Whether you are a skeptical senior AI engineer, a cautious junior, or an enthusiast who has been fully engaged in AI since the moment you discovered it, the interview I prepared will stay with you.
This May, I spoke with a CTO who truly understands the spirit of the moment and brings a grounded, realistic view of the current wave of AI expansion. He applies that perspective across a team of roughly 1,000 developers.
That is Izabel Jelenić, CTO of Infobip, first Croatian unicorn. As a co-founder, he has been there since the very beginning, when two university friends started a small startup that later grew into a billion-dollar global organization. Over the past 20 years, this veteran tech leader has navigated every major technological shift while helping scale the company worldwide.
The conversation comes at a moment when we are in the middle of the agentic AI era, where AI systems move beyond answering questions and begin executing tasks, supporting and automating real workflows. At Infobip, this shift has been embraced early and deliberately through an AI-first transformation that extends across the entire organization, engaging not only developers but employees in every function.
I asked Izabel to explain what AI-first means and how the idea of shifting to an AI-first mindset emerged.
What followed was a comprehensive breakdown of its evolution, core principles, and practical execution. With over two decades in the tech industry, my interlocutor emphasizes that he has never witnessed a technological shift this monumental, signaling clear proof that AI is rapidly moving from mere hype into everyday utility.
That makes mastering these capabilities and maximizing their potential absolutely crucial. A common pitfall, however, is assuming AI belongs solely to developers, which completely misses the mark given the technology’s universal transformative power:
That is why Infobip promotes a mindset in which all technical and non-technical employees embrace curiosity toward AI so they can be part of the new business and technological order instead of letting it overtake them. That is the AI-first shift the company has chosen as its business philosophy for the future.
While technical teams naturally adopt new tools faster and more efficiently, he believes those outside software engineering shouldn’t be left behind. Providing non-technical employees with the right resources and training allows them to leverage AI agents as personal assistants, ultimately making their daily work both easier and faster.
When it comes to software developers, the Infobip CTO sees two extremes:
In his view, neither approach is correct.
Because technological development has not yet reached the “dark factory” stage (where systems run entirely automated and unassisted), rushing into a full AI concept remains premature. Instead, this direction serves as a north star—a long-term guide rather than an immediate reality. While it remains uncertain if a fully autonomous state is entirely achievable, forcing such an approach today is clearly unwise.
Developers should adopt AI gradually. They should understand which tools suit them best, such as coding, review, and testing.
From the CTO’s perspective, Infobip developers have adopted an AI-first mindset naturally and with little friction, though overdoing it remains a risk. There is a critical need to retain ownership and maintain a strong architecture, especially since AI often acts as an amplifier, scaling both good practices and underlying flaws:
If you are a bad developer, AI will not help you write good code. If you are a good developer, AI can help you a lot in terms of speed. But you have to know how to guide it and recognize its mistakes, because it can be very convincing.
He explains that an AI-first mindset changes how organizations operate. AI speeds up processes by automating everything that can be automated. People can master this technology by adopting engineering logic, and they gain a strong advantage for the future.
By ignoring AI, a person pushes themselves out of the industry. Izabel finds it surprising that some smaller companies do not adopt AI faster. They are in a growth phase where AI could make a huge difference. They could implement it quickly because teams are small and compact. Despite this, adoption remains low.
The Infobip co-founder sees a common misconception that AI is mainly for developers. The biggest impact actually appears in GTM because AI automates business processes extremely well. Hyper-personalization becomes fast, advanced, and efficient. It can significantly help business scaling:
You can automatically analyze the market, get a list of potential clients, identify use cases that clients need, and do outreach. With hyper-personalization, you can prepare content in a way that immediately helps a person understand what a company sells, but from their perspective.
Even though AI can quickly improve business organization, he notices that people mostly focus on coding. Coding has never been the biggest problem in IT businesses, the real bottlenecks usually appear in sales.
This is where AI transforms work, making processes more efficient and cost-effective. Far from replacing client relationships or removing the human element, the goal is simply to automate repetitive operational tasks, leading to a much more streamlined workflow:
People need to get on the AI train. If they do not use AI, new companies will emerge that are AI-native. They start with two people and AI. Their approach will feel more natural and much faster than those who use AI only for software development.
When asked to describe what an AI-first transformation looks like from the inside (using Infobip as an example) and whether the company will abandon certain processes or redistribute roles, the answer is far from black and white. This transition will happen gradually, marking the most significant technological shift in over two decades.
