#Programming Blog

Intent is becoming a first-class artifact

ai software productivity

In practical terms the big thing that changed is this: plausible code is now basically free. Getting from a vague thought to something that looks like software is dramatically easier than it was. That does not mean building good software is suddenly easy. But it does change what actually matters.

A weird consequence is that the explanation of what you actually want starts to matter more. If code can be regenerated quickly, then more of the value shifts into direction. What problem is actually worth solving? Which tradeoff matters? What kind of change should even exist in the first place, really?

That changes the old “ideas are cheap, implementation is hard” line a bit. Implementation is still hard where it counts. But exploring possible implementations is cheap enough now that good ideas and clear intent are at a premium. Judgment. Taste. Choosing the right direction before you pour concrete on the wrong one. In a single word: ideation.

This really matters because AI can dump a huge pile of possibilities on the table. Variants, reframings, implementations, endless plausible directions. It is very easy to spend lots of time and tokens chasing down the wrong rabbit holes. The scarce thing is no longer producing options. The scarce thing is deciding which option is actually worth taking given the constraints of the real system.

Someone without much domain understanding can now put together something plausible very quickly. Sometimes it even looks good for a while. But plausible isn’t the same thing as right. And it is definitely not the same thing as trusted. What is really valuable now is being able to say: this is the direction that fits the problem, these are the principles we abide by and this is the version of the idea worth betting on.

When intent is explicit, review gets easier. Future humans have a better chance of understanding why the system behaves the way it does. Agents have something more stable to work from than a one-off chat. And teams get a cleaner way to separate shiny generated output from code they actually use.

The real value is not the trajectory of prompts. It is the path from intent to proven code.

Clear intent becomes a first-class artifact.