I have a vision. A dream of building an operational management system for organizations involved in sports worldwide. It is not a new idea. For years, I have planned it with a good friend of mine, someone deeply connected to sports on many levels. On top of that, he is an excellent coder and software designer. We have tested the idea and concept at the design level and even attempted to build prototypes. But due to the complexity of the idea, progress has been almost nonexistent. We realized early on that we would need an army of seasoned coders to make this a reality.
The project has been running in the background, always in our minds, waiting for the right opportunity. Recently, after being introduced to AI-assisted code generation, I started studying new methods of working with code. The journey with AI tools like Cursor and Lovable has been educational and inspiring. I began to understand the potential of AI for faster, better, and more productive software generation. At the same time, I started thinking ahead—is this phase we are experiencing just an intermission before something even bigger, like true code-on-demand? That discussion is for later. For now, we focus on building something big.
Some time ago, I realized that our long-time project, the operational management system, might actually be possible with AI. I started testing development first with Cursor but soon switched to Lovable and Supabase. With the schema in my head, I began prototyping. No designs, no selected frameworks, no predefined architecture—I let the machine decide. Authentication, user rights, policies, row-level security, and then features, one after another. The first impressions were promising. The speed, accuracy, intuitive solutions, problem-solving—it all exceeded my expectations.
As an experienced solution buyer and system power user, I quickly saw that the pace of development was far beyond a standard development team’s timeline. This might sound harsh, but I am convinced that in my current cooperation with AI, I can easily outpace small, conventional development teams when the conditions are right. My biggest advantage? My new team is indomitable. When I, as a designer and visionary, tell the AI what needs to be done and later realize I made a mistake or have second thoughts, my AI assistants fix the problem—without hesitation, without frustration. Just hard work. That is something human teams rarely achieve, and that makes all the difference.
Does this sound too good to be true? Yes, it does. While the speed and agility of development are remarkable, the devil is in the details. I have learned some lessons the hard way. Complexity often leads to guessing, hesitation, and wrong conclusions. Lack of documentation, even when specifically requested. A tendency to redo things when in doubt. With Cursor and Lovable, I have not yet found a 100% bulletproof way to avoid these pitfalls. Anyone who has worked with AI code generation understands the problem: context overflow. Many articles discuss this issue, so I will leave it for now.
The key point is this: our operational management system for sports just got a boost thanks to AI-assisted coding. I am confident that I can complete this project with Lovable. If I succeed, I will have accomplished something I could not achieve before, even with a small development team. This project is now a proper benchmark for testing AI’s capabilities in coding and solution providing.
This brings us back to Gadlet. Gadlet’s prototypes are up and running. Maybe I should take a risk and continue developing the operational management project with Gadlet. I will keep you updated on my progress. I believe switching to Gadlet will give us crucial insights into setting up a smooth workflow—turning ideas into reality for people who do not care how it is done but simply say, ‘This is what I want now.’
Follow the process, we will be in touch! Mikko