Operational Insights
Charting the cloud and AI landscape
More Than Just .NET: PowerShell Scripting in Copilot
August 1, 2026 • AI Assisted Coding
We all know that Visual Studio and Copilot are effective at building boilerplate solutions in C#, but how would it hold up writing utility scripts in PowerShell? Here's what I found, along with some suggestions for anyone looking to use PowerShell for large-scale data processing.
Token Costs: From Free-As-You-Go to Pay-As-You-Go to "Do You Really Know?"
August 1, 2026 • The AI Race
Frontier labs set AI upon us in the oddest of ways - they made it all free expecting people to pay for it later. Well, it's later! Yet are we paying the true cost for our tokens?
Azure AI Search with Phi-4 RAG (Video)
July 26, 2026 • Generative AI > RAG Pipelines
It's been a while, but I finally circled back to RAG development. I really shook it up this time - a new tool, a new model, and a different data source. Here's what I learned and the advice I have to give. At the end of the day, another job well done on the Azure platform!
Text-to-SQL: The Aggravation of Aggregates
July 23, 2026 • Generative AIHow could something so simple - in such wide use - be so difficult? How can an LLM be unable to generate dynamic SQL statements? They write code for people, after all. The answer is at the base of everything an LLM is, and is not. Allow me to explain and hopefully save you some pain.
Azure Document Intelligence: A Straightforward Standalone AI Service
July 21, 2026 • Generative AI
Deploying Microsoft's document extraction services on the Azure portal is an exceptionally straightforward process. Here are some architectural insights from my first hands-on experience with Document Intelligence.
Microsoft’s Satya Nadella Hints at an Enterprise AI Trust Problem
July 18, 2026 • The AI Race
In a surprising move, Microsoft CEO Satya Nadella shared an essay with the IT community last weekend that echoed the sentiments of previous AI leaders, such as Palantir's Alex Karp. While his essay left many on social media questioning his true motives, one thing is certain: his warnings about data risks are absolutely true.
Predicting the Future: A Distributed Multicloud AI Approach
July 14, 2026 • Generative AI > Connecting to Data
Kicking off a new project with a new mindset: Multicloud AI. In this post, I cover step 1 (completed) to find a solid solution to database integration and interoperability with a LLM and use it as an opportunity to pivot toward the future of what AI cloud architecture may look like soon.
SQL MCP for Dynamic SQL: I want my money back and I didn't even buy it
July 13, 2026 • Generative AI > Connecting to Data
Probably the worst programming technology I have ever used is the SQL MCP container. I don't even know why it exists. If you think it will mimic the power of an LLM or a SQL database, it won't. I will forge on and mix things up to find a better solution, but I hope to save someone else the trouble.
SQL MCP in Azure: Fixing the dab-config.json Mounting Trap
July 13, 2026 • Azure Compute > Azure Containers
Connecting the SQL Model Context Protocol (MCP) came with a few challenges, and at the end of the day, SQL MCP was not for me. However, that doesn't mean it's useless for everyone. If you are encountering errors with your container, it may be the dab-config.json file. This guide can help you fix it.
Azure Durable Functions vs. LLM Rate Limits: What to do When Parallel Fails
July 10, 2026 • Azure Compute > Azure Functions
Durable Functions became a handy method for running scheduled, orchestrated, in-context RAG requests to generate content, but I was not able to use one of its most beneficial features: parallel execution. Still, I didn't walk away disappointed, and I have several optimization suggestions to share.