Tarikh Keluaran Dirancang: Januari 2027

Tentang Permainan Ini

You draw. The AI reads it.

The only thing you do in this game is draw.

When you finish, a character named Kakiko leans in, looks at your drawing, and says out loud what it sees. Something like, "That's a DOG!"

If Kakiko says it's a dog, then it is a dog. It doesn't matter whether you actually drew a dog. All that matters is what Kakiko saw.

So Kakiko gets it wrong. You draw a dog, and Kakiko says, "Is that a ROCK?!" Getting it wrong is part of the game.

You don't have to draw well!

Winning has nothing to do with drawing skill. A scribble made of three lines can read as "dog" when a carefully drawn one doesn't. Stick figures work fine.

Add a pair of ears to a cat, and Kakiko might call it a dog. Working out how to draw something so it gets read the way you want — that's the heart of the game.

There's more than one way to play.

On your own (puzzle)

You're given a goal. For example: "This room is full of dogs, and one cat. Make Kakiko think the cat is a dog." Draw on some ears, add a tail, and if Kakiko says "dog," you've done it. If one try isn't enough, keep adding to the drawing. Each stage brings a new goal and a new world.

Together (versus)

Two or more players draw on the same sheet of paper at the same time. Each team gets a different goal. One side is told "Wreck the sea," the other "Protect the sea" — your goals don't line up. Every turn, Kakiko reads the whole sheet and calls out what just happened.

Together (co-op)

Nobody wins or loses. First, everyone draws their own character, and Kakiko gives each one a name. From there Kakiko becomes the narrator and carries the story along. When Kakiko asks for a bridge, everyone draws a bridge. Whatever you drew turns up in the next part of the story.

Pendedahan Kandungan Dihasilkan AI

Pembangun menerangkan cara permainan mereka menggunakan Kandungan Dihasilkan AI seperti berikut:

Sketch Switch sends the pictures you draw to a third-party vision-language model while the game is running, and shows you what that model says back. This is the core mechanic of the game rather than a side feature.

LIVE-GENERATED CONTENT
When you finish a drawing, the picture on the canvas and the stage prompt are sent to a generative model (Google Gemini, accessed through OpenRouter). The model returns a short label naming what it believes the drawing shows, plus a one-line remark written in the voice of the in-game character Kakiko. Both are displayed to you as returned. In Puzzle Mode that label is also what decides whether the stage is cleared. In Party Mode the model only answers fixed yes-or-no questions about the canvas; the score itself is calculated by the game code, not by the model.

PRE-GENERATED CONTENT
None. All artwork, music, interface text, stage design and character writing in the game were made by hand.

WHAT IS SENT
Only the drawing on the canvas and the stage prompt. No account details or personal information are sent to the model.

GUARDRAILS
Model responses are length-capped and are used only to name and comment on the drawing currently on screen. Because the model runs as a cloud service, Sketch Switch requires an internet connection to play.