When It Started Looking Real

I think the breakthrough happened before I was ready for it.

On June 2, I sat down and gave the AI one giant prompt. Not a sensible little starter prompt. Not “let’s build one page first.” I basically asked for the whole dream in one breath.

A full ecommerce and community website for Beads of Hope T1D. A shop. A customize page. A community area. Checkout. Google login. The works.

Looking back, it was a very 50-year-old-new-to-this move. I didn’t know enough to be cautious, so I just asked for everything.

About 20 minutes later, there it was.

A real-looking storefront.

Not an idea. Not a sketch. Not a document sitting in a folder waiting for “someday.” There were product areas, pages, a checkout connection, and even a whole set of database tables behind it. A database is just the place where the site keeps its information, like products, carts, orders, and users. The AI had built 22 of them.

I remember feeling two things at once: thrilled and completely disoriented.

Because when you have never built software before, you expect the hard part to be making anything appear at all. Then suddenly something appears, and your brain has to catch up. It felt a little like walking into a room you thought was empty and finding furniture already arranged.

For a minute, Beads of Hope T1D looked like a real brand.

And then, of course, it broke.

That same evening, none of the product images showed up on the published site. The shop page had duplicate category buttons. Every time I clicked where a product image should have been, the page snapped back up to the top of the “all” category like it was trying to escape me.

I told the AI, in plain frustration, that the images were still not visible and every click made the screen jump back to the top.

This went on for hours.

That is the part I want to remember honestly. The breakthrough was not a clean movie moment where the music swelled and everything worked forever. It was more like: “Oh my gosh, this exists!” followed almost immediately by, “Oh no, why is it doing that?”

A few days later, I hit another wall on the customize page. The error said:

Cannot find module '@/assets/blue-ribbon.png.asset.json'

I had no idea what an asset.json was. I still barely do. I only knew the page was complaining about something it needed and could not find.

There were also tiny design things that felt enormous to me at the time. Moving a blue ribbon down a quarter inch. Making the T1D Hope text stand out with white shading. Getting the hover zoom right on badge reel photos — first 3X, then 2X, then only on badge reels.

If you already know this world, that probably sounds fussy. But to me, those details mattered because they were the difference between “homemade website” and “real little brand with a purpose.”

And the purpose is what kept pulling me back.

Later in the month, when I was working on the launch video, the first version did not feel right. I told the AI, “I could have made this on my iPhone.” The second version was much more cinematic, with music and a photo card that originally said, “She was four when everything changed.”

I changed it to: “He was two when everything changed.”

Because that is the real reason behind all of this.

It is for my son.

That was another kind of breakthrough. Not technical. Personal.

The site started as a big prompt and a lot of stubborn clicking, but somewhere along the way it became a place for the story I actually cared about. A way to raise money and awareness for Type 1 Diabetes through handmade bead products. A way to make something useful out of a hard thing.

The store is live-ready now. Payments, shipping, tax, and emails are wired up, according to the AI. I still have to finish activating the real Stripe account, which means real bank information and the very real possibility of a first order.

That part makes me nervous.

I still wonder if anyone will buy. I still worry I will miss some business-side detail. I still feel out of my depth more often than I would like to admit.

But I also have a storefront that exists.

And for someone who started with no coding background and one giant, slightly ridiculous prompt, that still feels like a breakthrough.

Small takeaway: Sometimes the breakthrough is not when everything works. Sometimes it is when the thing becomes real enough to scare you.