language and drafts visualizations, letting you focus on the model behind them.
Try it →
ChatGPT
Great for writing and debugging SQL and DAX, refactoring a messy measure, and explaining a slow query plan.
Try it →
Claude
Reviews a data model for grain and relationship issues and drafts clear field-level documentation from your metadata.
Try it →
dbt
With its semantic layer and AI-assisted development, centralizes metric definitions so every dashboard reasons on the same numbers.
Try it →
Prompts

Five prompts to try today

Paste these into Claude or ChatGPT and replace the bracketed parts with your own details.

1. Write a DAX measure
In Power BI I have tables [describe] with columns [list]. Write a DAX measure for [metric], handle [edge case like blanks or filters], and explain how it evaluates.
2. Debug a slow model
This report is slow. Here's the model [describe tables and relationships] and the key measures [paste]. Suggest the most likely performance culprits and concrete fixes.
3. Refactor a messy measure
Here's a calculated measure that works but is unreadable: [paste]. Refactor it for clarity and performance, and explain each change.
4. Define a metric precisely
We disagree on how to calculate [metric]. Lay out 2-3 defensible definitions, what each includes and excludes, and which fits [use case] best.
5. Document the model
Here's my data model metadata: [paste tables/fields]. Draft clear, business-friendly descriptions for each field and flag any that look ambiguous or duplicated.
The playbook

Every AI play for BI Developers

Your full AI playbook for your role — updated every week. Tap any card for a step-by-step walkthrough and examples.

✦  New AI plays are added every week — and go straight to subscribers in their morning brief. Skip the scrolling and get yours delivered free. Get my free brief →
Loading the library…

A day in your inbox

This is the kind of brief a BI Developer gets, every weekday morning.
Monday morning
✦ Personalized for: BI Developer
Engineering PlaybookDebugging
Read the stack trace with a second pair of eyes

You hit an error you have not seen before. Instead of blind guessing, make the model narrow the search first.

Claude (free)  FREE  reads code and error output, explains likely causes

Paste the failure

Give it the error and the code that threw it.

Here is a stack trace and the function it points to. Language: [language]. List the 3 most likely root causes, ranked, with the exact line each one points to. Stack trace: [paste full trace] Code: [paste function]
Ask for the cheapest check

Get a way to confirm before you change anything.

For your top cause, give me one log line or one-line check I can add to confirm it before I edit anything.
Fix and verify

Apply the fix yourself, then run the failing case again. Do not paste secrets or customer data into the prompt.

You stop guessing and test one theory at a time. You still write the fix and run it.

Your role, all in one place
  
Tools, prompts & tricks
Your full library, one tap away.
›
  
Your playbook
Every entry, building each week.
›
  
How AI is changing your role
Where your work is heading.
›

You’re subscribed as BI Developer.  ·  Update your roles  ·  Manage preferences  ·  Unsubscribe
The Morning Current · Powered by Atomic Media Group, LLC

Get the BI Developer brief

One AI play, built for your role, every weekday morning. Free.

You’re in! We just emailed your first brief — it should land in a minute. Add brief@themorningcurrent.com to your contacts so it never hits spam.
Free forever. Unsubscribe anytime. We use your role only to personalize your brief.