Four agents build a browser game, with Jev passing context between them
Four agents split the work of writing movement logic, assembling the scene and handling collisions, with a fourth opening the browser to test by hand, while Jev passes context between them so verification stays part of the pipeline.
The most important agent on this team builds nothing. It only checks. In the video, four agents assemble a browser game from a 12-second clip. Rules works out the movement logic. Builder assembles the scene and interface. Logic takes controls and collisions. The fourth, Tester, opens the browser and plays it by hand. Sounds minor. But this is exactly where most AI projects break: the code is written, the report looks great, and the restart button doesn't work. Here, verification is part of the pipeline. The agents check hitbox overlap, jump timing, state after restart. Specific things, not "looks fine." Jev runs between them. It writes nothing, it passes context. One agent learns how the character jumps, and the next one already knows. It works like a relay race, not like four people in separate rooms. One more detail I liked. In the last frame, the gameplay checks are still marked pending. No green checkmarks in advance. Want AI to make reliable things? Give it a separate agent that doesn't trust the others. #AIAgents #GameDev #MultiAgent