Posts

In AI-assisted coding, prompts are becoming very important. A prompt is what you give to the AI so it knows what to do. Like giving instructions to a new worker. If the instruction is good, the result is good. If the instruction is bad, the result is bad. Today, many developers are already using AI tools to create code. But there is one problem: very often the Git repositories are a mess. You find the code but no real documentation. You don’t know who wrote what, or why. Sometimes code is broken. Sometimes it is not even clear what the app is doing. ...

When we first started building Gadlet, I was a seasoned professional from totally different scene. While Rolf has plenty of experience on multiple start-ups, I was just stepping into this world. I may not fit the stereotype of founder even though I usually wear hoodies– and to be honest, that made me a bit nervous. We poured our evenings, weekends, and little more money than we’d planned into a prototype for an AI-assisted code generation tool. It felt like a humble beginning: just us working, some coffee beside, and an idea we couldn’t shake. At the start, Gadlet was just a passion project. Today, it’s on the cusp of something bigger, and I would like to share how we got here. ...

You Will Become Useless! Yes, you read right: You might soon be out of a job. Or at least that’s what some headlines will have you believe. Sounds terrifying, doesn’t it? But before you panic, let’s take a calm moment to look at what’s really happening here. As someone who spent over 30 years solving problems in the world of business and software, I’ve seen my share of technologies come and go. From the first business software to cloud solutions and now to artificial intelligence, every leap forward brought fear and excitement in equal measure. Hard to believe, but there was a time when some people didn’t know what Excel was, and some even refused to work with it. This AI, it’s no different, just a bit faster and, because of its vast knowledge base, surprisingly creative. ...

Pricing a coding agent is not just about covering operational costs—it’s about ensuring long-term sustainability while maintaining trust with users. The challenge lies in balancing fairness, transparency, and business viability in a way that keeps users engaged without compromising the quality of service. Whether you’re building a coding agent as part of a community-driven initiative or aiming to turn it into a profitable business, one fundamental reality remains: tokens cost money. This means that, at some point, you need to charge your users. The real challenge is figuring out how to price your agent in a way that covers costs (and ideally generates profit) while keeping your users satisfied and coming back for more. ...

We’ve been busy. That’s probably the simplest and most honest way to put it. Over recent weeks, our hands have been full with extensive testing of our prototype. Interestingly, Gadlet itself has been deeply involved in this process, refining and iterating itself continuously. At times, the feeling is a little bit like watching the movie Terminator—seeing the AI take control and improve things automatically. It’s fascinating and a bit surreal, but the results speak for themselves. The better Gadlet gets, the faster and more efficiently it drives its own enhancements forward. ...

Building a coding assistant is already a challenge, but knowing whether a change actually makes it better is an entirely different beast. The naive approach? Ask the assistant to generate code using the same prompt before and after the change, then manually inspect the results. That might work for something simple—a JavaScript calculator with embedded CSS—but as soon as we scale up to complex projects, this becomes impractical. I started digging into existing solutions and quickly ran into HumanEval and Codex. While they aim to measure LLM coding performance, they don’t quite fit the need. HumanEval provides a set of Python function-generation tasks with unit tests, which is useful but limited. Codex evaluations rely on manually crafted benchmarks, which, again, require too much human intervention when testing incremental improvements in a live system. They also are more about measuring the code generation abilities of an LLM than the tooling on top that builds applications. ...

Why are we doing this? The simple answer: We want to revolutionize software production. Millions of people have ideas—visions of software and applications that could improve their everyday life. At home, at work, in their hobbies. Some ideas are just for fun, while others have real impact. Companies, especially the ones with limited resources, struggle with the same challenges. For some, it’s not just about convenience—it’s about survival. They need the right tools, but buying software off the shelf is not always an option. It may be too expensive, too complex, or simply doesn’t fit their exact needs. ...

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. ...

Last year Rolf, a longtime friend and trusted coder—someone I’d spent years frustrating with my grand visions and relentless demands—introduced me to a new concept: AI-assisted coding. He’d finally decided, with a mixture of amusement and relief, that I was ready to tackle coding on my own. Or at least, with the help of AI. A bold decision, considering my past as a corporate executive who had seen it all except for this. ...

Through the years, I have learned to appreciate the interplay of precision and simplicity in driving performance. Now, as I delve into the realm of AI-driven code generation, I find a striking parallel: the potential of AI to revolutionize software development is immense, but realizing this potential hinges on adhering to fundamental, well-defined guidelines—particularly when it comes to rule sets. The concept of rule sets—structured instructions to guide AI behavior—is hardly new. In theory, they allow us to shape AI output to align with project goals, coding standards, and specific methodologies. In practice, however, I’ve found that an overabundance of rules often complicates rather than clarifies. My experiences and observations through rigorous testing suggest that embracing minimalism in rule design can unleash the true capabilities of AI coding assistants. Here’s why. ...