AI is coming to Tabular Editor 3

Key takeaways

• An AI assistant is coming to Tabular Editor 3: A context-aware assistant that can interact with your semantic model and run C# scripts on your behalf.
• C# scripting provides change control: The assistant works through C# scripts with full undo support, so proposed model changes stay visible and easy to review.
• It focuses on common modelling work: Guidance, DAX suggestions, error analysis, and creating Best Practice Rules and reusable macros.
• Bring your own LLM: You choose the LLM provider, so data processing stays between you and your provider, and the assistant stays out of your way if you don't use it.

AI is becoming part of everyday semantic model development. In Tabular Editor 3, we want that assistance to be practical, optional, and controlled by the user.

Introducing the AI Assistant

We’re introducing an AI assistant directly inside Tabular Editor 3. It is a context-aware assistant that can interact with your semantic model and execute C# scripts on your behalf, while keeping the proposed changes visible in the tool where you already work.

Why we’re building this

AI is most useful in Tabular Editor when it works through the same mechanisms that experienced model developers already trust. The important mechanism here is C# scripting.
LLMs are often useful for generating C# code, and in Tabular Editor, scripts can modify every aspect of a semantic model with full undo support (Ctrl+Z) if the result isn't what you expected. The assistant doesn't get a separate, hidden way to change model metadata. It works through scripts, so the intended changes remain visible, easy to review, and under your control.

What the AI Assistant will do

The assistant won’t just write scripts – it will support you across many tasks, such as:

• Guidance and instructions for semantic model development, pointing you to relevant UI elements or features.
• DAX code suggestions that can answer complex business questions based on your current model.
• Error and warning analysis, helping you troubleshoot issues quickly.
• Creating Best Practice Rules and reusable C# script macros.

The assistant is also designed to stay out of the way. If you don't want to use it, you can continue working in Tabular Editor as you do today.

Privacy comes first

Trust is critical when working with sensitive models and data. That’s why this feature is being built as a bring-your-own-LLM assistant. You decide which LLM provider to use, so data processing stays between you and your chosen provider.

What’s next?

The AI assistant is still in development. Over the coming weeks, we’ll share more details about how it works, how to configure it, and which modelling tasks it can help with.

For further reading

• AI in Tabular Editor 3 -- Full control for your organization (Tabular Editor). The follow-up announcement explains how organizations can control, disable, or restrict the AI features introduced here.
• How Tabular Editor supports agentic development for semantic models (Tabular Editor). Places the AI Assistant in the broader Tabular Editor roadmap for AI-supported semantic model development.
• Tabular Model Definition Language (TMDL) (Microsoft Learn). Background on the semantic model metadata format that C# scripts can modify when the assistant generates model changes.

In conclusion

An AI assistant inside Tabular Editor 3 is on its way, and it is being built around the controls model developers already use: C# scripts, undo support, and explicit provider configuration. Because it follows a bring-your-own-LLM approach, you keep control over the provider, your data, and the model changes you choose to apply.