Posts

In the past 12 months alone, we have seen massive investments flow into AI-powered coding platforms. Cursor, one of the frontrunners, reached over $100 million ARR with millions of developers onboard, while Lovable signed up 30,000 paying customers in less than a year. These are not flukes or hype-driven spikes; they are strong signals that the market is undergoing a fundamental shift. What Is Driving This Market Shift? For decades, building software has required expensive, specialized human talent. Now, with advances in large language models (LLMs) and multi-agent AI systems, AI can plan, write, test, and deploy robust code from a simple prompt. This evolution collapses traditional development cycles from months to days or even hours. ...

A quick disclaimer: this topic might not seem directly related coding agents, when in fact it does - quite a lot - coding agents are all about prompting. And even if it wasn’t such a critical thing in coding agents it’s something that I’ve learned while working on them and wanted to share. At first glance, instructing a large language model (LLM) with something like “don’t do X” seems straightforward. But my own experiences—and plenty of research—suggest it doesn’t always pan out. Surprisingly, negative instructions often confuse LLMs or simply get ignored, whereas turning these instructions into positive directives makes all the difference. ...

I’ve been thinking a lot about how to make software creation easier—more intuitive, more efficient, more aligned with how people actually work. That’s what drives Gadlet. But if our goal is to empower non-technical users (and businesses) to build software, could the chat box be holding us back? 🤔 Why Chat Might Be the Wrong Default Chat UIs mimic conversations—easy enough for quick questions. But building software is not just chit-chat. Gadlet’s users want intent-driven creation, not dialogue. Chat interfaces: ...

Meet Mikko and Rolf – two Finnish founders with long business careers behind us and one big idea ahead. We are not marketers or growth hackers. We are builders. We’ve worked in many kinds of roles, seen what works, and learned even more from what didn’t. We all know why coding is hard and why you need a required skillset and knowledge to build quality software. Gadlet is our answer to a these questions: Why can’t anyone build software? Why is software development so hard? Why do most great ideas never see the light of day? ...

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. ...