Press "Enter" to skip to content

Category: Generative AI

What’s New at Ignite 2026

Arun Ulag tells us what’s new:

Over the past year, my conversations with customers have changed. A year ago, the question was which model to choose. Now it’s how to put agents to work on the processes that run the business, and how to trust them to do it.

With the same frontier models available to everyone, the advantage comes from what no one else has: your context. It’s how your business runs, what your people know, and the systems and data you’ve spent years building. That’s your IQ. It’s your intellectual property, so it should stay yours, and it should work wherever your people and agents do. Our job is to make every layer beneath your agents better, from the infrastructure that runs them and the estate they act on to the apps they power and the business context that tells them how your company works.

If you’re all-in on agentic AI, you’ll find a lot to be happy about. If not, well…

Leave a Comment

Remaining Relevant in an LLM World

Erik Darling shares some advice:

Erik Darling here with Darling Data. And in today’s video, we are not going to talk directly about SQL Server. We are going to talk about how to stay relevant in the age of AI, right? All the AI stuff going on.

Even, I mean, I think that’s, it’s obviously a stupid term. We all know that they’re LLMs, right? We all know it’s not artificial intelligence. It’s just random word generators. We just happen to, you know, be pretty, pretty decent at coding sometimes and whatnot.

Erik’s “I’m an old man because I use an RSS feed reader on my phone.” I feel seen.

I fully agree with Erik’s point about AI-generated blog posts as a waste of time. I get frustrated when I get part of the way through an article, have something click in my head, paste a chunk of the post into Pangram, and see that yeah, this is LLM-generated. Right around that time, I typically decide not to post it here (except in very specific circumstances).

1 Comment

Optimizing DAX with AI

Marco Russo and Alberto Ferrari speed up operations:

The debate over whether AI will replace human work is heating up. However, our vision is different: AI is not a replacement; it is a powerful tool, and when AI and humans work together on a problem, the outcome is better than when either works on their own.

Optimizing DAX is a fascinating task. However, in the process of optimizing DAX, you need to pay attention to several details:

  • The new formula needs to be equivalent to the old one; this requires extensive testing.
  • The shape of the query being executed matters: a formula may be better than another in a specific test, but not in others.
  • The data distribution matters: a database with 100K customers and 100M transactions requires a different optimization compared to one with 10K customers and 10B transactions.

You will often get about as much out of using generative AI tools as you are willing to put in. This article does a good job of showing that.

Leave a Comment

Testing AI Agent Skills

Eugene Meidinger and Ruben Van de Voorde try things out:

Writing a skill takes time, and skills are context that can help but also hurt the quality of the agent’s work. So how do you know if a skill actually helps? You can test it with evals. An eval is a prompt that you re-run under the same conditions, so that the only variable is what you deliberately change. You use the same model, starting context, and the same files (and wipe leftover memory from previous attempts). Then you compare: before and after an edit, with and without a skill, or two versions of a skill. Agents are non-deterministic, so you have to run the comparison multiple times to get a reliable difference; a few runs per condition is enough to start. Decide how a run is scored before looking at the results: use objective checks where you can (did it run the right command?), and for subjective calls write down beforehand what a good answer must include. Also run in a clean workspace: if the solution is already in another branch, the baseline run isn’t a real test. Some companies run large automated eval suites, but a few saved prompts and some notes are enough to start.

Click through for a testing technique and a warning around relying on a generative model to do the work for you.

Leave a Comment

Testing Fabric Data Agent Accuracy and Determinism

Marc Lelijveld trusts but verifies:

Over the past year, I’ve written quite a bit about Fabric Data Agents. From configuring them and preparing Semantic Models for AI, all the way to deploying Data Agents using the Data Agent SDK. But once you start moving Data Agents beyond experimentation, another question quickly becomes relevant: “How do you actually know whether your Data Agent continues to return the right answer?”

