“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…
Recently, I was creating an agent with the goal to identify potential incidents in Teams community of practice channels. I started building this agent to find problems such as “I need help” and create ServiceNow incidents from its information. Testing it meant feeding realistic support cases into the system. But here’s the problem: real support data contains sensitive information. Project names. Client issues. Internal struggles. You can’t demo that publicly. You can’t even use it safely in testing. This isn’t…
Recently I stumbled into an issue with my GitHub Copilot coding agent. Yes, correctly — I reached the premium request limit in my Visual Studio Code. And everybody knows, a throttling to an old LLM feels like driving an old timer. I’d been deep in spec-driven development using GitHub’s Spec Kit. This toolkit lets AI agents generate implementations from specifications. It helps you build high-quality software faster. Powerful. Efficient. Game-changing. But when you hit that limit? Everything changes. GitHub Copilot throttles…
Ever had a critical workflow break at the worst possible moment? Picture this: an approval is stuck. A notification never arrives. The business is already waiting. And somewhere in the background, a workflow has silently failed. I’ve been there. You know something’s wrong, but finding the root cause feels like searching for a needle in a haystack. Logs are scattered. Errors are cryptic. And every minute of investigation adds more pressure. That’s when I decided I needed more than alerts…
What if workflow failures weren’t noise – but tasks waiting to be structured?
My new post walks through how I built an AgentOps system where Teams, agents, and humans work side by side.
Clear tasks. Less chaos. More control.