An app is not good because AI built it. It is good when it solves a real problem, stays inspectable and does not fall apart at the first edge case.
The videos in this hub are about concrete builds: a sticker app, a website, small offline tools and the path from design to code. These are not perfect product launches. They are working examples.
The pattern is the same every time: keep the scope small, plan first, build second, check after. That is what separates useful AI work from vibe coding that only looks good in a screenshot.
Some videos intentionally appear in more than one hub when the context is useful there too.

A missing vacation score sheet becomes a bigger lesson: small, oddly specific tools can now be built when you need them.

A Panini album, 980 stickers and a problem no generic app solved well. This video shows the workflow behind StickerLog: plan, review, design, build.

This video shows the move from a blocked Wix workflow to a local static website with 214 HTML pages, GitHub and Netlify.

Claude Design is not just another model update. It changes where design work starts and who can create first visual drafts.

Part four of the Voicebox series did not go to plan. That is exactly why it is useful: two AI agents debug a real local setup.
For small, clearly scoped tools, yes. You still need judgment, testing and a tight scope. The more critical the system becomes, the more technical review matters.
Many problems are too small for an IT project and too specific for standard software. One local file can be exactly right.
It shows how AI can rebuild a website in a way that is not only faster, but also more controllable and machine-readable.
Do not start with code. First clarify the problem, data, boundaries, user flow and checks. Then the AI becomes much more useful.
I help freelancers, consultants, coaches and small teams turn AI tools into real workflows. Practical, inspectable and matched to how you actually work.
Book a free strategy call