Artificial Intelligence

84% of developers now use AI daily - mostly LLMs. They’re great for cutting workloads, but risky in the wrong spots. Here are 5 times AI shines, and 5 times it can totally wreck your work!

Textbooks are great, but let’s be honest - sometimes students need a study buddy with a sense of humor and a knack for explaining photosynthesis. This is where our AI assistant enters the scene.

The future belongs to those who ship products, not just publish papers.

The battle for the best open LLM just got a new challenger - from OpenAI itself.

According to Stack Overflow’s 2025 survey, 84% of developers are using AI tools - but 46% don’t trust the output. It’s a code-and-question dynamic: developers are coding with one hand and second-guessing with the other.

MCP and A2A are making AI development smarter and more scalable by connecting agents and tools easily - shifting the spotlight from prompt engineering to the bigger picture: context engineering.

In the age of AI-assisted development, it’s tempting to believe we’re entering a golden era where human effort in programming becomes obsolete.

For AI agents to work for you you have to train them, refine them, and ultimately build a well-orchestrated agent-to-agent system that can deliver real value.

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

Are we still designing interfaces, or are we designing people?

Infobip’s MCP is redefining how AI agents interact with real-world systems - enabling them to take meaningful actions with nothing more than a prompt.

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.

Each talk I attended and each new person I met partially chipped away at that feeling of doubt.