Imagine taking a big rock and slowly removing pieces from it until it becomes something meaningful or useful.
It is one of the new ways of coding that agents make possible. Before AI, producing code was costly, so a workflow like this was almost impossible to use.
These days, I describe what I want to build and dictate a lot of requirements. Agents generate a ton of code which should be a plausibly working solution. Now I have a rough block of code to work with. I start removing everything unnecessary until I reach the essence of the solution.
It doesn’t always work. Sometimes, I decide to start from scratch. But even then, I have learned which direction I don’t need to explore. I can also generate several versions and combine the best ideas from each one. To extend the analogy, it is like experimenting with several rocks before understanding what the end sculpture should be.
Of course, it is not the only way to code. If it works depends on the problem I am trying to solve. But I am happy to have this option in my toolbox now.