Learn to build a complex 3D multiplayer game, even with no prior game development experience. This workflow guides you through an iterative process of using an AI assistant like Cursor and Claude as a junior developer to go from a simple concept to a functional prototype.
with Claire Vo
Begin by giving your AI assistant in an IDE like Cursor a high-level prompt to generate the basic structure of your game. Don't aim for perfection; start with a minimal viable concept, like a gray cube on a starry background.
Iteratively add features by prompting the AI. For example, ask it to add movement controls (W, A, S, D). This forces you and the AI to start solving core challenges like 3D physics and user input handling.
Add controls for movement using the W, A, S, and D keys. The ship should be able to pitch, yaw, and roll.Find a 3D model from a source like SketchFab. Ask your AI assistant to write the code to import the model (e.g., in GLTF or GLB format). Use this opportunity to ask the AI to explain the underlying technology, such as how 3D model loaders work in Three.js.
How do I import a GLTF model into my Three.js scene and replace the gray cube with it? Also, explain how the GLTFLoader works.When you encounter visual bugs, like a model facing the wrong way, describe the problem and the desired outcome to the AI with as much detail as possible. Being specific is key to solving complex visual and orientation issues.
The imported ship model is loading sideways. The front of the ship should be facing forward, but it's currently oriented 90-degrees to the left. Please adjust the model's rotation upon loading to fix this.Once the single-player experience is solid, ask the AI for the best way to implement multiplayer functionality. It might suggest options like WebSockets. Have the AI generate the server and client code, and then ask it to review its own implementation to catch potential bugs, race conditions, or optimization issues.
Follow Sahil Lavingia's method for delegating small but impactful maintenance tasks, like fixing an internal Slack report, to the AI agent Devin. This workflow shows how to use simple, clear prompts to fix code and update system prompts without distracting your engineering team.
Learn Gumroad CEO Sahil Lavingia's process for rapidly prototyping a UI with v0, then using the AI agent Devin to autonomously code, implement, and submit the feature for review, turning a multi-day task into a one-hour workflow.
Improve your writing in real-time by using ChatGPT as a first reader. Get instant feedback on structure, clarity, and flow as you write, allowing you to polish your work section by section.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.