Posts on Gadlet

Skills are the next step after AGENTS.md

Fri, 10 Apr 2026 14:09:00 +0300

In short:

Skills are focused instruction modules for recurring tasks.

They are loaded when needed, so your base context stays cleaner.

You can use skills with or without AGENTS.md.

If you use both: AGENTS.md stays high-level, skills hold the detailed methods.

Most people hearing about skills for the first time ask the same questions:

What are they, really?
Why should I care?
How do I actually use them?

This article is written in that order.

FLAD pt. 2: Prompts for Generating `AGENTS.md`

Sun, 14 Dec 2025 17:53:03 +0200

This post continues the idea of Full-Loop Agentic Development (FLAD).

The previous article introduced FLAD as a development model where the agent owns the entire loop: planning, implementation, testing, validation, and only then handing control back to the human.

This time, we’ll keep it short and practical.

Below are two copy‑pasteable prompts, that you can use directly with a coding agent.

The first prompt generates a production‑grade AGENTS.md for an existing project.
The second prompt kicks off a new project in a FLAD‑native way, using existing ecosystem bootstrapping tools.

Both prompts explicitly require the model to research current‑year best practices, tools, and libraries before producing output.

Full-Loop Agentic Development: When the Agent Becomes Your CI/CD

Sun, 26 Oct 2025 09:11:03 +0200

Disclaimer: The information in this post reflects the state of coding agents today. They’re evolving fast — what’s hard now might be trivial next month.

The Cliff of Death

If you’ve spent any time experimenting with coding agents, you’ve probably felt it — that point where everything seems to work until it suddenly doesn’t. The agent writes code, deploys it for you, maybe even fixes a few things… and then progress falls off a cliff. The codebase starts to decay. Small shortcuts compound into big problems. And instead of helping, the agent begins to quietly break things.

Should You Version Control Your Context?

Fri, 19 Sep 2025 10:57:02 +0200

In an earlier blog post, I asked: Should you version control your prompts? It was a useful question at the time, but today I want to shift the focus. Perhaps it is not your prompts that most need version control. Instead, it may be the context.

Why Context Matters

When generating code with AI, the context is everything. Context determines what the system can see, what it can remember, and what it can base its reasoning on. At some point, though, context begins to slip out of control:

AI-Assisted Code Generation: What is the Cliff-Of-Death, why does it appear — and How We Avoid It

Thu, 18 Sep 2025 10:57:02 +0200

I like straight talk. The hype is real. Investors are searching for the next unicorn. Money flows, demos look great, and some platforms can produce working apps faster than any human team ever will. But if the goal is reliable software that survives contact with real users, real data, auth, policies, and deployment, the road today has a Cliff-Of-Death on it. You don’t fall right away. You sprint, you proceed, you smile, and then — in one final iteration — game over.

Measuring Improvements in a Coding Assistant, part 2: Iteration Efficiency

Wed, 17 Sep 2025 09:11:03 +0200

I’ve been thinking a lot about how we evaluate coding agents, especially after my last post on measuring coding assistants. The usual benchmarks focus on pass/fail results—did the agent solve the problem or not? But the more I tinker with these systems, the more it feels like that lens is too narrow. It ignores how the agent gets there.

Imagine two agents. Agent A spits out code that compiles and passes tests on the first try, but the code is messy, brittle, and hard to maintain. Agent B, on the other hand, starts off with a few errors, but quickly cleans them up across iterations, and the final product is well-structured and robust. Traditional benchmarks would rate A higher simply because it “passed.” But in reality, B might be the more reliable partner in the long run.

No-Code, Low-Code, AI-Code: What’s the Difference?

Fri, 05 Sep 2025 10:57:02 +0200

In last years, we’ve seen many tools try to make software creation easier. No-code. Low-code. Drag-and-drop builders. Big promises. But for many creators, results have been limited.

Now a new type of tool is coming — AI-assisted Code Generation. It sounds similar, but it’s very different.

Let’s break it down.

No-Code: Fast but Limited

No-code tools let users build apps without writing any code. Usually, this happens through visual builders — drag-and-drop components, predefined templates, and menus.

The Billion-Dollar Opportunity: Why Investors Are Betting Big on AI Coding Startups

Sat, 05 Jul 2025 10:57:02 +0200

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.

