The idea of prompt engineering is to verbalize the required application structure for the AI. Sometimes it feels that a faster way to solve problems is only reacting to the situation and producing a solution. Choosing to verbalize is often an attempt to make the structure explicit, maybe using some set of methods like computational thinking. I was recently working with data quality, and wanted to visualize a nested document in a certain way. It’s challenging to communicate it to AI. Extrapolating the situation further, how does a person with perfect programming skills and guided by rich imagination compare to AI assisted development? How large the hierarchies of known solutions are and how well do they cover all cases? Maybe we will see lots of lucky coincidences.
