I don't know how to code — I shipped a 10-language app anyway. Here are the 6 decisions.
I'm going to skip the inspiration and give you the engineering decisions, because that's what I'd want to read. Context: I'm a solo developer with no technical background. I built NameSoul, an app that generates a Chinese name for a non-Chinese speaker and then treats that name as a starting point — six style paths, a real historical figure behind each name, seal-script and calligraphy rendering,…
Instead of starting with features, I began by mapping the app's architecture. I sketched out the user journey, from input to output, then translated it onto paper. This approach prevented the need for constant refactoring later on.
Next, I realized the importance of communicating effectively with AI. My previous attempts had failed because I hadn't learned to provide clear, unambiguous instructions. I began to break down tasks into small, specific steps, treating the AI as a partner in a conversation rather than a brute force tool.
I separated aesthetics from the coding process. While AI excels at logic and structure, it struggles with visual design. By referencing specific designs I admired, I was able to guide the AI towards a look that fit my vision. I also decided to forgo excessive animations and visual polish, prioritizing a solid product over a flashy one.
The most expensive component of the app was not the code, but the dataset of historical figures. Building a verified dataset with accurate, user-friendly English descriptions took significant time and effort. This dataset served as the foundation for the app, making subsequent features run smoothly.
Localizing the app for ten languages presented its own set of challenges. It wasn't just about translating strings; each name's description and story had to be accurately translated, proofread, and checked for layout issues in each language. Proper localization planning is crucial before launch.
I rejected the idea of releasing a crude, usable version later, as I would feel embarrassed recommending such a product. Instead, I focused on choosing a few key areas where shortcuts could weaken the product, taking shortcuts elsewhere. This approach allowed me to minimize scope while maintaining a strong core.
My advice for future developers is to prioritize a clear architecture diagram, invest time in learning to communicate effectively with AI, collect visual references before expecting AI to produce designs, allocate time for data and localization, and be selective about where to apply shortcuts. My app is now live, and I'm ready to receive feedback to improve on version 1.1.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