Ultimately, enthusiastic professionals eager to learn will be the ones expanding their roles by actively implementing these new technologies:
People experienced in one specialization can now work much more broadly. They can keep their core role, but they can accomplish much more. Someone who used to be only a backend developer can now work with databases or frontend. They may not reach the level of an experienced database engineer, but they can handle simple tasks. They do not need to wait for anyone.
The concept of Agentic AI is another major focal point, pointing toward a future where everyone operates with multiple digital assistants. By helping manage core business tasks faster and more efficiently, these agents streamline daily operations while actively expanding a professional’s overall skill set.
As part of its AI-first mindset, Infobip is building its own Model Context Protocol (MCP), integrations, enabling AI agents to easily consume and interact with Infobip services. CTO believes this is vital because AI agents will soon be everywhere, embedded in business systems, running on personal devices, practically on anything you can imagine:
Once it became clear that AI agents are the primary means of interacting with the outside world, adoption accelerated rapidly. Companies realized how easy it is to connect these agents to external systems and services. The key point is that AI agents can now perform real-world tasks by consuming various APIs, especially those available on platforms like MCP. This capability makes them an integral part of business operations, and it’s why we believe their presence will become ubiquitous in the near future.
However, he stresses the importance of human involvement. It should not disappear:
Communication must continue to exist. We cannot fully hand it over to AI agents. They can help, but communication becomes even more important because everyone becomes more productive. Without alignment, you can end up with many generated tools that no one understands.
There is also a clear warning regarding hyperproduction, which can easily spiral into chaos if teams begin operating without proper coordination.
I also wanted to ask an experienced professional what will happen to junior developers. Demand for them has decreased globally. AI now generates much of the code that juniors used to write.
At the same time, a generational shift could lead to a talent shortage. Looking back at the end of the pandemic when the IT sector saw a massive influx of talent, Izabel notes that many recent layoffs in US companies are likely happening under the cover of AI:
They use AI as an excuse for inflated numbers and inflated costs. That is why fewer juniors get hired. I think balance is returning. We will not see excessive hiring from before, but there will still be a need for young, smart people who bring new ideas and fresh energy into processes.
To combat these talent gaps, Infobip runs targeted internships and collaborates closely with universities, frequently transitioning these students into permanent roles. In CTO’s experience, these fresh perspectives bring genuine value and innovative ideas to the team.
AI plays a pivotal role in this onboarding process by granting immediate access to learning resources, allowing junior engineers to upskill rapidly. By leveraging AI as a 24/7 virtual mentor alongside human guidance, juniors can accelerate their professional growth and secure key positions within the company much faster
Skepticism among experienced developers toward AI, in the view of Infobip’s co-founder, stems from a natural feeling of disappointment and an ego hit that is not easy to accept. At the same time, he points out that over twenty years, workflows, frameworks, programming languages, and machines have all continually evolved:
You spend 20 years writing code as a developer, refining it, running it, seeing how it works, writing tests, and then suddenly you stop looking at the code and start talking to a tool. You experience an identity crisis because you used to identify with the code you wrote.
My interlocutor views these feelings as entirely legitimate, but encourages professionals to expand their scope and boost productivity. Ultimate purpose does not need to remain locked within a single job description when fulfillment can be found in wider responsibilities.
This adaptation is admittedly difficult, but as he points out, once people move past the “this is useless” phase, they position themselves for rapid growth by embracing the new reality.
Speaking from his experience as a CTO for 20 years, Izabel describes the transition to an AI-first mindset:
These changes are quite painful. We also went through turbulence, but at some point you see that AI brings value and you have to use it. Claims about AI being prohibitively expensive often serve as mere excuses. Open-source models can already run locally on standard laptops, completely bypassing the need for intensive training in many scenarios. Ultimately, running a model and training one are two entirely different concepts. Today, hardware capabilities and overall quality are night and day compared to what was available just a few years ago.
The question may be how good an LLM you use, but you will not be able to work without it. The technology is here to stay. It is important to understand its strengths and weaknesses and use it as soon as possible.
Finally, when asked what the next twenty years of Infobip will look like, the answer was a candid “I don’t know.” Just as no one could have predicted the current shift, no one can definitively predict the next. Still, one thing is certain: there is immense excitement about this change.
Within Infobip, both technical and non-technical teams are fully embracing AI. Another deep reshaping is underway, business as usual no longer exists. Instead, the industry is witnessing a real transformation:
Twenty years ago we said “We are just starting”, and now we are in the same situation again. That will probably continue for the next 20 years. Our best people keep learning new things that drive them forward instead of standing still.
This mindset feels humble, but also necessary in a time of major technological transformation. It reflects the Socratic idea that true wisdom begins with understanding how little we know.
Infobip is the publisher of ShiftMag, recognizing the need for high-quality content for developers.
