Voice of the DBA

Tag: AI

  • AI Helps Me with My Sloppiness

    I type fairly well. Well, I type fast, but I do wear out a backspace key relatively quickly on most keyboards. That and a space bar.

    AI helps me deal with my issues in a way that I really like. This post looks at a small thing that I appreciate, and it’s why I wish I had a small local model running for more software.

    This is part of a series of experiments with AI systems.

    Searching for Posts

    Today I was searching for some posts. I typed in something and found nothing.

    2026-06_0178

    Clearly, I mistyped something, but before I fixed this, I alt-tab’d over to Claude and tried a similar query. It worked much, much better.

    2026-06_0180

    Not perfect, as the search (corrected) on my site shows more posts.

    2026-06_0179

    In this case, what I really wish was that this search box (and lots of other software), were running a small model, not an LLM, but a SLM, that would interpret my poor typing and do what I want. Or ask me and remember what dumb mistakes I make all the time.

    If an AI were powering the search, it would guess I mean “Monday” not “moday” and just run the appropriate search, get me all the results, and help me smooth out my day. Instead, I burned a few seconds looking at this, getting my brain to decode what search thing I’d mis-typed, and broke my concentration. I was thinking of a subject and had to change context to figuring out a search typo.

    Not a big interruption, but an interruption nevertheless.

    I typo things all the time. Git constantly asks me if “git stauts” is really “git status”, but it doesn’t just run that. I should re-enable autocorrect, but who has the time. Maybe I’ll ask Copilot to do that.

    In any case, the sloppy mistakes, the implied context, these are things humans deal with well. We can overlook typos and even understand things that don’t look like words. I bet many of you know what this says.

    “According to a researche [sic] at Cambridge University, it doesn’t matter in what order the letters in a word are, the only importent [sic] thing is that the first and last letter be at the right place.” – science alert

    For most of my life, computers required being more exact, which was a struggle for many people. Search, led by Google, has helped, but it isn’t as good as an LLM, nor does this help in many pieces of software.

    To me, this is one place a local LLM, watching what you type and doing a much better job than phone autocorrect, in all the place I type. That’s what Copilot should do. Fix my typing in software, in the CLI, and other places. Learn what I do and help me.

    Right now, Copilot is not something I like, but I see AI potential for the future if they try to make it work well, and not just stuff it in there.

    FYI, #@$#$#@$ Copilot didn’t do the work for me.

    2026-06_0190

  • 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.

  • Follow Your Hunch

    For a while, I kept seeing that the cost of writing code was approaching zero. So many people felt that with an AI LLM, the costs would go way down to produce software. I’m not sure that’s true. In fact, some companies are finding they spend more on AI tokens than salaries.

    However, the ability to produce more code, experiment with ideas, or generate proof of concepts has gone up. Whether it’s worth the cost or not depends on the engineer, but some organizations are finding that they can try more things than they would ever had time to try in the past. The time of engineers was the constraint, and if you can afford the cost, AI LLMs can relieve that time pressure.

    Maybe the ability to get more done with agents means you should follow one of your hunches in software. Maybe you should try something.

    Be thoughtful in your approach, use the LLM wisely, and learn to guide it efficiently, but use it to try an experiment that you might not think you have time to explore. Try an alternative. Implement something in a new way. OR implement it yourself and set the AI loose, asking it to work in a different way. You certainly could tell the LLM not to use your approach and try something different.

    To me, the big advantage of an AI agent is it gives me time, something that I see as the most impactful constraint in my life. I’d like to get more done, but I’m not willing to work a lot more. Using an AI agent with a measured approach lets me tackle things that I might not otherwise get done. Certainly not as quickly as I get them done, and certainly not without stealing some personal time.

    I get more done at work, without working more. I’m not working less, but I’m more effective. That’s what I’ve always aimed to do.

    Steve Jones

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

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

  • The Slow Growing Problems

    Both as a DBA and developer, I’ve had plenty of immediate, this-is-broken, fix-it-quickly issues. Usually, I, or someone else, wrote some bad code and somehow got it deployed. I mean, I do test things, and I would (probably) never change code after I’d tested it to fix that one little annoying thing, like the formatting. I’d (almost) never do that, and I’m sure you wouldn’t either.

    Yet somehow bugs slip in at times.

    Those are the acute issues, and they can be hard to fix at times, but often we can reproduce the problem in development and build a fix. Sometimes we even spot the issue quickly and just fix it in production. I’m sure you never do that, but I have had that experience myself a few times.

    However, in the database world, we can have other, slow-growing problems. I saw this post from Jacob Sebastian about production issues that don’t trigger alarms. There are just slowdowns that trickle across multiple systems and cause issues for clients. These aren’t things you instrument for, as a slowdown isn’t necessarily an issue. These things can resolve themselves, or they can develop into a major issue.

    I think about this like vehicle traffic. A minor fender bender on a highway might not be a problem, but it can become one. Cars don’t get out of traffic quickly enough, or traffic police don’t arrive soon and move the cars. Traffic starts to back up, which slows down the response, including that important tow truck that might keep things moving. Suddenly, it’s not a few people inconvenienced by an accident, but thousands.

    There are likely signals in your environment that would let you know about a potential issue coming soon. These are subtle and not always indicative of a problem individually, but taken together, they indicate a production issue is going to occur. To me, this is a place AI can eagerly be taught to look for these signals and then happily keep looking for them every day.

    The future of monitoring is the active examination of correlated data that precede an issue, hopefully giving humans, or other AIs, enough time to respond and prevent customers from experiencing a slowdown.

    I’d certainly welcome this in both traffic motorways and database systems.

    Steve Jones

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

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