I built an entire AI-powered app live, in front of an audience, in just four hours. Did I finish it? Not quite. Did I learn a huge amount? Absolutely. Here is what happened, what I learned, and why I will do it again.
The challenge was simple: could I build and launch a working AI cheatsheet generator, live on stream, using AI first coding and Kaijo1 as my main tool?
Answer: almost! By the end of the session, the app could create editable AI cheatsheets, but it was not yet deployed. A few minutes of post-stream fixes later, it was live for everyone to try. (Next time, I will check deployment on every commit!)
Try the app here: aicheatsheetgenerator.com
What We Achieved in Four Hours
In just four hours, I went from a blank slate to a working product. The app generates AI-powered cheatsheets that you can edit and customise. The core features were working by the end of the stream, but deployment tripped me up. It only took a few more minutes to fix, but it was a reminder: always check your deployment pipeline as you go.
The real story is not just about the code. It is about how much faster and more reliably I could build with AI-first tools. Coding AI made it possible to move at a pace that would have been unthinkable a year ago. Kaijo, my reliability assistant, will make future improvements even smoother.
What I Will Improve Next
Shipping live is only the beginning. Here are the improvements I am planning:
Pay to download: I want to add a way for users to pay to download their cheatsheets, supporting the project and unlocking more features.
Better editing: I will improve the editing experience, including box ordering, styles, and colours, so users can make cheatsheets truly their own.
Automatic Kaijo evaluation: I plan to tell Kaijo about the edits and automatically evaluate them, making the app smarter over time and more tailored to the user.
Lessons Learned from Live Coding
Building live is exhilarating and exhausting. The pressure to deliver in real time forces you to make decisions quickly and trust your tools. Here is what stood out:
AI-first coding is a force multiplier. I achieved more in four hours than I could have managed in a full day solo. The AI handled boilerplate, suggested fixes, and kept me moving forward.
Deployment is always the bottleneck. No matter how fast you build, if you do not check deployment regularly, you will get caught out. I will automate more checks next time.
Audience feedback is invaluable. Viewers spotted issues, suggested features, and kept the energy high. Live interaction made the process so much more fun and productive.
Watch the Full Recording
If you missed the stream, you can watch the full recording below:
Or watch it directly on YouTube.
What Should I Build Next?
Should I do another live build with a different service? What would you like to see me tackle next? Let me know in the comments or reach out on social media.
Join Future Webinars
Get notified about upcoming live coding sessions and AI development workshops.
View Webinar DetailsMore articles
Kill Your Prompts: Build Agents That Actually Work
Every technical team I talk to faces the same painful truth about AI agents. They build something that works brilliantly in their demo, showing it off to stakeholders who nod approvingly. Then they deploy it to production and watch it break in ways they never imagined. The carefully crafted prompts they spent weeks perfecting become a maintenance nightmare.
Recently I showed a (virtual) room full of technical leaders how to kill their prompts entirely. I do not mean improve them or optimise them. I mean kill them completely and build something better.
Read more →Master Prompt Stacking: The Secret to Making AI Code Like You Do
After months of fighting with inconsistent AI coding results, I discovered something that changed how I work with tools like Cursor. The problem was not my prompts. The problem was that I had no idea what else was being fed into the AI alongside my requests.
During a recent webinar, I walked through this discovery with a group of engineers who were facing the same frustrations. What we uncovered was both obvious and surprising: AI coding tools are far more complex than they appear on the surface.
Read more →The Huge List of AI Tools: What's Actually Worth Using in June 2025?
There are way too many AI tools out there now. Every week brings another dozen “revolutionary” AI products promising to transform how you work. It’s overwhelming trying to figure out what’s actually useful versus what’s just hype.
So I’ve put together this major comparison of all the major AI tools as of June 2025. No fluff, no marketing speak - just a straightforward look at what each tool actually does and who it’s best for. Whether you’re looking for coding help, content creation, or just want to chat with an AI, this should help you cut through the noise and find what you need.
Read more →Unlocking Real Leverage with AI Delegation
Starting to delegate to AI feels awkward. It is a lot like hiring your first contractor: you know there is leverage on the other side, but the first steps are messy and uncertain. The myth of the perfect plan holds many people back, but the reality is you just need to begin.
The payoff is real, but the start is always a little rough.
Here is how I do it.
Read more →How I Make Complex AI Changes
Most technical leaders know the pain. You get partway into an ambitious AI project, then hit a wall. You are not sure how to start, or you get so far and then stall out, lost in the noise of options and half-finished experiments.
Recently I tackled this head on. I did this live, in front of an audience. I used a framework that finally made the difference.
The challenge: could I take a complex change, break it down, and actually finish it, live on stream? My answer: yes, with the right approach. Here is exactly how I did it.
Read more →