I'm just a dad
with an idea.

I'm not a professional software developer.

I didn't start with a team of engineers, investors, or a massive budget.

I'm a dad. I have a job, a family, responsibilities, and probably more ideas than I know what to do with.

But I've always had this thought in the back of my mind:

What if I could actually build the things I imagine?

Not just write them down. Not just talk about them. Actually turn them into something real.

That's where my journey with AI began.

Something interesting happened along the way.

The more I learned, the more I realised what might be possible.

What started as experimenting with AI slowly grew into an entire collection of projects.

I began building Sorelium Tower, a system designed to bring different AI workflows together.

Then came Sorelium Flow and Speech, my own tools for creating and editing videos, generating narration, and helping turn ideas into content.

I worked on EverythingAI, an interactive platform for learning about artificial intelligence.

I built a website for Sorelium Studio.

I've explored games, digital products, automated systems, and even ways to create my own 3D characters.

Not everything is finished.

Not everything works perfectly.

Some things have been rebuilt more times than I'd like to admit.

But these are no longer just ideas sitting in my head. They're projects I've actually worked on and brought to different stages of life.

And that means something to me.

I think there's a misunderstanding about building things with AI.

People sometimes imagine you type a sentence, press Enter, and suddenly have a perfect piece of software.

I wish it worked like that.

AI has made things possible for me that I wouldn't have known how to approach on my own.

But I've still had to make decisions, explain what I wanted, test results, find problems, rethink designs, and sometimes start again.

When Codex became part of my workflow, things improved. I could work on larger pieces of code without manually moving every change between ChatGPT and my files.

But that brought its own challenges.

Usage limits became something I had to work around. Sometimes I'd be making good progress and hit a limit. I'd have to wait, plan what to tackle next, or find another way to keep moving.

And even with better tools, errors didn't magically disappear.

That's an important difference.

This is probably the most important thing I want to say.

If you're sitting there with an idea for a game, an app, a website, a business, or something completely different, don't automatically dismiss it because you don't know how to code.

I was in that position.

I didn't know how to build most of the things I wanted to create.

And I'm still learning every day.

But tools like ChatGPT have changed what's possible for someone willing to experiment.

You can ask questions. You can learn. You can build something small, break it, understand why it broke, and improve it.

You don't need to start with a massive project.

Start with one idea.

Get one small part working.

Then build on it.

Of course, AI can make mistakes. You'll need patience, judgment, and a willingness to check its work. Some ideas will be harder than others, and not every project will succeed.

But don't let the fear of not knowing enough stop you from trying.

You don't have to know how to build the whole thing before you take the first step.