Of course, you can open the Data Agent, enter a prompt and manually validate the response. That works perfectly fine while experimenting with a handful of questions, although it can already become quite time-consuming. Now imagine having to validate 20, 50 or maybe hundreds of questions, and not just once, but every time your data, Semantic Model, Agent Instructions or other parts of the solution change.

There is another aspect to this. With generative AI, we don’t only care about accuracy, but also about determinism. If we ask the same question again, can we rely on the Data Agent to consistently produce the expected outcome? This is where automated testing becomes increasingly important.

Read on to see how you can work toward answers for both.

Comments closed

DAX Lib MCP Server

Marco Russo makes an announcement:

At the end of 2025, we launched DAX Lib, a public repository of DAX user-defined functions. So far, importing a DAX library has required a few manual steps, like clicking Add to Power BI on daxlib.org and then copying and pasting the DAX code into the TMDL View of your model, or using the dedicated tool in Tabular Editor 3. Both work well, but if you already use an AI assistant next to Power BI Desktop, we can now delegate this task to it. The DAX Lib MCP server version 0.1.0 is available now.

Click through if you’d like to snag a copy. It’s only available for Windows at this point, though considering Power BI’s OS requirements, that makes sense.

Comments closed

Choosing a Chunking Strategy for RAG Applications

Bala Priya C puts together a decision tree:

In this article, you will learn how to choose the right chunking strategy for a retrieval-augmented generation system by working through a structured decision tree tied to the properties of your documents and retrieval task.

Topics we will cover include:

  • What each major chunking strategy assumes about your documents, and when those assumptions hold.
  • A six-question decision tree that maps concrete document and retrieval conditions to specific chunking strategies.
  • The failure signals that indicate a chosen strategy is not working, and the fixes that tend to resolve them.

Click through for the list of strategies and when to include each.

Comments closed

Lessons Learned from Troubleshooting with LLMs

Grant Fritchey spends a weekend:

Grant Fritchey walks through a real troubleshooting saga – using Wine, a shim DLL, a misconfigured registry entry, and a lot of trial and error – to get a BridgeCom Maverick radio’s Windows CPS running on Linux Mint.

Along the way, repeated dead ends revealed a pattern: AI tools stay locked onto whatever direction you last pointed them, and it’s up to you to redirect, request alternatives, and demand measurement over guesswork.

In this article, Grant shares everything he learned from the experience, including 8 key takeaways to help you avoid similar trouble when using AI in the future.

Grant takes us through the story and shares eight tips for better troubleshooting along the way. Oh, and Wine is notoriously finicky, so I can totally get why it’d take a while to sort out the issues Grant had.

Comments closed

Connecting Azure Databricks to a Microsoft Foundry AI Gateway

Drew Furgiuele connects the dots:

While some people might look at the different capabilities and think this is an “either/or” scenario, the reality is that most Azure customers are going use (or even need to use) both: developers building apps and agents in Databricks, for example, may want to leverage a model or other agent deployed in Foundry. Meanwhile, developers in Foundry may need to call a Databricks managed MCP service.

These types of calls aren’t all that difficult; in fact, both platforms provide built-in connectors or UI solutions to make this happen: simply provide the service endpoint, pick your authentication method, and you’re pretty much done. However, the introduction of the respective gateways, especially on the Foundry side, can make this just a little more complicated. Let’s look at one example.

Click through for that issue and how Drew was able to work around it.

Comments closed

Adding Temporal Reasoning to RAG

Ivan Palomares Carrascosa checks the date:

Topics we will cover include:

  • How to extend standard subject-predicate-object triples into time-stamped quadruples stored in a simple temporal graph.
  • How to calculate recency weights with exponential decay and use them to rank conflicting facts as of a given query date.
  • How to tune the half-life parameter and integrate the temporal graph into a deterministic 3-tiered Graph-RAG retrieval pipeline.

This is especially important if you’re searching over the news or other systems that value more recent information over older information.

Comments closed