AI on Tim Schaeps

My GitHub Copilot Journey - Part 7: Fixing a Big Issue (and What It Means)

Thu, 30 Apr 2026 18:30:00 +0200

Today I had a deployment that was working yesterday. Today it wasn't. What followed was one of those debugging sessions that perfectly illustrates both the power and the economics of working with GitHub Copilot.

If you've been following this series (starting with Part 1: The First Ask ), you know the progression: from quick questions, to deep conversations, to infrastructure automation, to multi-agent squads. This post is about what happens when that infrastructure fights back — and how the tool helps you win. (And then, in a beautifully meta moment, I asked the tool to calculate its own cost. More on that later. 😊)

My GitHub Copilot Journey - Part 6: The Squad

Mon, 27 Apr 2026 23:00:00 +0200

In Part 5 , I described the compound effect — what happens when trust, depth, breadth, and infrastructure all stack up. I thought that was the end of the story. It wasn't.

Somewhere around week seven, I stopped talking to one Copilot. I started assembling squads. (I realize that sounds dramatic — but bear with me, it'll make sense in a moment 😊.)

This is the part of the journey where GitHub Copilot stopped being a tool I used and became a system I orchestrated. Where I went from having one conversation at a time to coordinating multiple specialized agents working in parallel. And where I started thinking about how to bring this capability to an entire team — not just myself.

My GitHub Copilot Journey - Part 5: The Compound Effect

Mon, 27 Apr 2026 22:40:00 +0200

Two months ago, I asked an AI to explain an error message. Last week, I built a complete web application — frontend, backend, authentication, infrastructure, CI/CD pipeline, monitoring dashboards — in a single afternoon session of 122 exchanges.

This is the final part of the series (well, almost — more on that in a moment). Not because the journey is over, but because the foundation is set. In Part 1 I built the reflex. In Part 2 I went deep. In Part 3 I went wide. In Part 4 I started automating the systems around my work. Part 5 is about what happens when all of those layers compound. (And yes, there's a Part 6 — because the story didn't end where I expected.)

My GitHub Copilot Journey - Part 4: The Infrastructure Leap

Mon, 27 Apr 2026 22:30:00 +0200

Eight weeks ago, I accidentally committed a secret to a public repository. Last week, I was designing authentication architectures with managed identities and federated credentials. Same person. Same tool. Completely different confidence level.

This post is about the most transformative phase of my journey: when I stopped using AI for code and content, and started using it for infrastructure, deployment, and DevOps. To me, this is where the productivity gains went from impressive to structural. (I won't pretend the learning curve was smooth — there were definitely some embarrassing moments along the way.)

My GitHub Copilot Journey - Part 3: Beyond Code

Mon, 27 Apr 2026 22:20:00 +0200

I hired a coding assistant. Then I realized it's not a coding assistant. It's a thinking assistant that happens to be really good at code.

In Part 1 I built the reflex. In Part 2 I learned to go deep. Part 3 is about going wide — and to me, this is where things got really interesting.

The category explosion

Looking back at my usage patterns, something happened around week 4. My sessions, which had been almost entirely about code, started fragmenting into wildly different categories (I honestly didn't plan this, it just sort of happened):

My GitHub Copilot Journey - Part 2: The Long Conversation

Mon, 27 Apr 2026 22:10:00 +0200

Most people use AI like a search engine: one question, one answer, done. To me, the real power unlocks when you keep going.

In Part 1 , I described the reflex shift — replacing Google with a direct question. That's stage one. Stage two is what happens when you stop leaving after the first answer. And honestly, I discovered this almost by accident.

The accidental deep dive

It started by accident. I needed to prepare a workshop on a topic I partially understood (I won't pretend I was an expert — I knew just enough to be dangerous). Usually that means: read five articles, outline on paper, restructure three times, fill in the gaps, and hope the narrative holds.

My GitHub Copilot Journey - Part 1: The First Ask

Mon, 27 Apr 2026 22:00:00 +0200

I spent 20 minutes googling an error message. Then I asked an AI, got the answer in 8 seconds, and spent the next 10 minutes wondering why I hadn't done that sooner.

To me, this is a story about trust. Not the blind kind — the calibrated kind. The kind you build one correct answer at a time, and that honestly takes a bit of patience (but it's worth it, I promise 😊).