I Tested MIG in Real-Life Azure – Did It Feel Like a Stuffed Cubicle?
TL;DR I carved one Azure H100 into virtual โcubiclesโ using MIG (Multi-Instance GPU), compared it to an A100, ran Triton inference workloads, and captured both latency and cost. The verdict – The H100 with MIG delivers better latency and consistency, while the A100 is more cost-effective at scale, depending on your workload. CoโWorking Meets the […]
I Tested the Limits of Azure OpenAI Safety – Hereโs What Happened
TL;DR I ran a mini-red-team exercise against Azure OpenAI, testing common jailbreak tactics and prompt engineering attacks. Microsoft Defender for Cloud caught nearly everything. The key? A feature called User Prompt Evidence that turned vague alerts into precise, real-time context. If you’re running AI workloads in Azure and havenโt turned this on yet, youโre playing […]
Mastering Azure AI Search: A Step-by-Step Guide to Your First POC
Azure AI Search transforms unstructured data into actionable insights, making it ideal for enterprise search, knowledge mining, or customer-facing applications. This guide offers a step-by-step approach to building your first POCโfrom setting up resources and defining KPIs to deploying a functional application. Youโll learn core POC components, how to organize datasets, enhance search with Azure […]
Medallion Lakehouse Architecture in Microsoft Fabric
When managing data in the Azure Cloud, data extraction, transformation, and governance are the core of any organization’s data management strategy. Microsoft Fabric, combined with the Medallion Architecture design pattern, allows organizations to leverage the power of Azure to meet their goals by delivering reliable, governed data for business use and reporting. In this blog, […]
