You might notice that the advice you get from Copilot in SSMS isn't very good, but it isn't necessarily AI in general. Part of the problem is something specific about SSMS Copilot and the way it prompts LLMs, and I wish I could tell you exactly what it is, but I can't because I don't have access to how SSMS is changing your prompts.
I get a lot of emails like this:
Hi! I built an app. Can you take a look at it, give me your feedback, and then help get the word out to your readers?
I asked y'all to make the comments on this post look like my ChatGPT history, and y'all understood the assignment. The answers were all over the place from accurate to humorous. Here are the 5 runners-up first, each of whom won a Fundamentals Bundle for themselves or someone they love, since many of these folks already had a Fundamentals membership:
Need to share an execution plan, like on forums or on Stack Overflow, and you wanna get their advice as quickly as possible? Paste the XML into PasteThePlan.com and you get a link that you can share to anyone with your plan's details.
The user interface is now cleaner, with separate tabs for query plan, query text, AI suggestions, raw XML, and your recent plans:
Let's have some fun.
Put yourself in the frame of mind of the fella who writes this blog.
PasteThePlan has a new AI Suggestions tab, and it's been really fun to watch the query plans come in and the advice go out. Here are some examples: Date "tables" - when I looked at the query, I glossed over the real problem. I thought arc_Calendar was a real date table, but AI figured out…
Copilot in SSMS has two parts. Usually people focus on the pop-out Copilot chat window, and that's useful for sure, but honestly I think you're going to get way more mileage out of the code completions feature, right away, because it blends in with your existing workflows. Let's say that I'm working with the Stack…
Let's start with a 7-minute demo video - I didn't edit this down because I want you to be able to see what happens in real time. In this video, I point the desktop version of Claude Code at a Github issue for the First Responder Kit and tell it to do the needful:
https://www.youtube.com/watch?v=RI0EscPWYKs
LinkedIn is full of absolute trash these days. Just flat out bullshit garbage. (Oh yeah, that - this post should probably come with a language disclaimer, because this stuff makes me mad.)
People wanna look impressive without actually putting in the work to gain real knowledge. They're asking ChatGPT to write viral "expertise" knowledge posts for them, and they're publishing this slop without so much as testing it.
I know a lot of y'all lag behind on upgrading SSMS, but v22.3 just introduced something that you need to be aware of. It's going to impact any of your users who DO upgrade their SSMS, or who use Github Copilot. There's something that you can do in order to improve Copilot's code quality and make it match your preferred coding standards.
This seems like the appropriate first BrentOzar.com blog post in the year 2026, eh?
In the PollGab question queue for Office Hours, MyRobotOverlordAsks asked a question that merited a full blog post answer:
First off, I understand if you read the headline and you have a knee-jerk reaction. I totally understand that there are a lot of people out there who hate AI, and believe me, I hate most uses of it. Lots of its advice can be misleading at best, and absolute garbage at worst. However, if…
When you ask data people how they feel about AI, you get pretty rabid, extreme reactions. People either love it or hate it. Set that aside for a second, and let's zoom out and think about a bigger picture question.
What's it like to work with someone you know, versus a stranger?
You know how you put "https://" at the beginning of web site addresses, and your browser can magically talk to all kinds of web servers, all over the world? Well, the Model Context Protocol (MCP) is a standard for AI stuff to talk to other things. It's like http for AI. It's less than a…
