I ended my last post “Spec-Driven Development: When the Spec Is Too Big” with a promise: “My next post covers what happens when I restart with Dataverse-first.” Here it is. But Dataverse-first is harder to put into a spec than it sounds. I wanted AI to develop my optimal data model and not to dictate it upfront. The trick was giving GitHub 🌱 SpecKit the right bigger picture first. Describe the full problem. Steer toward the data layer. Then strengthen…
I had a spec, I had GitHub Copilot Pro+! A new billing period with fresh credits has begun. So I started to refurbish my Expense Management system. In detail, I was building with a fresh spec that should rebuild the whole system in one run. And yes, that was the problem. Everything looked good. Copilot credits were melting away during implementation. Some hours later I had my first results. The Azure portal showed me what was there. Content Understanding analyzers:…
Most developers I know have been here. They type a detailed prompt into their AI agent. The output looks right. They run it, tweak a detail, run it again – and somewhere around the third attempt, the whole thing has quietly shifted into something else. The problem is not the AI. The problem is the approach. Spec-driven development changes that. Before a single file gets created, you define intent. You build a shared understanding for your business stakeholders, your architect,…
I haven’t written a line of code since January. Not because I couldn’t. I stopped because spec-driven development showed me I was spending time on the wrong part of the job. Today, it is easy to type “build me XYZ” and get code in seconds. I did that too. Sometimes the result looked great. Then I ran the same prompt again and got something different. Logic shifted. Edge cases disappeared. The output stopped being predictable. The turning point came when…
“The dangerous part starts when people try to build one agent for everything. Then you don’t have automation anymore – you have a very polite chaos machine.” Fellow MVP and friend Marcel Lehmann commented that on my last post. And yes – he was describing exactly what I had built at first. Until I started to split my agents and recombine them again with a new feature. This is the final part of my Teams ITSM Copilot series. You’ve seen…
Your Teams channel is busy. Messages come in constantly – questions, announcements, status updates, and a well known “I have a quick question…” that turns into a long thread. But how do you know which ones are actually incidents? In my previous post, I introduced a multi-agent ITSM system built with Copilot Studio. One agent qualifies incidents, another tracks them in ServiceNow. But before any of that happens, someone needs to watch the channels. That’s the job of the Incident…
Who doesn’t know such calls for help? “Can someone help me with Databricks? I can’t access my S3 bucket. Getting permission denied errors.” Just another Teams message. Another problem solved in minutes through quick collaboration. No ticket created. Then came the memo. Management wanted to shut down all support channels. Force everyone to use ServiceNow, our ITSM (IT Service Management) platform for tracking IT incidents and requests. Make compliance mandatory through restriction. I knew this would backfire. From my perspective, banning Teams…
I was deep into spec-driven development with GitHub’s Spec Kit. Writing detailed specifications. Describing what I wanted AI agents to build. And I was typing. A lot. My fingers became the bottleneck. Then I thought: why am I typing when I could be talking? I opened Copilot Chat and looked for a microphone. Nothing. Turns out there’s a small extension you need: “VS Code Speech for Copilot.” I installed it and the microphone appeared. But then I discovered something better. The…
What if you could build a PCF control without writing most of the code yourself? I just tried vibe coding with GitHub Copilot – describing what I want and reviewing its solutions. My goal: A JSON viewer for Power Apps that works in both Canvas and Model-Driven Apps. Back in 2020, I built the PCF-MarkDown Viewer. Let me tell you, that was an adventure. Installing the Power Platform CLI, wrestling with XML manifest files, configuring TypeScript, debugging webpack builds. Hours…
Recently I stumbled upon a question that kept nagging me: How can I get unified workflow metadata? This came up while I was working on my demo for the blog post Lightweight Workflow Monitoring. In that demo, I reused my Try-Catch-Finally pattern originally developed for Power Automate Flows. I applied this pattern to an Azure Logic App. So far, so good. But then I hit an unexpected twist. In Power Automate, I rely heavily on the workflow() expression to access…