development

At the Pragmatic Summit, I heard firsthand that Uber engineers aren’t just using AI to write code anymore, they’re assigning it work. Let’s see how that plays out.

I often hear AI terms used loosely, so I put together this guide to explain key concepts like agents, tools, and LLMs clearly.

After spending time with OpenClaw and seeing how it actually works, I’m convinced the hype is real. It shows that autonomous AI agents are finally living up to their promise.

With AI building features, teams must shift from doing tasks to orchestrating them - PMs guide intent, engineers oversee systems, designers review output live, and QA builds self-healing processes.

We’re past just making better tools: machines will do the repetitive coding, and humans will focus on guiding, judging, and architecture.

Ex-Tesla AI director now programs mostly in plain English with AI, calling it the biggest workflow change in 20 years.

To get the full power of a Deployment Pipeline, you need more than tools - you need practices that let it shine and reveal both your strengths and your weaknesses.

17 countries, 20 hours, and a lot of voice-driven experiments: Warsaw became a playground for builders testing the limits of AI, gaming, and storytelling at the Project Europe x ElevenLabs hackathon

The following is an attempt to clarify the circumstances of a production incident that happened more than 10 years ago; it is also a lesson to all of us to decouple our production servers from boilers in distant Balkan countries.

As AI coding assistants level up from autocomplete to autonomous, the real challenge isn’t what they can do - it’s how we use them wisely.

'Who could refuse that?' Turns out, almost no one - especially when faced with puppy eyes, heartfelt asks, or a desperate Pikachu. Refusing is hard, and it costs more than we admit.

Open source isn’t a free-for-all playground - it’s more like borrowing your neighbor’s lawnmower, but with a rulebook you actually need to read.

AI is helping write code and automate tasks, but until it masters true agency (think independent decision-making and goal-setting) it’s still more like a coding assistant than a full-fledged teammate.