The thing I'm building, App Store Analyzer, is a website that does one thing: it reads an iOS niche and writes a deep market analysis for indie devs. For a long time that analysis had one brain — and it spoke German.
That made sense at the start. German is my home market and my own language, so I built the analysis logic in German first. I could actually feel whether the output was good or garbage, section by section, because I was reading it in the language I think in. It got deep. Reliable. I trusted it.
Then it started to hurt.
Every time I wanted the analysis in another language, I was basically running the whole expensive thinking step again from scratch. German code, German slugs, German routes, German everything — and a goal of serving 14 languages. The whole thing fought itself.
So I rebuilt the brain in English. Not "translated the code" — rebuilt the canonical brain so English is the one source of truth. Now the engine thinks once in native English, and that single analysis gets translated and cached into 13 other languages. Generate once, translate many.
It was not a clean ride.
The lows. A refactor left a pile of undefined names and quietly 500'd my detail pages — live, in production, while I thought everything was fine. I misread a normal cache warm-up window as a dead backend more than once and "fixed" things that were never broken. I spent an embarrassing stretch hammering an endpoint with a wrong key, watching 403 scroll by, before realizing my terminal had eaten the line that set the key. Small things. Hours each.
The highs. Two of them I didn't expect:
It got cheaper, not just cleaner. I'm not paying for a full deep analysis per language anymore — one real generation, then lightweight translations. For a solo dev watching every API cent, that's the whole game.
And the English brain was actually sharper. I ran the old German output against the new English one side by side, fully expecting English to be the weaker copy. It wasn't. In a few sections it was tighter and clearer than the original. The German one stays native too — home market, my voice — but English is now the spine everything hangs off.
I'm not going to pretend I planned this cleanly. This is my first real project and I'm building it with AI as my pair, learning the architecture as I trip over it. The "one canonical language, translate outward" idea is obvious in hindsight. It was not obvious at 11pm three deploys deep with production throwing 500s.
If you're building something solo and multilingual: pick your canonical brain early. Future-you will thank present-you.
Building in public — would love to hear how others handle the multi-language cost problem. 🌍
Top comments (0)