Voice of the DBA

Tag: AI

Using AI for Git Hooks
Recently I had someone internally ask about whether SQL Source Control supports Git Hooks. Since it was after UK work hours, I decided to run a quick test. One problem, I haven’t setup a Git hook in a few years.

Could AI help me? See what I did.

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

Asking for Help

Claude is my go-to AI. I don’t have a good reason why I don’t lean on Copilot or ChatGPT or anything else, but I’ve become more comfortable with how Claude works and responds to me. When I have something that doesn’t have any PII or other sensitive requests, I tend to start with the free Claude site.

Here was my prompt: what is an example of a git precommit hook

Simple, easy, no punctuation or big setup. I just needed something. I got some code:

and an explanation. Here’s the’s the text of the explanation (italics from me):

This hook:
1. Prevents commits with console.log statements
2. Catches trailing whitespace
3. Runs your linter
To set it up, save this as .git/hooks/pre-commit and make it executable with chmod +x .git/hooks/pre-commit.

If the hook exits with a non-zero status (like exit 1), the commit is aborted. You can bypass hooks temporarily with git commit --no-verify if needed.

Many teams use tools like Husky to manage hooks in a project, making them easier to share across the team since .git/hooks isn’t version-controlled by default.

This shows some bash, which I don’t think runs natively in Windows. That makes sense as a lot of coders are likely using Linux/MacOS for complex stuff and the default training for Claude likely assumes that. I asked about Windows and got two options: Node.js and Husky. Since I don’t like to install things, I went with Node. Here’s the next question I asked.

I didn’t want to lint or worry about whitespace, since I’m depending on SQL Source Control to create the files, so I asked a different question: can you create a pre-commit hook using node (for Windows) that checks for a commit message between 1 and 50 characters?

The response is good. I didn’t want this, and reading this, I realize Claude is right. I wasn’t quite thinking through the process here. I also didn’t want the code for a commit-msg hook, so I ignored the code.

I could see that I was getting generic hooks, mostly for other code, so I rephrased a prompt: I want a sample pre-commit hook for .sql files to test something, what is a good example

The response was a practical hook for SQL files. The code had a couple of messages printing our errors when I failed things, and the code here isn’t important, but here was the explanation. The bottom of the code is shown, and then the list of things that are checked.

At the top there is a comment about the hook, and since I’d done this a few years ago, I thought I know what to do, but I asked. I mean, why not ask the AI for more help? I liked that it noted not only do I need to add this to my .git folder, but I need to track this if I want to share it. That’s important. I do want other team member, or in this case, me on another machine, to have this hook.

Testing the Hook

I then went to SQL Source Control and made a change. In this case, I added a file that I knew would fail the check. Here’s my code:
```
ALTER PROCEDURE dbo.GetAllCustomers

AS

SELECT * FROM dbo.customer
```
I could see this code change in the SQL Source Control GUI, but no error. I thought this might be staged, and I somewhat assumed the hook would fire on staging, so I asked.

My new prompt: when does this hook fire?

The response let me know that I had to commit this to get the hook to fire. It runs on the commit command, as before the commit succeeds. That’s good to know. Thanks, Claude, for helping me learn something.

In checking from the CLI, I realized that SQL Source Control at this point hasn’t staged the file. It also hasn’t written the file, so there’s nothing to stage. One of the downsides (one fo the few) of SQL Source Control is very limited git configuration. The write, stage, and commit happen at once.

I tested this and sure enough, I got a failure when I tried to commit. The hook fired and saw my SELECT *, and my lack of a semi-colon.

I tested this further by fixing these elements individually, and I could correct the SELECT *, but I couldn’t fix the semi-colon. I realized with testing that when SQL Source Control writes the file, it always includes a “GO” at the end. So my hook doesn’t work.

Asking for Modification

I decided to see if Claude would fix this, as I wasn’t sure what to change myself. I’m not a Node nor RegEx person, and I’d be googling a bunch to figure this out (or find someone else’s code). Instead I tried this: can you adjust this hook to ignore the missing semi-colon if the file ends with a GO, or check for a semi-colon before the GO

The response was interesting. The explanation said this:

Now it handles both cases:
- File ends with GO: Checks that the line before GO has a semicolon
- File doesn’t end with GO: Checks that the last line has a semicolon
The relevant code is here:

I can read this and it makes some sense, but I would have struggled a bit to get this done in a reasonable time. Instead, it was seconds for Claude to produce this.

