The SQL Server MCP Server

How to Work with On-Premises AI Models to Generate T-SQL Code

See how a small local model performs on some SQL tasks. This shows how Ollama can run a model on your laptop.

The Quiet Part

AI is affecting labor and employment. Steve has a few thoughts today.

Are You Working More Hours?

AI is causing some people to work more, which seems at odds with the idea of what AI should be: a useful tool.

The best AI developer tools in 2026: from coding agents to code review

AI developer tools have matured fast. In 2026, most engineering workflows touch at least one AI coding agent, code reviewer, or research assistant — but the right combination depends heavily on your team size, codebase, and tolerance for setup overhead. This guide breaks down the tools actually worth using across three categories: research and architecture, day-to-day development, and code review, based on real, hands-on experience.

Fixing P1 Queries

Steve asks if we should focus on the slowest queries or tackle other issues in our systems. Or if we should even have to make these decisions.

Building Your Own Software

AI helps with building software, but it doesn't do all the work.

A Quick Second Opinion

Communication is hard, and it's something most of us can learn to do better. Steve notes that using an LLM for tasks will also help you learn to communicate better.

I Want to Use My Brain

AI doesn't mean that Steve doesn't think. He still gets to use his brain.

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.