How I Built 12 Games with AI (Without Knowing How to Code)
I’ve been using computers since 1980.
I’ve built websites, businesses, and brands online for decades. But there’s one thing I’ve never been able to do…
Code.
I took a programming class in high school and quickly realized it wasn’t for me. When I look at code today, I still feel like I’m staring at a foreign language.
And yet, here I am.
I’ve now built a collection of playable games—daily puzzle games, an idle game, and even a 3D shooter, all using AI.
👉 https://games.aiforeveryoneshow.com/
These aren’t concepts or mockups. They’re live. You can play them right now.
That alone should tell you something about where we are.
This Started with Curiosity, Not a Plan
Like many things I’ve done over the years, this didn’t begin as a business idea.
It started at dinner.
My fiancée Erin and I regularly play the daily games from the New York Times. Wordle, Connections, Spelling Bee—those have become part of our routine. One night I casually mentioned that I might try building something similar.
Not to compete. Just to see if I could.
I opened up an AI coding tool and asked it to help me create a simple Connections-style game. That first project turned into a game I call Threads.
It worked.
I was excited to see my idea become a reality so quickly and easily!
From there, I began building more daily games. Nothing overly complex. Just simple, engaging experiences that people might come back to each day.
The Real Breakthrough Wasn’t Technical
At some point, something changed for me, and it had nothing to do with code.
I realized I wasn’t actually “building” these games in the traditional sense.
I was directing them.
Instead of asking, “How do I write this?” I found myself asking, “How do I explain what I want clearly enough for the AI to create it?”
That’s a very different approach and it feels a bit like a superpower.
It’s also the part most people still haven’t fully grasped.
From Daily Games to Something Bigger
Once I had a handful of working games, I decided to try something a bit more ambitious.
During another conversation with Erin, I was explaining the idea of idle games. They are low-interaction games that quietly progress and somehow keep you coming back for more. You may have heard of the grandfather of idle games, Cookie Clicker.
Well Erin suggested I do something with puppies. (Because of course she did)
That was all I needed.
The result was PupTown, an idle-style game built around rescuing and adopting out dogs.
👉 https://games.aiforeveryoneshow.com/puptown/
I had no prior experience building games like this. No background in game engines. Just a process:
Prompt.
Test.
Adjust.
Repeat.
What used to require a team became something I could iterate on myself.
Then I Decided to Push It
At that point I thought, why not try something I definitely shouldn’t be able to do?
I went back to one of my earliest gaming memories: Castle Wolfenstein 3D. It was one of the first 3D shooters I ever played, and it stuck with me.
So I tried building a simple, retro-style 3D shooter of my own.
Of course, I stayed on theme.
Dogs.
In this case, rescuing dogs by taking down bad guys with a water gun.
That project became PoundBreak.
👉 https://games.aiforeveryoneshow.com/poundbreak/
Let me say that again.
I built a 3D shooter without knowing how to code.
Is it a blockbuster game? Of course not.
But that’s not the point.
The point is that it exists.
What This Really Shows
This isn’t about games.
It’s about access.
For years, if you wanted to build something digital, you needed to know how to code—or you needed someone who did.
That requirement acted as a gatekeeper.
Now that gate is starting to open.
Not completely. Not perfectly. But enough that someone like me can take an idea and turn it into something real.
And I’m far from the only one. If you spend any time on X or in developer communities, you’ll see people building things every day with tools like Claude Code and Codex.
Some of what they’re doing goes well beyond what I’ve built.
What People Get Wrong About This
Whenever I share this, I tend to hear two reactions.
One is that AI is going to replace developers.
The other is that this somehow “doesn’t count.”
Both miss the point.
AI doesn’t remove the need for thinking. If anything, it increases it.
If you don’t know what you want to build, the tool won’t figure it out for you. If your instructions are unclear, the results will be inconsistent.
The work hasn’t disappeared.
It’s changed.
The Skill That Matters Now
The most important ability in this environment isn’t coding.
It’s direction.
Being able to clearly communicate what you want, evaluate what comes back, and refine it until it works.
That’s where most of the time goes.
And that’s the part people underestimate.
As we’ve been saying for the past few years, “learn to prompt”.
Yes, It’s Still Rough
Working this way isn’t perfect.
Things break.
Outputs aren’t always what you expect.
You spend time iterating.
But that’s not the real story.
The story is that someone without programming skills, like yours truly, can now participate in creating things that were previously out of reach.
Once that door opens, it doesn’t stay closed for long.
The Opportunity Sitting in Front of You
There are people reading this who have had ideas sitting in the back of their minds for years.
Apps.
Tools.
Games.
Products.
The only reason those ideas never moved forward was because they didn’t know how to build them.
That excuse is getting weaker.
So Here’s the Question
If someone who doesn’t know how to code can build and publish games…
What have you been putting off?
Try Them Yourself
If you’re curious, go play the games and see what’s possible right now:
👉 https://games.aiforeveryoneshow.com/
I’d genuinely love your feedback.
