Why Do Power BI Copilot AI Instructions Seem To Work Better in Desktop Than In The Service?

I’m spending a lot of time with organisations testing Power BI Copilot at the moment, and something I hear a lot is that Copilot works well in Desktop but when you publish your model to the Power BI Service the results are a lot more inconsistent. One reason why is because of how updates to … Continue reading Why Do Power BI Copilot AI Instructions Seem To Work Better in Desktop Than In The Service?
Published on:
Learn moreRelated posts
Storytelling with Power BI Scatter Chart
Column or Bar chart can be easily used for showing a single measure’s insight across a category. Mixed charts such as Line and Column ch...
2 days ago
Introducing the Fabric Notebooks Competition for Power BI
Join the Power BI Notebooks Competition this August to showcase your creativity and contribute to the community gallery.
3 days ago
Introducing the First-Ever Fabric Notebooks Competition for Power BI!
Join the Power BI Notebooks Competition this August to showcase your creativity and contribute to the community gallery.
3 days ago
Power BI Cognitive Services and Azure Machine Learning features retiring; transition to Fabric AI services
Power BI is retiring Cognitive Services and Azure Machine Learning features by September 15, 2025, transitioning AI capabilities to Microsoft ...
4 days ago
Running a Power BI Performance load test using Visual Studio Code
This is the final part of my blog series for Power BI Performance testing, where I will finally run the Power BI Performance Load testing usin...
5 days ago
AI in Power BI: Time to pay attention
5 days ago