I love board games — especially the kind you can play without leaving home. You just call your friends, drop a link, and you're playing in minutes. At some point, I caught myself wondering: how realistic is it to build a complete game almost entirely with AI? Not a prototype, but something actually playable. I decided to find out.
Three days later, I had a working browser-based board game: rooms, multiplayer, bots, chat, full game sessions.
But the most interesting thing turned out to have nothing to do with AI writing code.
What's the Game?
The game is called "Growing City" (Растущий город). It's an economic board game about developing your own city. Each turn, players roll a die, buildings activate, income flows in, and you earn money to buy new structures. Gradually you build up enterprises, construct your economic engine, and race to complete all the key buildings before your opponents.
You can play directly in the browser with no registration. I wanted the simplest possible entry: open the site, enter a nickname, create or join a room.
If the mechanics seem familiar — you're not imagining it. I was inspired by a well-known city-building board game.
Day 1: AI Really Can Write Games
I'm not a developer. I work in tech, but I don't code professionally. Over the past few months I've been experimenting heavily with vibe coding, so I decided to build this project the same way.
I didn't start with code at all. First, I wrote out the mechanics in detail: what cards exist, how a turn plays out, what should happen in each situation. Once the logic settled, I started gradually converting the description into code using AI.
Day 2: Writing the Game Was Just the Beginning
When the first playable version appeared, it quickly became clear that the code was far from the hardest part. The biggest problem was balance.
If you leave everything as-is, players find the single most profitable strategy within a few games and repeat it endlessly. I had to manually tweak card costs, adjust activation probabilities, revisit effects, and examine how different buildings interact. And here, AI doesn't really help.
It can suggest ideas, it can rewrite code — but whether the game actually becomes more fun after changing one number is something only a human can judge. I ended up spending more time on balance than on the initial working version of the game.
Day 3: Infrastructure Hurt More Than the Code
Once the game worked locally, all that was left was the "easy part" — deploying it to a server. How wrong I was.
SSH, Node.js, PM2, Nginx, SSL, domains... and a bunch of other unfamiliar words.
I started with the cheapest VPS. Then I ran an AI agent directly on the server, editing code and deploying changes in real time. Predictable result: the server kept crashing.
The lesson that followed was obvious in hindsight: developing directly on production, especially on a minimal VPS, is a bad idea. Sometimes the most useful lessons are the most basic ones.
The Unexpected Conclusion
When I started the project, I was sure the hard part would be writing the game. In practice, it was the opposite. Within a few days, I had a working product.
Friends played it, found bugs, we fixed things and tweaked others. Then came the question AI handles much worse: where do you find players? Code is easy to verify — either it works or it doesn't. Building an audience is a completely different challenge.
Code has become much more accessible. You can ship an MVP very fast, especially if you're good at working with AI. But after that, a completely different kind of work begins.
You need to find your first users, collect feedback, retain players, understand why they return or don't. And AI can't do that for you.
This seems to be the key bottleneck for most vibe-coded projects right now.
Want to Try It?
The game is live at rastushiy-gorod.ru. No registration needed — just open it, create a room, and start playing. Solo against bots or with friends.
If you give it a try, I'd really appreciate any feedback. Two things I'm most curious about:
- Was it clear what to do without digging into the rules?
- Did you find a strategy that breaks the balance?
I read every comment and keep iterating on the game. That's how the project is developing right now.
Top comments (0)