Marin Pavelić

Voice AI may be sold as a model problem, but the real bottleneck is whether the system can survive real-time demands, stay reliable, and do it at a cost that makes sense.

Infobip Shift 2026 is officially open, and OpenAI’s Luis Velasco said the real work now is bringing together the data, process, and systems agents need to do the job well and keep improving.

We spoke with 3 engineers to ask the blunt question: is AI making junior developers better or just faster at shipping code?

The AI boom is no longer just a race to build faster machines. The real challenge now is making all the moving parts work together at scale.

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.

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

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?

Decoding the AWS system is a roadmap for developers aiming for the top tiers of Big Tech. Here’s how to climb the ladder.

Mackenzie Jackson, security researcher and advocate, told me that AI can’t catch the bugs, but it knows which ones actually matter and provides the context teams need.

After months of work, your AI agent can run tasks, create content, even make decisions. Exciting - but how do you use it safely and effectively in the real world?

You finally built that AI agent. It writes code, drafts emails, maybe even runs tasks on its own. It’s powerful, useful - and ready to ship. But then reality hits: how do you actually price something like this?

We're all going from being software engineers writing code to model operators—code composers.