Day 18. Building the game I've dreamed of for 15 years with AI.
I've learned how to build proper levels with AI. I take the design and the architecture, and AI helps me put it all together and check the balance.
I made the first level of my game almost entirely by hand. I wanted to understand how it works and what I like, from how big the trees should be to how the textures tile. After a day digging around in the terrain tools it all made sense, and I could see how much of it could be automated by painting zones.
Claude helped me a lot with the tileable textures. Matching the colors took a ton of iterations, and that was the hardest part of the whole level.
For level two I took a different route. I built myself a simple HTML planner with a logical map of the level, where I place everything and design the layout. Painting a level and making it fun to play are two different jobs, so I kept the design for myself.
We even made automated tests with Claude: 2D simulations that show which routes a player takes and how hard the level is. They're rough, but they give a real sense of how the level plays.
Once the plan was ready, I handed everything to Claude, and 3-4 hours later I had a working level. It reused the patterns from my first level, scattered objects unevenly so nothing looks placed on a grid, and generated extra props whenever I asked.
I showed it one example, it picked up what worked, and we turned that into a skill for the next levels.
The video is a quick flight over level two, then how it got there, from my first sketch to the version I play now.
My wishlist for coding agents: one ping when you’re needed, a short “here’s what changed” when you return.
I don’t need to watch every tool call like it’s a live sport.
I feel like I’m frying my dopamine system with all this Claude/Codex work.
Constantly monitoring and instructing, anticipating the work it’s going to produce.
Then killing time waiting, consuming way more algo feed content than ever before.
How do y’all tackle this?
I’d trade a launch checklist for an honest “here’s how I found my first ten users” post.
Where did you find them? What did you say? How many ignored you?
That’s the stuff I’d read.
Advice to solo founders (from $1k MRR experience 😄)
You are not going to win just because you have a SaaS with a unique idea.
Don’t think building in public will get your idea copied.
It can still be copied in an hour after you launch.
“Not building in public” is not the solution.
You will only win if you have good distribution.
That’s the reality.
Start posting content ASAP. Build your personal brand.
I started posting content in January 2023 and built a crazy 4-5M reach per month through organic distribution.
Then when I launched a SaaS directory (codehype .ai) it started getting that many users that other directories couldn’t achieve even after doing SEO and other stuff for 1-2 years.
My success of getting $1,400 revenue in the first month of https://t.co/kNoOqdoffD was because I had distribution.
Do not build a great SaaS and not work on distribution.
Build an average SaaS and distribution simultaneously.
Then iterate and improve.
We cannot ignore AI coding. It will only become more powerful as we move forward.
Your only winning route is:
First-mover advantage + distribution.
Work on it.
At least start with X and Instagram.
@harisahmad59 Which kind of post actually brought paying customers: tutorials, progress updates, or launch posts? Would love to see one example that converted.
I'm building Stillwater with Codex, Blender and @threejs: an interactive 3D world rendered in the browser.
Here's a quiet fishing trip as the rain rolls in.
Someone show me a Claude Code mod that saves you ten clicks every day.
Tiny demo, what it replaces, and how you remove it. That’s enough to get me interested.