Make a puzzle game with AI: the rule is small, the levels are the work
A puzzle game is one small rule and fifty arrangements of it. Flockbay writes the rule as GDScript, which leaves you free to do the part that is genuinely hard. Free AI to start: Flockbay's AI and your own Claude, ChatGPT, agent or API key are free for your first build; after that, a plan keeps you building. It runs on Windows, macOS and Linux, on the official Godot engine.
The main page on this subject is Puzzle game maker: the rule is the game, and the rule gets written.
AppImage, x86_64. Ubuntu 22.04, Debian 12, Fedora 39 or newer.
Intel or AMD Chromebook, with Linux turned on.
The rule and the levels are different problems
Take any good puzzle game and write down its mechanic. It fits in a sentence. Blocks slide until they hit something. You can swap places with your clone. Colours combine when adjacent.
Now write down what makes the game good. That takes a hundred pages, because it is the order of the levels, the moment the rule reveals a second implication, the level that teaches without a tutorial, the one that is only hard because you assumed something.
Traditionally the sentence takes you two weeks to program and the hundred pages never get written because you ran out of energy. Reversing that is what this is for.
Getting the mechanic built
You describe it to Flockbay, it goes into the brief, and Flockbay writes GDScript in your project: grid movement, collision rules, win conditions, undo, reset, move counters. Then it runs the game and pushes the pieces around itself, sending input events and reading the debugger, to check the rule does what the brief says.
Undo is worth asking for on day one. Puzzle games without undo are punishing in a way that has nothing to do with difficulty, and building it in later is much more awkward than having it from the start.
Then you play the mechanic in an empty room, doing nothing but pushing the pieces around, until the interaction feels clean. Ambiguity in the rule shows up here and is much cheaper to fix now than after thirty levels exist.
More on this: AI stealth game maker: the guard has to be readable
Designing levels is your job, even when Flockbay builds them
Flockbay builds what you design: say where the walls, the blocks and the goal go, and it lays them out. What does not work is asking for a level and taking whatever comes. A puzzle level nobody designed is either trivially solvable or accidentally impossible, and the interesting middle — the level whose solution feels like a discovery — comes from a person who knows what the player has understood so far.
A puzzle is precise to the cell, so this is the genre where the by-hand tools earn their place. Godot's own 2D and 3D views are right there, and you can move one block one cell, play again, and let Godot's undo take it back if it was worse.
The first four or five levels are the ones that matter most and they take the longest. They are teaching. If the player learns the rule without being told it, the rest of the game works. If they do not, nothing later saves it.
Play your own levels a week after making them and you will find out which ones actually teach.
More on this: AI puzzle generator: generating puzzles is easy. Generating good ones is not
Practicalities
Flockbay is a desktop app for Windows, macOS and Linux, with open-source Godot bundled inside. Your game runs locally on your machine. Not a browser tool.
Puzzle games are the genre least likely to strain any machine, so local performance is not the reason to be here. Owning a real Godot project on your own disk is.
Building needs an internet connection because the chat and asset generation are network services. Playing what you built does not. Free AI to start: Flockbay's AI and your own Claude, ChatGPT, agent or API key are free for your first build; after that, a plan keeps you building.
When to add the second mechanic
Later than you want to. The urge to add a second rule usually arrives when you have run out of ideas for the first one, which is normally about twenty levels before the first one is actually exhausted.
When you do add it, the good levels are the ones where the two rules interact rather than alternate. Those are hard to find and they are the reason to make a puzzle game at all.
More on this: AI puzzle maker: make the puzzle game you keep describing to people
Playtesting a puzzle is unlike playtesting anything else
You cannot test your own puzzles for difficulty. You know the solution and you cannot unknow it, so your sense of how hard a level is becomes useless the moment you finish making it.
What you can test is clarity. Watch someone else play, say nothing, and note the exact moment they get stuck and what they try instead. Their wrong attempts tell you what your level appears to be about, which is often not what you intended.
One person playing silently is worth more than a page of your own notes. This is the cheapest and most reliable quality step in the genre.
A starting project for this is the puzzle game templates.
Questions
- Can it generate puzzle levels for me?
- It builds the levels you design, and you can move any piece by hand in the editor. Puzzles nobody designed tend to be either trivial or unsolvable; the interesting ones come from knowing what the player has learned.
- Can I get undo and reset without coding?
- Yes. Ask for them early and Flockbay writes them into your project.
- Does it do grid-based movement?
- Yes. It is ordinary code rather than a fixed template, so grid, hex, or something stranger all work.
- Is it 2D or 3D?
- Either. Say which the game is and the tools follow, with the same chat either way. A 2D puzzle game gets a TileMapLayer, whose TileSet gives the edges and the collision, and sprites at an exact position, rotation and scale, which is the shape most grid puzzles want.
- What does it cost?
- Free to download. Free AI to start: Flockbay's AI and your own Claude, ChatGPT, agent or API key are free for your first build; after that, a plan keeps you building.
Free to download for Windows, macOS and Linux.
Download Flockbay free