When I re-tested, this passed the SQL Source Control GUI and I had a working git hook looking for a couple of simple silly mistakes I might code.

Summary

This is an area that I have a little experience, but not a lot. I’m a junior dev when it comes to Git, and Claude is definitely more skilled. However, I have to know what to ask to get a result and I thought the answers and explanations were good in helping me setup this test in a few minutes rather than the better part of an hour (or longer) if I were searching and trying to assemble code.

This is one of those areas where AI was very useful to me. It built a fairly trivial coding item I needed, it helped explain things when I had questions, and it was helpful in adjusting code quickly when I realized I needed something else.

Imagine asking a colleague this, realizing you’d asked the wrong thing, and then asking them again for new code. How slow, and annoying, would this be for both of you? AI is a game changer here, for things that are too simple to work with a colleague on, yet complex enough that you’d waste a decent chunk of time googling.

That time savings went into me testing the code and testing SQL Source Control. I verified that SQL Source Control can work with git hooks in minutes.
January 26, 2026
Flyway Tips: AI Helps with Commit Messages

At Redgate, we’re experimenting with how AI can help developers and DBAs become better at their jobs. Everyone is asking for AI, as well as the ability to turn AI off. We’re working hard to accommodate both requests as we look for ways to leverage AI.

One of the areas we’ve started to add some AI is in Flyway Desktop (FWD), with a few features designed to help reduce the cognitive load and save time as they work with databases.

I wrote about summaries of migrations scripts and migration script naming recently. This post looks at another of those changes, which is the generation of a commit message..

I’ve been working with Flyway and Flyway Desktop for work more and more as we transition from older SSMS plugins to the standalone tool. This series looks at some tips I’ve gotten along the way.

Summarizing My Changes

Commit messages are hard. There are numerous posts on the art of writing one, as well as no shortage of examples showing poorly structured messages. As I look through my own messages in the SQL Saturday repo, I’m somewhat surprised at times at ow well I’ve described something, or how poorly. I’ve certainly had the “fix” messages creep into my work.

When we start making database changes, we often have a number of things we might touch. A new column could necessitate view and stored proc changes. One view might impact another, or a function. A piece of work might include alterations of a few tables, and fixes that might not be obvious need a bit of a description in the commit message.

If nothing else, we need to ensure we’re linking commits to planned work on Azure DevOps boards, in Jira, or wherever a project manager might be assigning tasks.

Flyway has added an AI feature to help us summarize our changes. It’s in preview as of Jan 12, 2026, and is designed to help ensure we get a better commit message than “fixed.”

Generating Commit Messages

When I go to the VCS tab in Flyway Desktop (FWD), I see all my changes listed. In this case, I’ve been demoing and testing a lot of things that I haven’t committed. Bad practice, and I’m a little upset with myself for not keeping my repo clean.

Notice the little sparkle below the Commit button? This is where the AI help lives. If I select a few files, in a few seconds I’ll get a message generated for me. This is a decent summary, at just over 50 characters.

If I don’t like this and want to edit it I can. If I do that, the AI won’t overwrite this. I’ll change the wording and select another file. Notice that the message remains the same.

If I want a new message, I can click the AI sparkle and it will regenerate this. I’ll show this in the video below.

If I select all the files, the AI summary isn’t great, but then again, I don’t know how I’d summarize all these changes. I might not do any better.

This is a small thing, but I often find that I struggle to come up with a meaningful message at times. Sometimes I do a good job and add something relevant with a work item number. Sometimes I want to just type “new table” or “fixed bug”.

This reduces some of the creativity burden when I’m working through database changes.

Enabling AI Features in Flyway

This is a preview feature as of Jan 5, 2026 as I write this. To get this in your FWD, your organization needs to have enabled AI features in your portal. I’m just a member, but whoever is an admin for your Redgate products would find it here.

In FWD, you need to look at the Preview Features item under the config menu.

In this area, you can enable or disable features as needed. I see these marked as Red-gate only, but I think they are supposed to be released to some customers by this time. It’s likely I need to upgrade my FWD, which I’ll do when I have time.

Once you do this, you should start seeing some AI stuff with the purple/pink shaded area and the sparkle icon that we’re all seeing everywhere.

