This post is a walk-through of building a Fabric Tenant that has a private-link protected workspace with Lakehouse data, and a **non** private-link workspace with a Semantic Model and Power BI reports.
Open AI's GPT-5.2 dropped, and is available on my accounts as of this morning. Wanted to share my initial hot-take how it performs in business applications compared to older models like 5.1, 4.1, and Llama-3.1 as well as gpt-oss-20b.
In this post I'll talk through the architecture and implementation details for building a complete custom MCP tool solution using Python. Then in the accompanying video we'll create an Azure AI Foundry Agent to test the MCP Server.
AI is in its early days of adoption and platform realization. Despite the noise surrounding model benchmarks, context window sizes, and chat interfaces, the real platform shift hasn’t happened yet.
In this post we’re going to talk about GraphRag — one of the techniques we can use to add knowledge to the context of a large language model prompt. We'll go through the concepts, theory, and end with a video walk-through of a fully functional full-stack GraphRAG application.
In this video, we walk through how to build a complete end-to-end image vectorization and similarity search system using modern AI tools, multimodal LLMs, and GPU-powered infrastructure.
I watched the full Ignite Keynote so you don't have to! Here are my notes from the Ignite 2025 Opening Keynote.
Finding a great manager and a helpful mentor are important elements of building a rewarding, successful career. But the real game-changer? A sponsor.
In this deep-dive video, I’ll walk through the full workflow of LoRA fine-tuning the Phi-4-Mini-Instruct model to improve natural-language-to-SQL accuracy. The demonstration runs on an NVIDIA DGX Spark, but the methods apply to any CUDA-based environment.
