Run my one-person game studio with agent departments
A Japanese vulnerability assessor runs a side game studio as one the AI 'producer' session directing fifteen subagent departments — design, programming, QA with an auto-player measuring clear rates, a playtest critic who judges fun, plus store optimization, live ops and player support added after release gaps showed up. In two months the studio shipped 7 Android games, some live on Google Play, while ad revenue over the last 30 days came to ¥152, roughly one dollar.
How it works
- Split the studio into departments by question, not output: spec analyst, designer, programmer, UI, QA, playtest critic
- Give feedback like 'level 3 is too easy' to the producer, which routes it: designer picks numbers, programmer implements, QA measures clear rates with an auto-player, critic plays it cold
- Human playtests the build on a real phone and approves
- After launch, add the missing post-release departments: store optimization, live ops, player support, web research and a browser operator
Why it’s worth knowing
Fifteen agent departments shipped seven games in two months — and the honest revenue line reads about one dollar.
Where it’s from
Summarized from a public post on dev.to. See the original ↗