I'm working on something for the prototyping phase of game dev and want to understand how people here actually work. Solo devs and small teams both welcome.
Looking for 20 minutes with a few designers or developers to walk through your last prototype. What did you open first, where did you get stuck, what did you end up skipping.
No pitch, nothing to sell. Happy to share what I learn back with anyone who wants it.
Comment or DM if you're up for it and I'll sort out timing from there.
A useful first split is whether the prototype tests the game loop or the production pipeline. For gameplay prototypes, we open the shortest playable loop, record the first moment a tester hesitates, and defer polish unless it changes the decision. What people skip is often a clearer signal than stated preference.
I'm a professional computational specialist (working in accelerator physics and applied math), I recently started game dev as a hobby since AI coding tools have gotten very powerful over the last few months. My prototype game Echolumination started as a concept I had years ago but never had the time to build it. My procedure was roughly:
1. Chatting with Claude Fable over the viability of my unique RTS game (comparing existing engines like Unity/Godot or making it a mod for an existing RTS game like SC2). We concluded after some research that making it from scratch is the best approach, and making it browser-based with Pixi.js is a good starting point.
2. After going through the overall scope of the game, I decided on the prototype goals and discussed with the LLM on the proper order to build things in phases and have a clean working setup on GitHub. This is where I designed the coding practices (e.g. decoupling the sim from the renderer, building the main concept of the game's engine, and adding more to it over time).
3. After many weeks of adding features one-by-one in phases (e.g. UI, map layout, unit types, buildings, abilities, how damage is calculated, and much more) and having the LLM fix bugs (roughly 500 Claude sessions (mostly using Opus for coding and Fable for planning)). I finally released the prototype after about 6 weeks from starting.
4. Now I'm focusing on polishing parts, adding new abilities, replacing old assets, and eventually adding content.
My game was coded with AI but I was involved every step of the way. The art assets were built by AI but are simple geometric shapes (no stable diffusion or anything) and the music/sfx are from purchased bundles from real people.
Solo dev here. In my case i develop 'on paper' (or a document like a Gdrive docs) several aspect of the game: mechanics, ideas, story, references. Then with the help of chatgpt i turn it on a GDD and or a Todo List for Zen Wiki. Check the AI did it right, modify myself what's not, and then go for it.
Sometimes If i feel stuck in brainstorming phase or i have a doubt about something. I just copy paste what i have in the LLM and add 'feedback?' (just that) and press enter, and let it give it's opinion or lose faith in humanity a bit more. (If you are reading this after the bombs fell, I'm sorry) . Also, sometimes, i explain what i am doing or want to do and basically ask what for references, movies, series, or basically point me what I'm missing out.
Then I just create a small project akin to a devroom,where i develop the game in it's more 'base' level (literal like a devroom) if i need to use AI for scripting something that escapes my reach because is too complex or too cumbersome, I use it.
Then I create the artwork, decorations, levels, etc. I get art from several sources, 3D models and textures sometimes from myself, sometimes if i want to save time I search in OGA or here in itch, sometimes if i need to,I use StableDiffusion XL to create or modify textures, I use it inside Krita to have more control via drafts or modifying the stuff afterwards.
I am not a musician, so the music comes normally from OGA, Fiftysounds of freesounds. If i don't find what I want of need, then i use Google's Gemini to explain the audio track i want and let it generated for me. (I have to try local audio generators).
I also use the AI like ChatGPT or Gemini to ask for stuff i don't know how to to and don't waste time browsing during hours in sites that bomb you with adds or 'kindly' ask you for disabling the adblock. I mean things like 'How i made a audio file to sound like coming from a old speaker in Audacity?' Or after uploading a screenshot in the llm i ask things like 'feedack?'
More or less, that's how i use it.
