Engineered, Not Vibe Coded
People call coding with AI "vibe coding". Sloppy, they say. Not real engineering. I am not interested in having that debate. Whether it is good or bad in the abstract is not an interesting question to me.
What interests me is what the current advances in AI, especially coding agents, actually enable: rigorous engineering. And by rigorous I do not mean lines of code. Lines of code matter, but they are not the point. I mean being very intentional about the feature set you want, starting from a clear spec and a clear direction, and keeping things as simple as possible so you get to the core of the problem you are solving.
I have a concrete case: a few months ago I started writing VoiceToText1, and I used Claude Code to write it. It has been my daily driver ever since. Whatever we end up calling this way of working, the result is a fairly robust tool that I rely on every day. I was in the driver's seat the whole time.
Why I built my own
Before writing my own, I used Wispr Flow and then the Willow Voice subscription service. Both work fine. I have nothing against either of them functionally. But the frequent updates kept making them more clever in ways I really did not want, and the feature set never quite met my needs. So I started writing my own.
A daily driver
I use VoiceToText for far more than I expected when I started. I compose messages and emails with it. I talk to coding agents with it. I dictate blog post drafts with it.
In fact, this very post started as a dictation. I spoke my raw thoughts into VoiceToText, read the transcript, and proofread it over and over. Then I asked Claude Code to clean it up, with strict instructions: make it idiomatic, give it structure, and do not generate anything I did not say. Which is pretty much the same way I drove it to write the code in the first place.
What kind of vibe is this?
I think we have been abusing the word "vibe". It is short for vibration, from the Latin vibrare, to shake. Somewhere along the way it came to mean coding by feel: wave your hands at the model, accept whatever comes back, move on.
That is not what I did. This tool was spec'd and engineered, with me guiding every step of the way. I chose the features. I wrote the spec. I set the direction. I rejected code that did not fit the structure and the idiomatic style I wanted, and I drove the AI until it did. None of it was autopilot. I was intentional about the specs, disciplined about the structure, and disciplined about the tests.
What drives a process like that is not a vibe. It is fundamentals, solid understanding, and long years of experience. The engineer is the one driving: setting the direction and managing the entire process. Call it vibe engineering if you like. Whatever the word, the distinction that matters is who is driving.
So is it sloppy? Is it vibe coded? I do not know what those words mean anymore. What I know is that I used a coding agent to build a robust tool that meets my needs exactly, with just the features that I want and none of the distraction or cleverness that I did not ask for. That, to me, is intentional planning and engineering.
Along the way I also used OneLoop, the small coding agent I built myself2. How I used it here is a separate post, and I will write about it at some point as a way of showing how I use coding agents in real work.
Footnotes:
VoiceToText: press a hotkey, speak, and the text appears where you are typing. Overview: https://www.birkey.co/VoiceToText/, source: https://github.com/oneness/VoiceToText.
I wrote about building OneLoop and what it taught me in The Agent Is Not the Point.