Tag: AIExperiments

  • A Small LLM Fail

    Another test with Copilot in SSMS (v22 P3) that didn’t go so well. This one surprised me.

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

    Looking for Known Data with Copilot

    One of the things I wanted to do recently was do some checkdb checking of a system. As a result, I was looking for the last time this was run on a database. I decided to ask Copilot.

    2025-10_0169

    This made perfect sense, as this was a new restore, and I hadn’t run it. So I asked for the query.

    2025-10_0170

    This doesn’t work, but I’ve gotten used to pasting in errors and letting the LLM sort this out. So I did this.

    2025-10_0177

    OK better, but this still doesn’t work.

    2025-10_0178

    I apply this and run it, and it works, but doesn’t return data. I wouldn’t expect this to for this database, so I try to clue in the AI.

    2025-10_0179

    Seems wrong. On this page, DatabasePropertyEX, I see this:

    2025-10_0180

    Not sure why this doesn’t work well. I don’t see a way to change the model, so I’m not sure what’s being used or when it was trained, but I’d expect it to know what is in DatabasePropertyEX().

    Prompt AI

    Prompt AI was a little better, though not at first. I asked the question:

    2025-10_0181

    I got this:

    2025-10_0183

    I can’t select this code (submitted a bug), but this isn’t bad. The result of my next query failed as well.

    2025-10_0184

    At least I had a clue what to do. I started then with this:

    2025-10_0185

    I got the “with TableResults” added. I then asked it to modify this to find the last time DBCC CHECKDB ran. I got this:

    2025-10_0187

    Summary

    To be fair I futzed with both of these a few times. An LLM isn’t deterministic, so I got different results, but I never got the correct result from Copilot. I did get this from PromptAI at one point, which does work.

    2025-10_0188

    GenAI’s are funny beasts. You definitely need to spend some time learning how to use them.

  • Creating a Striped Backup Set with AI

    I needed to test a striped backup, so I decided to ask the AI’s for help.

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

    The Problem

    A customer wanted to know if we could handle a large striped backup set. In this case, 20 files. I didn’t want to try and do this myself because I was busy at the time, so I thought I could get the AI’s to help me.

    I started with this prompt:  for a sql server database called “Sandbox” can you generate a backup command that will stripe the backup across 32 files with “sandbox” the current date/time, and a number for the backup file name?

    Local Gemma3 LLM

    I started with a local model because I had that open. I got a result that looked OK.

    2025-10_0149

    Below this I had PowerShell code to help me:

    -- Using PowerShell (example):
    # $i = 1
    # while ($i -le 32)
    # {
    #   $filename = "D:\Backups\Sandbox\_" + REPLACE(CONVERT(VARCHAR, GETDATE(), 112), ' ', '_') + "_" + $i.ToString("D3").PadLeft(3, '0') + ".bak"
    #   # Execute the backup command:
    #   Invoke-Command -ComputerName <ServerName> -ScriptBlock {
    #       & "backup.exe" -Database "Sandbox" -BackupFile "$($filename)" -BackupType "D" -Init -Format "MEDIANAME = \"Sandbox\""
    #   }
    #   $i++
    # }

    This won’t work, proving that there isn’t enough database training in some of these small models. The model does warn me this won’t work as is.

    Claude

    Since the local model was slow, and didn’t get me what I wanted, I tried Claude. Same prompt, and I got this code, which is nice in that it handles the current date time whenever I run it.

    DECLARE @BackupPath NVARCHAR(500) = 'C:\Backups\' -- Change this to your backup directory
    DECLARE @DateTime NVARCHAR(20) = CONVERT(NVARCHAR, GETDATE(), 112) + '_' + REPLACE(CONVERT(NVARCHAR, GETDATE(), 108), ':', '')
    DECLARE @BackupCommand NVARCHAR(MAX)

    SET @BackupCommand = 'BACKUP DATABASE [Sandbox] TO '

    -- Generate 32 striped backup files
    SET @BackupCommand = @BackupCommand +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_01.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_02.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_03.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_04.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_05.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_06.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_07.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_08.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_09.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_10.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_11.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_12.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_13.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_14.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_15.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_16.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_17.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_18.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_19.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_20.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_21.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_22.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_23.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_24.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_25.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_26.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_27.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_28.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_29.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_30.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_31.bak'', ' +
         'DISK = ''' + @BackupPath + 'sandbox_' + @DateTime + '_32.bak'' ' +
         'WITH COMPRESSION, STATS = 10'

    EXEC sp_executesql @BackupCommand

    I could easily then test this by adding a SELECT and commenting out the Backup command. When I do that, I see these results.

