local-ai.ccBrowse 26 releases

GAME LAB / CASE 01 / DS4FLASH0731

One prompt.
One race.

DeepSeek V4 Flash 0731 led the build through DS4. Qwen 3.6 A35B joined as a vision subagent, turning visible failures into targeted fixes.

Starting with one Unity3D car asset, the agents created a racing game for the Godot engine in one initial prompt, then corrected it with two short follow-ups.

LEAD DeepSeek V4 Flash 0731HARNESS DS4VISION Qwen 3.6 A35BENGINE GodotINPUT 1 Unity3D car asset

PLAYABLE GODOT WEB EXPORT

Run the original build.

Open the agent-generated Low Poly Racing build in a new tab. The compressed WebAssembly game downloads only after you choose to launch it.

Steer
A left · D right
Build
ds4flash0731
Engine
Godot Web
Launch the Godot game
Low Poly Racing gameplay from the actual Godot build

THE PROMPT LOG

Build once.
Correct twice.

The initial request supplied intent and one asset. Each follow-up described only what was visibly wrong.

  1. 01

    Initial build

    One asset. One prompt. Build the race.

    Use this Unity3D car asset to create a racing game in the Godot game engine. Add a track, player controls, a race HUD, and a reset flow.

    OUTCOME The first playable scene and game structure were created.

  2. 02

    Follow-up one

    Put the wheels back on—and make it drive.

    The car does not have wheels and the player controls do not work. Add the wheels and make the car controllable.

    OUTCOME The visual asset assembly and input path were repaired.

  3. 03

    Follow-up two

    Fix reset and reverse the reversed steering.

    Fix the reset button. The directions are reversed: A currently moves right and D moves left. Change the controls so A moves left and D moves right.

    OUTCOME Reset returned to a clean state and the final key mapping matched the player’s expectation.

MODEL ROLES

Builder + eyes.

01 / LEAD AGENT

DeepSeek V4 Flash 0731

Worked through DS4 to plan the scene, assemble the project, wire gameplay, and apply follow-up corrections.

02 / VISION SUBAGENT

Qwen 3.6 A35B

Supplied visual inspection so the agent loop could reason about missing wheels, scene state, and the visible result—not only the source files.

01source asset
01initial prompt
02follow-ups
02local models