Article
An IT Firm Quoted €50,000. Can Claude Code Build It in Two Hours?
One hour. Fifty-five minutes.
That is how long it took me to program something a Czech software firm had quoted at over €50,000. I did it with Claude Code.
A working tool that the company really needed.
What Is Claude Code?
Claude Code is an AI coding agent from Anthropic. It runs in the terminal, reads and writes files across the whole project, runs commands, handles your Git workflow and writes the code step by step, based on how you describe what you want. It is not a chat window that hands you a snippet of code to copy. It is an agent that builds the tool for you.
That is the difference most people outside software development do not yet understand. When I tell them I made a program or an app in under two hours, they picture me typing questions into a box. That is not what happened. I described the tool, the agent proposed a plan and began writing and testing real code. I checked the output to see whether it worked the way I wanted.
The short answer to what Claude Code is comes from what it let me do: replace a month and a half of quoted agency work with a single afternoon. The full story is further down this page.
How to Use Claude Code
It is simple. You install it, run it in the terminal or through the app, and tell it in plain language what you want. The skill lies in defining clearly what you want and in recognising when the agent is wrong and is building something that is not what you had in mind.
What I have learned from using it on real projects:
- You need a clear idea. My only input when building the €50,000 tool was a clear idea of what it should be.
- Give it context. Most of the value lies in preparing the material and in making sure the agent keeps its memory. I have written about training an AI agent that learns between tasks, so that it does not start from zero every time.
- It is worth realising that you have complete freedom in what you create. You do not have to settle for solutions from other providers, which are mostly paid. With Claude Code, I built my own analytics system, exactly the way I need it.
Claude Code vs ChatGPT
This is the comparison most people reach for, and it mixes up several things. First, ChatGPT and Claude as chat assistants are conversational. You ask, they answer. Claude Code is an agent built on Claude that writes code on your computer. Comparing Claude Code with the chat version of ChatGPT is like comparing a programmer with an adviser.
ChatGPT has its own tools that are equivalents of Claude Code. The choice is more about what suits you better. I have also tested running local models on my own computer and written about the limits of local AI models. After my experience with them, I moved fully to Claude Code.
A €50,000 QUOTE FOR A SIMPLE PILOT
The request came from the company's management. A tool that would make it easier for customers to find their way around the website and through a purchase. The scope of the project was specific enough to be defined.
I took over a conversation with a Czech software firm. My colleagues had started it but did not have the capacity to continue.
I asked for a rough price and a timeline. Not a binding offer. Just a range. Something to plan with.
Their answer was one sentence I will remember:
"We cannot give you an estimate, not even a rough one."
To give an estimate, they explained, they would first need to carry out a paid analysis. Two thousand five hundred euros. To examine the problem properly.
I refused the analysis.
A MONTH AND A HALF OF WORK: FOR WHAT
Later in the conversation, without any paid analysis, the number came out anyway.
About a month and a half of senior work. Over €50,000 to launch a simple pilot.
A simple pilot.
For more than fifty thousand euros.
Five years ago, I would have taken that offer to the company's management. We would have weighed it against an off-the-shelf solution.
Now there is a third option.
BUILDING IT WITH CLAUDE CODE IN UNDER TWO HOURS
I came to the IT meeting with a short presentation. I set out the options: continue with the external firm we had already been talking to, or build it with an AI coding agent.
The same afternoon, I programmed it.
The agent proposed a plan, started implementing it, and within the first few minutes something was already working. The rest was fine-tuning: adding features, improving behaviour, handling the edge cases I noticed while testing.
The only thing I brought to the build was a clear idea of what the tool should do.
Not a detailed specification of every feature. Just a clear idea of what the tool should do.
And it turned out to be enough.
Join the Library
Full access to my findings, personal stories, and what I learn from the people I meet.
Join the Library · €29.99 per year How to get your first job with no experience… How a small business, creator or politician can be… What should I study in the age of AI?… I Left My Job for Several Months to Read… How I Fell in Love With Her, at First… How do you stop depending on social media? Can…Get the full article by email and feel free to reply if you want to discuss it further.
