I’ve been working on data apps recently. The idea is to pick a data source X, and create an app that captures the basic analytic functions that you want to run on it. What it means in practice is having a data model, data imports and exports, some automated analytics, reports, and a graphical user interface on top of these.
This type of cases feel good fit with AI assisted programming. There’s always domain specific software that does something like this, there’s general analytics software, and there’s advanced libraries like Pandas. None of these can match the agility of a quickly generated analytics app tailored for the case at hand. Pandas coupled with some other libraries obviously coming close but you still need to remember the APIs, and mostly do the work listed above anyways.
One example is a windowed chess analytics app that can be used to analyze game PGNs using open source chess engines, search for games and positions with interesting and possibly complex features, and report and visualize the results. How far are we really from it being possible to prompt engineer the whole app using low cost AI, knowing nothing on programming?