Blog
-
The AI Service Desk: Filling the L1 Gap Before You Hire for It
It starts with “just a quick question” Every product and engineering team knows the pattern. Someone pings a chat thread with “I need a new ___”, “I have a problem with ___”, or “can you check the ___”. Then comes the back-and-forth: what exactly is broken, which environment, did it ever work, what did you…
-
A feature engineering experiment from my garden
Can AI tell good Ajvar from bad Ajvar? This year, I grew vegetables, again. Nothing particularly revolutionary about that. Mostly peppers, and a few other things. Then came the inevitable question: What do you actually do with all of it? The answer, at least in this part of Europe, is obvious: Make ajvar. But while…
-
AI is not a feature strategy
A chatbot here.A recommendation engine there.AI-generated content.A predictive model.A copilot added to an existing product. It looks like progress. But adding AI to products is not the same as having an AI strategy. Features answer “what?” An AI feature strategy usually starts with a technology: “Where can we add AI to our product?” This can…
-
What actually happens inside a neural network
Most explanations stop at the diagram or jump straight to the calculus. I wanted the bit in between, so I animated it. Six minutes, eight examples. One real input travels through a five-layer network, every weighted sum resolves into an actual number, the loss gets calculated, and the error flows back through every weight. Then…
-
I built a Chrome extension so I could stop reading clickbait
My first published extension. Vibe coded, built for myself, now yours too. Every morning I do the same thing: coffee, then three or four news portals. And most mornings I end up annoyed. Half the headlines are clickbait. Of the ones that aren’t, plenty bury the single sentence that actually matters at the very end,…
-
AI Security, Explained Through the Teams Trying to Break, Measure and Control It
I recently went through a small research, asking – What is the AI equivalent of cybersecurity’s Red Team / Blue Team model? The only answer I could find seems to be: there isn’t one universally accepted model yet. But there are several emerging roles that make the AI security landscape much easier to understand. I’m…
-
AI Risk: Getting Into Production Too Soon?
There is a moment in almost every AI project when excitement starts to replace caution. The model works. The demo looks impressive. The numbers are good. Someone says, “We need to put this into production” And sometimes, that is exactly when the real risk begins. When AI leaves the laboratory I was recently reminded of…
-
The Era of Gathering User Requirements Is Over (Even in Highly Regulated Environments)
When “Good” Requirement Gathering Is Not the Problem Let’s acknowledge something upfront. In certain industries, requirement gathering is not naive. It is disciplined, structured, and deeply embedded in how organizations operate. This is not chaos. This is maturity. And yet… even here, the cracks are starting to show. Not because the process is poorly executed,…
-
AI in the API Layer: The Most Underrated Opportunity in Legacy System Modernization
When companies talk about introducing AI into their systems, the conversation almost always starts with the user interface. “Let’s add a chatbot.”“Let’s improve UX with AI suggestions.”“Let’s automate reports.” All valid ideas, but they miss the most powerful and strategic opportunity: The API layer. If your system has a well-defined API architecture, you already have…
-
AI Tokens Explained: The Real Cost of Speed, Money, and the Planet
Every time you type a question into ChatGPT, Claude, or any other AI tool, something invisible happens behind the scenes: your words get chopped up into little units called tokens. Tokens are the currency AI runs on – they determine how much you’re charged, how fast your answer appears, how much the AI can “remember,” and…
