Voice of the DBA

Category: Editorial

  • Cognitive Coverage

    Satya Nadella talked about cognitive coverage in the age of AI, about being able to understand and manage AI agents to get work done as a software developer. The interview from Hard Fork Live covers the future of work and comfort in this new age. This reminds me of a book that the CEO of Redgate recommended, Reshuffle. I love the book, but it’s slow reading as I constantly stop and think.

    Work is changing; it’s becoming unbundled and re-bundled in different ways, and many of us will have to learn to work in new ways. Not all of us, but many of us. Some might see their day-to-day efforts change little; some will not recognize their job a year from now. As with anything, lots of us will be in the middle with some changes, some status quo. That’s certainly where I am with AI assistance.
    The short version of what Satya says is that there is new glue work coming to software engineers. To me, this is where we re-bundle the work that needs to be done: there is work completed by us, results from AI LLMs, and the glue that puts that stuff together. The glue is managing, organizing, deciding, and probably a few other xxx’ings in there. It’s also about understanding what’s happening across all the work you are responsible for completing.

    That understanding is the cognitive coverage. I like that term as it implies that I need to know the sum total of what’s happening from my team, both humans and AI agents. I can grok the way the river of work is flowing.

    And it’s flowing. It’s not stopping. It might be getting wider. I can lightly influence it, but if I don’t keep an eye on things, it might go in directions I don’t expect and even overflow its banks.

    The hosts noted that most people want to know their jobs won’t change or how they will change. That’s one of the big things with AI that’s disruptive and scary. With a machine able to learn and adjust in ways that are more flexible than ever in the past, we have to be adaptable as well. We have to learn to work with this flexible, non-deterministic, eerily human-like technology. It’s a scary and unnerving thing for many of us.

    AI is definitely changing the world. It’s not magic; it’s not going to automatically get rid of all, or maybe not many, humans, but it is going to change the demands placed upon them. Getting a grasp of your cognitive coverage of what AI does is going to be important.

    Steve Jones

    Listen to the podcast at Libsyn, Spotify, or iTunes.

    Note, podcasts are only available for a limited time online.

  • SQL Server Still Wins

    Is it worth continuing to run SQL Server when PostgreSQL licensing is zero? Rebecca Lewis has a well written post on why that looks at some of the pros and cons of paying for SQL Server instead of moving to PostgreSQL. She starts with some of the things PostgreSQL does well, of which I think the Extensibility is really cool. SQL Server has some of this in CLR and the non-SQL language support, but those seem kludgy and complex to me. They aren’t really integrated into the SQL Server platform.

    They’re good, but I do wish vendors or the community could add some extensions in a way PostgreSQL does. Of course, I also worry about stability, so maybe this is a wish that isn’t really a great idea.

    The pros list for SQL Server is quite a good list, at least for existing users. Tooling isn’t close, both for DBAs and developers, and inside the platform. At Redgate, we support both SQL Server and PostgreSQL with Redgate Monitor, and there is so much more information that we can gather from SQL Server on what’s happening. It’s truly amazing when I compare them. We constantly are looking to add to our PostgreSQL monitoring solution and ensure admins see as close a view in PostgreSQL as SQL Server, but the reality is so much information is available.

    On the dev tool side, while SSMS can be slow, it’s still way better than any other database development tools I’ve seen.

    The innovation argument for SQL Server over PostgreSQL isn’t a great one, as PostgreSQL continues to evolve, but I’m glad Microsoft continues to work on the engine. I wasn’t enamored with SQL Server 2022, but I do like 2025 and look forward to what comes in 2028 (my guess). What I really wish, however, is that Microsoft marketed SQL Server more, with a little less Fabric in the way.

    That being said, I am continually grateful for the SQL Server marketing team’s support of SQL Saturday/Day of Data events.

    It is interesting to think that the Microsoft-stack gravity is Rebecca’s third argument. It certainly makes a lot of work convenient if you use Microsoft tools, and I completely agree that ripping this out is a major reason why people stick with SQL Server. Across the last 5-6 years, I’ve had many customers tell me they’re moving to PostgreSQL and abandoning SQL Server. They constantly ask Redgate for more PostgreSQL tools (and we’ve built some), but the reality is that a year, or two, or three later, they still have those ambitious plans. They haven’t moved.

    It’s really, really hard to change database platforms.

    That might not seem like a pro, but it is a reason why SQL Server still wins in many organizations. It’s comfortable, effective, performs well under a variety of situations, and quite frankly, there are millions of people who are more comfortable with it than many other platforms.

    I like other platforms, but I love SQL Server. It’s been good for my career and I look forward to spending the next 10-15 years continuing to help others get the most out of their installations.

