2026-06-26
213 reads
AI LLM Assistance
The LLM layer you’re probably missing (LLM gateway pattern explained)
The LLM gateway pattern is a thin service layer that sits between your app and large language model (LLM) providers, centralizing every AI call through a single entry point. It gives you immediate control over routing, logging, retries, fallbacks, and cost tracking – preventing the chaos of scattered integrations, unclear billing, and provider lock-in as your system scales. Learn all you need to know about the LLM gateway pattern in this article.
2026-06-19
Follow Your Hunch
One of the positives of AI is that you can try things on which you might not otherwise have time to experiment.
2026-06-17
132 reads
What Happens When You Ask a Local AI to Query Your Database?
Learn how you can run a simple LLM on your own machine with Python.
2026-06-17
4,039 reads
Liability for AI Errors
Who is liable for mistakes made when listening to AI tooling? In at least one case, Steve isn't sure.
2026-06-13
100 reads
SSMS Copilot is Messing With Your AI Prompts
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.
2026-06-10
Vibe coding and databases: the hidden risks of AI-generated database code
Explore how Andrej Karpathy’s “vibe coding” trend reached databases. Uncover risks, real incidents, and 5 critical failure patterns
2026-06-01
Stop Prompting Your AI Agent. Give It a Playbook.
Learn about how you can better prompt your AI Assistant in solving problems and producing code.
2026-05-25
4,203 reads
What Can AI Really Do?
Steve asks you what you think AI can do for you today, with a few suggestions of what he sees.
2026-05-18
151 reads
When, and when not, to use LLMs in your data pipeline
LLMs should be used in data pipelines for unstructured text, semantic search, and natural language queries – but avoided for deterministic, high-volume, or regulated tasks. Drawing on my real-world experience building large-scale ML systems, in this guide I’ll explain exactly where LLMs belong in your data pipeline and, just as importantly, where they don’t.
2026-05-15
Blogs
Measuring RAG Solutions: Are We Retrieving the Right Information?
A RAG pipeline that answers questions in the demo is not the same thing...
Advice I Like: Lots of Ideas
By Steve Jones
“A multitude of bad ideas is necessary for one good idea” – from Excellent...
Building a DBA Agent for Your SQL Server Estate with MCP
Yesterday I gave a talk for MSSQLTips called “Building a DBA Agent for Your...
Forums
How do I connect to a SQL Server database on my ISP?
I've got a web application for my side business. I've added a SQL Server...
Looking for New Blood
Comments posted to this topic are about the item Looking for New Blood
Server-Level Row Counts for Tables and Views
Comments posted to this topic are about the item Server-Level Row Counts for Tables...
Question of the Day
Hyperscale Replicas I
What types of secondary replicas are available for the Azure SQL Database Hyperscale edition?
See possible answers