An independent guide to the JEV ecosystem. Official JEV website

Original community demo · Video hosted on X

Gaming worlds

Real-time gameplay

Real-Time Tetris Control with an AI Agent

A Tetris demo uses Jev to select moves while the game continues running, exploring decision-making in a changing game state.

Marcus Lowe@marcus_lowe
Published
Original post
X / @marcus_lowe
View original demo on X

Opens the author's original post in a new tab.

The implementation ideas below are our interpretation of the community demo. Check the original post for the author’s actual setup.

Where this fits

Use a game with a small action set to explore the effects of decision latency and observation frequency.

How to build on the idea

Observe the board, generate legal actions, request a decision, and apply it only if it still fits the current game state. Repeat as the board changes.

An illustrative decision

These examples explain a possible workflow; they are not recorded demo results or API request and response formats.

Example input
A falling piece, the current board, and legal options: move left, move right, rotate, drop.
Example decision
Choose one legal move for the current frame.

Scope and limitations

The board can change while a request is in flight. The demo does not establish a general game-playing benchmark or guarantee strong play.

Try a decision of your own

Define the context and a small set of choices in the playground, then use the API guide to connect your application.