Archive
2026
-
Why Coding Agents Cannot Replace Experience Engineering
Why coding agents cannot replace software engineers. Building digital products requires client discovery, domain expertise, interface design, and human friction that AI cannot duplicate.
-
The Dark Factory Trap: Finding the Sweet Spot for AI in Engineering
Why fully autonomous dark factories risk model collapse, and how human in the loop pipelines keep digital products reliable, accessible, and clean.
-
Why the Dark Factory Fails for User Interfaces
Fully automated AI coding is popular. But when we build user interfaces, a dark factory fails. We need human empathy and unique brands.
-
EU Pay Transparency Directive: A Shift in Hiring Culture
The EU Pay Transparency Directive comes into effect in June 2026. This post explores its impact on recruitment workflows, candidate rights, and company culture.
-
The Myth of the Code Reader: Why AI Agents Are the Better Senior Engineers
Many think senior developers will only read and review AI code in the future. This is wrong. With good tooling and files like decision.md, agents learn faster than human teams.
-
Engineering Excellence or Brain Rot? The AI Development Paradox
Why AI in software development needs more than just a prompt. Lessons from legacy code, greenfield success, and the investment required for a clean baseline.
-
The hidden cost of vibe coding and AI agents
AI agents help us code fast. But "it works" is not the same as 'it is good'. We look at real risks for security, quality, and accessibility in 2026.
-
Prompting is not everything — Why the tool matters
I tested Claude, Gemini, and Copilot with a "Zero-Shot" CV generator task. The results show that a good prompt needs a strong engine to work.