I am an independent developer who has shipped three iOS apps with the help of AI. The results are not a polished success story: one paid app generated $37.18 in roughly two months, another took about three months to build and earned only ¥3 from ads, and my multilingual party-game collection Wacha! reached 12 downloads on its first day.
Those first two apps do not support multiple languages, so I am not linking them here as recommendations for international readers. They still matter to this story because they taught me that finishing a product, monetizing it, and helping people discover it are three separate challenges.
What is Wacha!?
Wacha! is a free iPhone party-game collection for 2–8 players. It combines social deduction, quizzes, cards, word games, and action games, with both local and online play. The app supports Japanese, English, and Korean.
Players join a six-digit room, pick a game, and keep playing together without creating an account. Messages and visual stamps remain available in the lobby and during games.
AI was part of the entire workflow
I used AI for more than code:
- Reading an expanding Swift codebase
- Implementing and debugging game rules
- Generating visual assets
- Translating the interface
- Preparing App Store review notes
- Writing outreach copy
- Building and updating the product website
I have also used Claude Code and Cursor professionally. For this personal workflow, Codex has been the best fit for me—not as a universal benchmark, but because it can connect long natural-language requirements, source analysis, image generation, and visual feedback from screenshots in one continuous context.
Developing away from the desk
I sometimes leave my Mac running at home and work remotely while I am away. I send concrete tasks to Codex for implementation, review preparation, localization, and promotion. AI keeps production moving, while product decisions, testing, and responsibility for the release remain mine.
What the small numbers taught me
The biggest lesson was that building and distribution are different jobs. AI can dramatically increase the amount one person can create, but it does not automatically create an audience. Instead of hiding the small numbers, I use them to decide what to improve next.
I am continuing to add games, improve multiplayer behavior, and make it easier for groups to start playing immediately.
Disclosure: I am the developer of Wacha!.
Top comments (0)