    Steve Jones

    Listen to the podcast at Libsyn, Spotify, or iTunes.

    Note, podcasts are only available for a limited time online.

  • Is Fabric a Reliable Service or a Ripped Resource?

    Over the last few weeks, I’ve noticed a few complaints from different friends and customers about issues with Microsoft’s Fabric service. I had assumed these were isolated incidents in just a few places, and customers were being refunded according to an SLA. Then I saw Joey D’Antoni’s post this week about Fabric going down. It lists quite a few of the incidents in June, including a few global ones.

    However, the most surprising thing in the post was this link, noting Fabric doesn’t have a dedicated SLA. Instead, it’s under the general Microsoft support agreement, meaning your organization needs to have a support plan to get help. I think that makes some sense, but I’d really expect that a data service in the cloud, including an analytic service that touts itself as real-time, would have a high SLA. Some agreement on the order of 4 9s at least, if not 5.

    For those of you who think you can do better on premises, I’ll remind you that four 9s mean you get 52 minutes of downtime a year, or 1 minute a week (roughly). Five 9s is 5 minutes a year, and the weekly calculation doesn’t matter. I’ve had systems run for a year, but a lot, and not a lot of databases, especially with patching 6 times a year. This year, with AI (my guess) finding lots of holes and GDR releasing quite often, I would guess that three nines is out the window for most SQL Server systems that aren’t HA clustered in some way.

    As a point of reference, Denny notes that Azure SQL database, Business Critical, has a four-and-a-half 9s level of reliability and financial refunds for costs if that’s exceeded. You will need some sort of business insurance if you worry about revenue issues, but my guess is that most of us live with the downtime and work around it (and hopefully, plan for it).

    I’ve been skeptical of Fabric (outside of Power BI). It feels cobbled together, so many issues are reported, and I feel like it’s immature. If I were working on a new analytics project, and we didn’t have a solution, I might PoC it, but I’d be more likely to consider Databricks, Snowflake, or Redshift rather than Fabric.

    Perhaps you have a different view, or you have had success with Fabric. I know some people who have, but it seems one-sey two-sey and not commonplace. There seem to be so many workarounds and issues; it makes me skeptical that Fabric is really ready for primetime if Microsoft won’t stand behind it. Databricks only gives credit up to three 9s, but if they fall below 95%, they issue a 100% credit. Snowflake offers four 9s.

    I feel that if Microsoft were confident in their reliability, they’d offer refunds if they didn’t perform.

    Steve Jones

  • I Want to Use My Brain

    I had a very interesting conversation recently with a longtime DBA who was worried about using AI in their database work. The Redgate State of the Database Landscape 2026 report showed that the vast majority of you (99%) are getting value from AI, so clearly it’s being used. However, this individual was concerned that using AI for tasks would not engage their brain, and they might lose some of their SQL skills.

    And they want to use their brain at work.

    I would hope most of you want to use your brains and accomplish things. That’s a lot of the reason I continue to work and enjoy what I do. It engages me, and I find the challenge of solving problems to be interesting work. Whether that’s simple T-SQL queries, architecture for an application, or the culture challenges of changing teams. It’s exciting to move anything forward.

    I would hope most people want to use their brains at work and not just get through the day without straining their mental faculties. It’s fun to solve a problem, puzzle, or challenge. The thing I’ve learned is that AI doesn’t preclude that.

    I use AI to tackle tedious things. Small things. Minute-saving things. The number of times I use an AI to do something that saves me minutes is surprising. Those minutes add up across the week and let me avoid some of the tedious work and focus on the things I enjoy: deciding if something works and if it is the appropriate solution.

    I might ask an LLM to generate some code, summarize some text, or give me a first draft. I might use a lot of what I get, or just a little. I might throw everything away and do it myself, but often that little kickstart gets me moving quicker than I might otherwise get started, and it’s lower stress for me when I’m on a deadline.

    I enjoy PowerShell, but sometimes the tedium of getting the syntax right and formatting things is annoying. Scaffolding around an algorithm can be a pain. An AI can do a lot of that stuff and I can evaluate the result. I never type > instead of -gt anymore because the LLM does it. I decide if I like the approach or not, or if I want to write a little code inside the scaffolding.

    I still use my brain. AI hasn’t changed that. It’s just that I avoid some of the tedious things. And if I need a break, I can go for a walk or cook or play guitar rather than slogging through a chore that isn’t interesting.

    Steve Jones

    Listen to the podcast at Libsyn, Spotify, or iTunes.

    Note, podcasts are only available for a limited time online.