Summary
Common questions on this article's topic
What is Claude Code?
How do you use Claude Code?
What is the difference between Claude Code and ChatGPT?
How much does custom software cost?
Can you build an app with Claude Code in a few hours?
Will AI replace software companies?
Related articles
Over the past few years I have interviewed hundreds of candidates for marketing specialist, advertising specialist and data analyst roles. I often invited beginners to interviews with a practical task: people who had only completed a course, had studied the subject, or had tried the work on a small project of their own. I saw in them the motivation to develop in the field.
It cannot be done with 100% certainty. When I wrote about the dead internet theory, I wrote that we will no longer have certainty online and that for every verification tool there will be a tool that fools it. This is still true.
I see a lot of AI fatigue around me, loss of motivation and burnout. One example is a colleague who is leaving her job and says she plans to leave the digital marketing industry altogether.
More articles
Are you a content creator playing by the rules of YouTube, Instagram or Google? Are you a small business owner whose business model depends on how often Amazon recommends you, how expensive Facebook ad impressions will be or how expensive Google Ads clicks will be? If all or most of your contact with your audience or customers depends on a big platform showing you to them, you are not in a strong position.
The development of artificial intelligence changes how we look at which paths in life make sense. Which studies and which profession to choose.
It was Thursday, 31 March 2022, when I handed over the last of my responsibilities to my colleagues, closed my laptop and went to the library. I left my job for several months and immersed myself in philosophy. And I am immensely grateful for it. Today I am, like most people, on a merry-go-round, and it is hard for me to stop and think about the fundamental questions of my own life.
It was September 2023. My life, my work, everything was completely different from now. It was simpler. I owned almost nothing. I needed to film an advert, I went up to a floor inside the company where the product I needed for that advert was, and there I noticed her for the first time. She laughs at me when I describe it like this, but at that moment the universe told me, that is her.
How and why I am gradually leaving social media and the big platforms. When I read that Meta is testing a new way to charge for organic posts that link outside its platform, it confirms how right I was to become steadily less dependent on the big platforms and on social media. It does not mean I have left them completely. It means that whether or not I stay in touch with my readers depends on them less and less, and today almost not at all.
One of my family members described a firm that has its data in several different tools, and its employees still join it by hand, in spreadsheets. That is the ordinary state of firms. When somebody tells such people not to do it by hand and to use AI, they will not understand. Most firms do not even have the basic connectors between the tools they use. These firms need help with AI transformation.
The same task, two models. Fable 5 against Opus 4.8. On paper Fable is the better model, with a larger context and stronger specs. And still it lost. Opus handled the task with a single round of checking for 721,000 tokens, while Fable needed nine rounds and burnt through 2.78 million tokens. The difference was not in the model, but in how I set the task. And I know it, because I measured it.
A few weeks ago I installed a small local AI model on my laptop that watches a live camera feed. I turned the webcam on in the dark, and in near total darkness it recognised me and the objects in the room. That such things exist, I have known for a long time. What opened my eyes was the accessibility. I installed it in one prompt, free, and it runs entirely on my machine, sending data nowhere.
Seventy per cent. That is where the first AI output begins, even when you give it the full company context and the best examples from the past. We are talking about the kind of output that cannot be defined programmatically. It is more complex. Often it is creative work. On one repeated type of output I reached eighty per cent within a week. Every further percentage point is harder than the one before.
I once wrote about building my own privacy-friendly analytics tool. It had bot detection from the first version, yet it was not enough. Direct visits took a strangely high share of my traffic. When someone claims that 20% of their visits are bots and 80% are humans, I used to think the same. Today I would say the opposite ratio is closer to the truth. This is how I got there.
I have Heidegger and my notebook beside me. I am asking where all of this is heading, where artificial intelligence is taking us.
Four days in Catalonia. No computer, no AI, almost no social media. I bought this notebook so that I could write down what I would think about, and what I would come across and learn on the trip.

