As a kid playing soccer, this was the big disappointment: you scored a goal, only for the referee to call offside. You thought you were behind the invisible line … but apparently not. This maps well to our third TODO when working with autonomous agentic systems (remember, the first was about circuit breakers and the second about fallbacks): guardrails and monitoring…

Imagine you plan a city trip. You set a budget. A date…

Training an AI model is hard. It requires skill and persistence. And the methods evolve constantly in this fast-moving field…

In the last Workflow Wednesday, we talked about interruptibility by design and promised more todos when building agentic systems. Here is the second: fallback and override. Suppose you introduce transport robots in a warehouse…

Before you consume something powerful, you check what’s inside. AI skills are a recent invention. And marketplaces to share and reuse skills formed almost immediately…

Today’s AI is energy-intensive. I get many questions about it. And it is true: today’s AI is largely a brute-force approach…

Remember the market drop on May 6th, 2010? The Dow Jones lost 560 points in four minutes. Perceived risk spiked, market participants pulled out, and a stampede followed, temporarily annihilating roughly one trillion dollars in market value…

Remember when you played Minecraft for the first time? Building in 3D felt simple and endless. I assume few would have guessed that this game would become a serious training and evaluation ground for AI agents…

Chances are, you started the year with good resolutions. I applaud you. And maybe you acquired a scratchbook to journal your journey…

Remember when you were a child on Silvester and were allowed to light a small firework for the first time? Chances are you were in awe, a little scared, and fascinated by the light at the same time. You kept your distance, careful about the splinters - and drawn to it…

Remember how you learned to ride a bike? With the help of your parents or a friend, you acquired a skill through repetition and feedback (well, falling, actually ;). Skills are also the AI trend this week…

Most of us use ready-made LLMs - they’re reliable, versatile and tested. But sometimes, you need to train your own. Andrej Karpathy’s llm.c shows how to train a small model on sequences, like lines from Shakespeare, by turning each word into a number and learning which comes next…

When ants search for food, they try paths, explore, and when they find something, they let the others know. A simple tactic. If you’ve ever had ants in your kitchen, you know how effective it is…

“Optical character recognition (OCR) is a solved problem.” That’s a common conviction in the industry: it is often treated as a mature technology. A commodity we can stop worrying about…

Is today’s AI imperfect? Yes. Should we ignore it…

After months of writing, editing, and refining … my upcoming book The Modern AI and Data Platform is almost here. It’s a collection of 42 short, fun-to-read chapters capturing everything we’ve learned about building powerful, future-proof platforms that create real value from data and AI, including the human side: culture, collaboration, and clarity. The book is structured in three parts: why AI belongs at the core, what defines a modern architecture, and how to turn principles into practice…

When you open a mechanical watch, the first thing you notice is motion: dozens of moving parts. A marvel of alignment. Gears, springs, and jewels in perfect interplay…