Latest Articles

Watching AI product evolution from the sidelines makes you feel like things are going fast, but according to Anthropic's Gian Segato, that might not be the best metric.

This team was shipping production code at the same time as the MCP specification was taking shape. That is the reality of working with a technology that was evolving in real time.

When dozens of developers share the same environment and Git repository, testing changes quickly becomes chaotic. Here's how Kubernetes solves that.

A CTO with 20 years of experience through multiple tech shifts sees layoffs not as an AI effect, but as a correction after an unsustainable hiring boom. He sees AI as a reset: an opportunity for strong junior engineers, and a wake-up call for senior developers facing an existential shift in how they stay relevant.

There is a gap most engineering leaders prefer not to explore: the distance between the clarity they believe they're projecting and the confusion their teams actually experience.

The case for cutting junior engineers looks airtight at the CFO level, but wrong from every other perspective.

Twenty developers got real about their jobs: the rush of shipping something that actually works, the way a fat paycheck can make you stay longer than you probably should, and the slow death of sitting through another meeting that should've been an email.

At Devoxx UK, I spoke with Trisha Gee - author and one of the most recognized voices in the Java space - about what really happens when teams lean heavily on AI. Her take was far darker than the conference hype.

Everything you think is non-negotiable in software development, Sander Hoogendoorn's team quietly dropped - and nothing broke.

Adobe doesn't publish its engineering career ladder, but we've gathered the data to give you a clear picture.

Production incidents are a context problem. By the time an engineers understand what's happening, they've already bounced across several different tools - and the incident is still ongoing. PagerDuty thinks MCP is the fix.

A 1,000 libraries, 90% coverage, 1,700 in API tokens. Nobody typed a single test by hand.

What happens when regulators ask an AI company to explain exactly how its system made a decision?