Why Positive Prompts Outperform Negative Ones with LLMs?

Wed, 02 Jul 2025 17:19:32 +0300

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.

Beyond Chat: Rethinking the UX of AI Coding Tools

Wed, 25 Jun 2025 19:34:19 +0200

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:

Looking for the Odd Investor Out – Invitation to Join the Gadlet Journey

Thu, 19 Jun 2025 17:23:42 +0200

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?

Should you version control your prompts?

Tue, 27 May 2025 21:54:02 +0200

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.

From Bootstrapping to Business: Gadlet's Next Chapter

Mon, 14 Apr 2025 14:42:42 +0200

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

Mon, 31 Mar 2025 11:02:02 +0200

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.

The Challenge of Pricing a Coding Agent

Sat, 15 Mar 2025 22:25:02 +0200

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.

Testing, Learning, Building – The Gadlet Journey Continues

Thu, 13 Mar 2025 21:54:02 +0200

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.

Measuring Improvements in a Coding Assistant: A Hard but Necessary Problem

Mon, 17 Feb 2025 22:02:18 +0200

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, What, and How

Mon, 17 Feb 2025 21:54:02 +0200

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.

Building Something Big

Tue, 11 Feb 2025 18:54:02 +0200

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 Wow Effect: First Time Coding with AI

Thu, 30 Jan 2025 20:54:02 +0200

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.

Maximizing AI Coding Assistance: The Case for Minimal Rule Sets

Sun, 05 Jan 2025 16:06:18 +0200

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.

Meet Mikko

Wed, 01 Jan 2025 23:54:02 +0200

I’m a 55-year-old former business executive with a passion for bridging the gap between technology and business. Over the past 30 years, I’ve dedicated my career to business development, new business models, and software integration, always striving to create cost-effective ICT solutions that maximize productivity and impact.

One of the greatest challenges I’ve faced is fostering clear and meaningful communication between business leaders, end users, suppliers, and developers. This challenge has shaped my mission: to ease these barriers and help people and organizations produce and acquire software that truly matters.

Meet Rolf

Wed, 01 Jan 2025 23:54:02 +0200

Hi, I’m Rolf. Let me share a bit about my journey in technology.

Growing up, I was surrounded by the fascinating world of computers. My mom was a pioneer in the 1960s, working with those massive, room-sized machines. By the 1980s, she was teaching others the emerging language of coding. At just 9 years old, she taught me to code, and I was not only playing games but also diving into their inner workings. Having a computer expert as a parent was a fortunate beginning to a lifelong journey in technology.

A Milestone in AI and Software Development: The Arrival of Gadlet

Wed, 01 Jan 2025 22:41:29 +0200

As an experienced corporate executive with decades of experience in software development, integrations, and new business model creation, I’ve seen technological revolutions come and go. But today marks a momentous occasion in my personal journey and our collective exploration of what’s possible when artificial intelligence meets software development.

I’ve been privileged to participate in an ambitious start-up project that dives deep into the seemingly endless possibilities of AI in software creation. This initiative is not just about AI as an assistant but about turning it into a robust coder capable of handling real-world software development tasks. Over time, our talented team of developers has iterated through numerous versions of the tool, shaping it into something remarkable.

How to Create Your Own Coding Assistant

Tue, 31 Dec 2024 13:48:18 +0200

Unleash the Power of AI: Build Your Own Coding Assistant

Ever dreamed of having a tireless coding partner that understands plain English and writes code for you? That’s exactly what a Coder Agent is - your personal AI-powered coding assistant that turns your ideas into working code.

In this guide, I’ll show you how to create your very own Coder Agent using Python. Whether you’re a seasoned developer or just starting out, you’ll learn how to harness the power of Large Language Models (LLMs) to automate your coding workflow.

First Post

Tue, 31 Dec 2024 10:42:42 +0200

Welcome to Gadlet.com

Welcome to the beginning of gadlet.com, a site dedicated to the fascinating world of coding assistants, with a special focus on our very own creation, Gadlet.

Our Vision

We are not accustomed to sharing in this manner - open and unfiltered. However, we believe this is the right approach. Transparency and collaboration are at the heart of innovation, and we want to invite everyone to join us on this journey. By fostering conversation and discovery together, we can push the boundaries of what coding assistants can achieve.