    2025-10_0150

    Note I’ve started adding some line breaks to the results so I can check things.

    Prompt AI

    I decided to try Prompt AI as well. I started with this code:

    BACKUP DATABASE sandbox
    TO DISK = ‘sandbox_20251013_x.bak’ WITH INIT

    Then I opened Prompt AI and entered this: expand this backup command to create a striped backup of 32 files, replacing the x with a number for each file

    You can see this below:

    2025-10_0148

    This got me a quick and dirty backup test.

    2025-10_0147

    2025-10_0151

    Then we need to correct the syntax.

    2025-10_0152

    Now I have a command.

    2025-10_0153

    However, this doesn’t work as I can’t use string concatenation inside the backup command. I asked Prompt AI to generate a string for this instead (from this code) and then sp_exeutesql and got this code:

    DECLARE @DateString VARCHAR(8) = CONVERT(VARCHAR(8), GETDATE(), 112) -- Format: YYYYMMDD
    DECLARE @BackupCommand NVARCHAR(MAX)

    -- Build the backup command as a string
    SET @BackupCommand = 'BACKUP DATABASE sandbox TO '

    -- Add all backup file destinations
    SELECT @BackupCommand = @BackupCommand + CASE
                                                  WHEN LEN(@BackupCommand) > 25 THEN
                                                      ', '
                                                  ELSE
                                                      ''
                                              END + -- Add comma except for first item
         'DISK = ''sandbox_' + @DateString + '_' + CAST(number AS VARCHAR(2)) + '.bak'''
    FROM master.dbo.spt_values
    WHERE type = 'P'
           AND number
           BETWEEN 1 AND 32

    -- Add WITH INIT
    SET @BackupCommand = @BackupCommand + ' WITH INIT'

    -- Execute the dynamically built command
    --EXEC sp_executesql @BackupCommand
    SELECT @BackupCommand

    That works.

    2025-10_0155

    Summary

    Both Claude and PromptAI worked, though Claude worked well with a first prompt. I continue to like the Sonnet model and find it really helpful in saving time.

    It took me longer to write this post than generate the code in 3 places and test it. In terms of saving time, Claude would have saved me at least probably ten minutes, maybe more, as I’d spend time making decisions. With Claude, I got the code in under a minute and then needed to test it.

    Always test your code. Including your AI-generated code.

  • A Broken Copilot Query

    I was testing the new SSMS (v22 Preview 3) with Copilot and ran into an interesting issue.

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

    My Query

    I was working on something unrelated and tried this prompt, which should have saved me a few minutes from looking on MSLearn.

    2025-10_0168

    As you can see, I get a nice list of things. However, then this happened.

     

    This kept going. I gave it a minute, then opened my screen recorder (which is close to a minute) and started recording.

    After capturing this, I stopped the query. Things seem to work OK, but this is definitely something that concerns me about agents and letting them go. I don’t know if this was a stuck process, if this was consuming compute or tokens, but it was certainly an issue.

  • Prompt AI helping with Auditing

    I had a conversation with a customer asking this question: how can I tell who called a stored procedure so I can audit the action?

    I decided to see if Prompt could help me here.

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

    The Setup

    I had this code, which is a simple stored procedure. I sketched this out, but I’m looking for a function to add to my code that helps me audit the caller.

    2025-09_0128

    I opened the Prompt AI (ALT+Z) and asked the question you see in the image. I also asked to assign it to the variable, but didn’t exactly specify everything.

    2025-09_0129

    In the image below, you can see the code that changed. Prompt AI added the System_User function, which is exactly what I wanted.

    2025-09_0130

    I accepted this and then asked to change this to the user instead of the login.

    2025-09_0131

    Again, the function I wanted was added: CURRENT_USER.

    2025-09_0132

    I know what I needed, or I had an idea. However, if I wasn’t sure what function to use or if there was one, this is handy. I’m working inline, rather than going to a browser and hitting Books Online or Googling for the answer. I can keep coding or looking at my code as the AI runs.

    If I ask for an explanation, I get one, which helps me judge if this is actually the code I want.

    2025-09_0133

    If you have SQL Prompt, get Prompt AI a try by opening it with ALT+Z.

    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.

    Video Walkthrough

    I show this live in the video below.