AI in Coding, Part 4: I Let AI Build BigToFit.com During My Lecture (Here's What Happened)

When I gave my lecture on AI in Coding, I didn’t want to just talk about the future. I wanted to show it in action. Instead of picking a random demo app, I chose something personal: something I had started years ago but abandoned: BigToFit.com, my blog and YouTube companion site for my weight loss journey.

The blog was hacked long ago, right around the time my main site (irhadbabic.com) was attacked too. I stopped both the updates and my journey. But recently, as I restarted working on my health, I thought: why not also restart BigToFit, and this time, let AI help me build it?

Scoping the New BigToFit

I began by asking ChatGPT to design an improved version of BigToFit.com. I use it for product management and design tasks on purpose: because, frankly, I haven’t found a better model for this type of work. In just a few prompts, it scoped out a backlog with clear features, user flows, and design suggestions.

That gave me a solid foundation I could plug straight into development.

Building It with Cursor + Claude 4+

With the backlog ready, I dropped it into Cursor, my AI-native coding environment. For coding, I chose Claude 4+, which I’ve found excellent for structured tasks.

The site itself was built on Hugo, a static site generator, so there was no backend to worry about. Cursor generated a very solid Hugo site while I continued speaking.

By the end of the lecture, I had a very decent version of BigToFit.com running locally on my machine. It was more than one might have expected from something built in the background while I was on stage.

What’s Next for BigToFit

The site isn’t live yet: for now, I’ll publish an under construction landing page while I finish polishing it. Soon though, the new BigToFit.com will go live, rebuilt with the help of AI.

This wasn’t just a coding experiment. It was a way to restart a project that matters to me, and to prove that AI can take an idea from backlog to working product in under an hour.

What Worked Well

Product design – ChatGPT scoped a clear, logical backlog.

Speed – Claude 4+ inside Cursor generated a working Hugo site during the lecture.

Structure – The output was organized and coherent.

Where It Fell Short

Polish – The design was functional, but not yet branded or personalized.

Testing and security – Not present, as expected with static site generation.

Deployment – Nothing was published automatically. This was also expected, since deployment is still my responsibility.

The Lesson: AI Helps You Restart Faster

For me, this wasn’t just a demo: it was a restart. BigToFit.com went from “an old hacked blog” to “a new Hugo site with fresh energy” in under an hour.

That’s the power of AI in coding: it doesn’t just save time, it gives you momentum. It helps you restart, rebuild, and move forward faster than ever before.

✅ Key Takeaway

AI isn’t just a coding shortcut. It’s a productivity partner that can turn your ideas into working products faster than you expect. But it still needs your vision, oversight, and deployment work to reach production.

This article is part of my series “AI in Coding – From Past to Future.”

🎥 Watch the Full Lecture

For a deeper dive into this topic, watch my complete presentation on AI in software development:

Note: The introduction is in Bosnian, but the main lecture is in English and starts around the 3-minute mark.

This lecture covers all the topics in this series and provides additional insights and Q&A. You can see the BigToFit.com demo happen live during the presentation!

Full Series:

• Part 1: From Lisp to Copilot: The Evolution of AI in Software Development
• Part 2: AI Tools Every Engineer Should Know in 2025
• Part 3: Best Practices for Working with Your New Junior Developer
• Part 4: I Let AI Build BigToFit.com During My Lecture (this post)
• Part 5: AI in Coding: How Far We’ve Come (Coming October 13)
• Part 6: The Next 10 Years of Coding (Coming October 16)
• Part 7: Will AI Replace Programmers? (Coming October 20)
• Part 8: Future-Proofing Your Career (Coming October 23)

Have you tried building something live with AI? What was your experience with AI assisted rapid prototyping? I’d love to hear about your own experiments with AI development workflows.