Articles

When I first started coding with Claude, I thought I was teaching it how to program. Turns out, we were teaching each other how to understand. What began as an experiment in efficiency became a journey in trust — the same kind of trust we cultivate in agile teams, where clarity, curiosity, and courage matter […]

Most conversations about AI focus on productivity.How much faster can we code?How many jobs will change?How many people can one developer replace?How quickly can organizations automate work? Those are important questions, but I think they miss the deeper shift that’s happening. AI is exposing how we think. It’s exposing how we communicate, how we model

AI can now generate a non-trivial application in a single shot. That changes everything. And it raises a question many developers are quietly asking: If AI can write the code… what’s left for me? You Were Never Hired to Type Let’s start here. You were not hired for your ability to type. You were hired

There’s a reason most legacy systems feel heavy. It’s not because they’re old. It’s not because they lack patterns. It’s not even because they’re poorly tested. It’s because they lack agency. And once you learn to see that, you can’t unsee it. Why Most Legacy Code Is Procedural in Disguise I’ve reviewed thousands of systems

There’s a quiet misunderstanding spreading through our industry right now. Developers are using AI to generate code. The code compiles. The tests pass. And they think they’re done. But working code is not the same thing as well-designed code. In fact, AI has made design thinking more important than ever. ⸻ Working Code Is the

Most “legacy code” isn’t legacy because it’s old. It’s legacy because it has lost its agency. I’ve worked with millions of lines of production code over four decades, across some of the largest companies in the world. The pattern is always the same: Objects don’t manage their own state Behavior is scattered Changes ripple unpredictably

Most people are using AI like a very fast search engine. They ask for code.They ask for answers.They ask for solutions. And sometimes, that works.But if you’ve spent any time building real software—software that needs to grow, change, and survive contact with reality—you’ve probably felt that something is missing. What’s missing isn’t a better prompt.It’s design thinking. Design Isn’t

AI isn’t confused — we are. If you’ve ever typed a prompt into ChatGPT and thought, “That’s not what I meant,” you’ve met the mirror. AI amplifies whatever we give it — our thinking, our assumptions, our clarity — and it reflects them back, sometimes with stunning accuracy and sometimes in spectacular confusion. The difference

Over the last month, I’ve been building something I wish I’d had years ago—a Prompt Manager that makes working with AI faster, smarter, and more organized. If you’ve been following the YouTube series, you’ve seen it evolve from a rough concept into a functioning tool. In this post, I want to share the key takeaways

Working with AI has taught me something I never expected about programming: that clarity isn’t just logical — it’s emotional. When I’m distracted or impatient, the quality of my code, my prompts, and my thinking all decline. When I slow down, breathe, and connect to the intention behind what I’m building, AI responds in kind.