Building small digital products with AI-assisted “almost no-code”
I’ve been working as a solo founder for a while now, and along the way I realized something important to stay productive , I needed small, finishable digital products alongside my long-term project.
So during the past months I experimented with a simple idea:
“What if I build small products using mostly free AI tools — almost like no-code?”
I’ve recently been experimenting with something simple but powerful:
Using only free AI tools — ChatGPT Free, Claude Free, Copilot, and Gemini — to build complete digital product.
That experiment turned into two shipped products:
- Senkai Arena – HTML5 game
[ https://www.indiehackers.com/product/senkai-arena ]
If you’re curious about the full story behind it, I wrote it
[ https://medium.com/@jaroenwut/how-i-built-the-html5-game-senkai-arena-using-free-ai-tools-as-a-solo-founder-af94713d25cf ]
- RoenAmp - HTML5 MP3 Player
[ https://www.indiehackers.com/product/roenamp ]
If you’re curious about the full story behind it, I wrote it
[ https://medium.com/@jaroenwut/how-ai-helped-me-recreate-roenamp-a-1999-mp3-player-in-2025-20aed2d89fa0 ]
Why I’m sharing this
As a solo founder, momentum matters more than anything.
These AI-assisted mini projects kept me from burning out, helped me maintain creative energy, and gave me small wins along the way.
🙏 Thanks for reading!
I’d be thrilled if you could try the demos and share your feedback — it really helps me improve and plan the next projects.
The pairing of 'runs locally' + 'no API keys' is undervalued positioning. It speaks to the technical buyer who has already been burned by SaaS tools that changed pricing, added rate limits, or went down at the wrong moment.
The one-time purchase model makes sense when the tool does a defined job well. What's the job this tool does?
Good point.
In this case it’s not a single tool actually.
I’m experimenting with using free AI tools (ChatGPT, Claude, Copilot, Gemini) to build small digital products — like simple HTML5 games that are actually playable.
The idea is to keep projects small and finishable so a solo founder can maintain momentum.
I love the pragmatic angle here — building small products fast with AI + no-code is exactly how a lot of founders can de-risk early stages.
From a validation POV, the real leverage often isn’t just how fast you build it — it’s knowing what signal will tell you it actually matters.
For example:
• people saying “I’d pay $X for this”
• repeat use / habitual engagement
• users changing workflows
Those signals distinguish fun experiments from real demand.
Curious: when you talk about almost no code with AI, what’s the first user signal you’d watch before deciding to invest more time or polish?
Thank you very much for your interest in this thread and for the valuable advice.
At the moment, I’m using AI to help develop small, lightweight game products. I intentionally position these games to be fun, easy to pick up, and quick to finish — designed for short breaks and brief moments of relaxation during the workday.
For me, the first signal isn’t payment yet.
It’s whether players come back and play again on their own.
If someone opens a small game during a break, finishes it, and then returns to it again the next day, I see that as a sign the game has started to earn a place in their daily routine or workflow.
Only after observing this kind of behavior do I start thinking about polish, packaging, or monetization.