Summary

Getting meaningful commit messages can be hard, but it’s also a tedious thing. I find that developers often get lazy and do the minimum. That AI might not be much better, but it does reduce the need for a user to think of a message and gives them a starting point from which to work.

To me, this is one of the better uses of AI, handling a common, but tedious task. Now to go clean up my repo and take advantage of this with a bunch of smaller commits.

This feature is documented, but we are likely to enhance and change it a bit, so all feedback is welcome. If your organization doesn’t want you using AI, and you could share some schema from a migration script, I’d be happy to test it for you and see what summary is produced and send it back to you. Ping me on X/LinkedIn/BlueSky if you want.

Flyway is an incredible way of deploying changes from one database to another, and now includes both migration-based and state-based deployments. You get the flexibility you need to control database changes in your environment. If you’ve never used it, give it a try today. It works for SQL Server, Oracle, PostgreSQL and nearly 50 other platforms.

Video Walkthrough

See a video of me looking at this feature below.

January 23, 2026
Learning From Breakage

I’ve had the fortunate, or maybe unfortunate, experience of being thrown into a few jobs with no training. At a couple of my bartending jobs, I had to start working without any training, calling over someone to help run the ordering machine while I made and served drinks. I managed to slowly learn how things worked throughout that first shift, so I was ready to work on my own the second night. I had a similar experience at a tech job, starting as the lead DBA/IT Manager in a crisis, having to try and solve problems after ask others how things were supposed to work. I ended up fixing a bit of code, adjusting networking, and directing others on my first day.

When we have a crisis, we often learn a lot from the situation. I’ve been through crashed upgrades, virus breakouts, hardware failures, and more in my career. While each was stressful and often not enjoyable, I learned a lot each time and came through the incident a more capable developer/DBA/whatever. When we work through a tough time, we are often better equipped for the next time something goes wrong.

I ran across a great piece that says you never really know a system unless you’ve broken one. This is Tim O’Brien, a software architect who has learned a lot about databases from failure. In fact, I love his interview question for data professionals: “tell me about the worst database schema you ever created. What did it teach you to avoid?” I’ve certainly learned a few things over time from my schema designs, but those are stories for another piece.

The piece draws parallels to today’s use of GenAI technology and vibe coders who seem to have success that they highlight in posts without discussing the problems. I do believe AI technology is going to make a lot of things easier (and faster) to build and then fix when they break. And they are going to break, partially because AI tech might not do a great job, and partially because we might not direct it well enough. Clear communication is key when working with AI.

I’ve started to build some skills with AI, but as I try to tackle more complex tasks or scale up my work, I realize that I often don’t know enough about either the problem or AI technology, and I’m going to make mistakes. I’m going to break things and then have to fix them, or more likely, learn how to get the AI to reduce the number of broken things in some way before I have to take over.

And learning to take over might be the number one skill with AI tech, but that’s something that you will only learn from the AI not working well for you in a variety of situations.

Steve Jones

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

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

January 21, 2026
Who’s the Winningest Coach (with AI Help)
I was listening to the radio the other day and the hosts were discussing the NFL playoffs in 2026. Someone mentioned the winningest coach was Nick Sirianni of the Philadelphia Eagles and no one wanted to face the Eagles. I was wondering if the first part of that was true. I used Claude and SQL Prompt AI to help.

Note, I enjoyed watching the Eagles lose in the first round to the 48ers. As a lifelong Cowboys fan, that was great. However, I am impressed with Jalen Hurts and was glad to see him win last year.

This is part of a series of posts on SQL Prompt. You can see all my posts on SQL Prompt under that tag. This is part of a series of experiments with AI systems.

Getting the Data

First I had to find data. I did find this page of coaching history at Pro Football Reference, which lists coaches, however, I wanted to compare the first few years of their careers, not their totals.

I decided to see if Claude could help get some data. I started with a query: This pages has a list of nfl coaches: https://www.pro-football-reference.com/coaches/

I want to loop through each coach and get the details of their career to find the team they coached and the year, returning this in a CSV that has team, year, and coach name. Can you write a python script to do this?

This kind of worked. I got a script, and it ran, but there were some errors. PFR doesn’t like scrapers and they want to protect their data. I get it.

I told the AI there was an error and it helped me get the Chrome driver and Selenium module to drive a real browser from automation. I commented out the “headless” part so that I could see it working (a bit).

This kind of worked, but not really. I got the coaching list and I could see the browser going through each coaches page, as well as the CLI output, but lots of errors. PFR does a good job of blocking this.

