“Knowing that Azure changed is useful. Knowing that Azure is currently having a bad day — and getting that information to the right people — is operationally necessary.” In my last CloudLens article, From RSS Scraper to MCP-Powered Radar, I wrote about how the project evolved from a slightly overconfident RSS scraper into a proper Azure… Continue reading From Radar to Response: How CloudLens Learned to Deliver Azure Service Health into Teams
Category: ai
Building a Serverless AI Agent on Azure Functions – with Nothing but a Markdown File
A hands-on walkthrough of the Azure Functions serverless agents runtime (public preview, announced at Microsoft Build 2026). We build a tiny "Cloud Study Buddy" agent, deploy it to a real Azure subscription with azd, and test it end to end — documenting every command, every gotcha, and every fix along the way. What was announced, and why it matters… Continue reading Building a Serverless AI Agent on Azure Functions – with Nothing but a Markdown File
From RSS Scraper to MCP-Powered Radar: How AzRadar Grew Up
"Never be blindsided by an Azure change again." A quick recap (a.k.a. the embarrassing prequel) Back in September 2024 I shared a humble little proof-of-concept: an Azure Container Instance that read the Azure Updates RSS feed, asked GPT-4o to make sense of it, and dropped the result into a Storage Account. It was honest work. It also looked… Continue reading From RSS Scraper to MCP-Powered Radar: How AzRadar Grew Up
Building a CLI for Dynamics 365 CRM — And Turning It Into an AI Agent Skill
How I built a command-line interface for Dynamics 365 CRM, tackled enterprise authentication without a custom app registration, and unlocked a powerful new pattern: using the CLI as a skill inside AI agents like GitHub Copilot, Claude, and others. Why a CLI for Dynamics 365? If you've ever worked with a large-scale CRM system —… Continue reading Building a CLI for Dynamics 365 CRM — And Turning It Into an AI Agent Skill
Reverse Engineering 