What was amazing is that the script in my repo is something that would have been hours of me messing with different modules and trying to debug the issues. This was literally about 30 minutes of multiple tries before I gave up for the night.

The next day I decided to give in and just grab data from some coaches that I know have won Super Bowls and had success early in their careers (sorry, Andy Reid). I went to each page and clicked the “CSV export” item and then copy/pasted the data into a file. I then asked the Copilot AI for help. Each set of data was nice, and the file was named for the coach, but the coach’s name wasn’t in there. So I let Copilot edit it.

Admittedly this wasn’t automated, but by the time I’d created a new file for a new coach, CP had cleaned up my old one. With this in mind, I had 6 coaches of data stored in CSV.

Back to Claude. No reason not to use Copilot, but I like Claude. I asked it to give me an import script.

It did, and I saved it (coachimport.py). I ran this, but it errored out. Since this was a file in my repo, I moved back to Copilot, which has access to the files. I asked it to fix the errors. This was the prompt (everything after the colon was pasted in) : I am getting this error in the script: Error importing rawdata\NickSirianni.csv: (‘42000’, ‘[42000] [Microsoft][ODBC Driver 17 for SQL Server][SQL Server]The incoming tabular data stream (TDS) remote procedure call (RPC) protocol stream is incorrect. Parameter 24 (“”): The supplied value is not a valid instance of data type float. Check the source data for invalid values. An example of an invalid value is data of numeric type with scale greater than precision. (8023) (SQLExecDirectW)’)

It started to examine the files.

Then it found a problem and started fixing things. Since this is an import and I’ll stage the data, I can let it run and check the results.

While this was running, I also used SSMS and the Flat File Import to pull in one file from the subfolder to see how well it worked. I basically, next, next, next on this, which was good enough.

In the time it took me to import 1 file, Copilot had finished and imported all the data. I could query the staging data and see all my rows. I quick check of the different files showed me all rows imported.

This was with the free Claude web tier and paid corporate Copilot account.

Now, what do we learn?

The Analysis

Since I had the data in a table, I could use SQL Prompt AI to help analyze the data. I started with a simple query:
```
SELECT coach, SUM(w) OVER (PARTITION BY coach)
FROM dbo.Coach_Staging
```
I could do more, but I’m playing with AI tech, so I then added a prompt: help me analyze this data by comparing each coaches first 5 years with wins, losses and ties and win percentage.

I got this code:
```
SELECT coach,
SUM(W) AS TotalWins,
SUM(L) AS TotalLosses,
SUM(T) AS TotalTies,
CAST(SUM(W) AS FLOAT) / NULLIF(SUM(W) + SUM(L) + SUM(T), 0) AS WinPercentage,
AVG(CAST(Rank AS FLOAT)) AS AverageRank
FROM
(
SELECT coach,
Year,
           W,
           L,
           T,
Rank,
ROW_NUMBER() OVER (PARTITION BY coach ORDER BY Year) AS YearNum
FROM dbo.Coach_Staging
) AS CoachYears
WHERE YearNum <= 5
GROUP BY coach
```
That’s about what I would have written. I was about to start adding the row_number when I thought Prompt could help me. I additionally asked for an order by and an average rank, and ended up with a query that made sense.

The takeaway for me was that I could have written the code, but in a few seconds, SQL Prompt gave me a query I could use. This was way faster than I could have written the query, even with SQL Prompt Intellisense.

The Results

Well, is Sirianni the winningest coach in his five years. Here’s what I see.

By win percentage, Don Shula is better, but there were less games, so Nick Sirianni has more wins and losses, and a slightly lower percentage, but a higher rank. I think it’s fair to say he tops the list, though it depends whether you look at wins or percentage.

It was also surprising to see Mike Tomlin, who recently left the Pittsburgh Steelers, coming in third.

An interesting analysis that went way quicker than a few I’ve done in the past. AI is incredibly helpful here, and as I think about all the similar types of queries people have asked for help with over the years, I can see how AI will be very helpful over time.

Of course, with larger data sets, you’ll want to verify the queries are working with other checks of the data, and you’ll likely want some automated tests on small sets to verify any changes to algorithms still return the correct results.

If you haven’t tried SQL Prompt, download the eval and give it a try. I think you’ll find this is one of the best tools to increase your productivity writing SQL.
January 21, 2026