About

I'm Sertan. I lead an engineering organisation and still build every day.

My first research was on augmented reality and computer vision in the mid-2000s. The ideas were right, the timing was early, and I chose an engineering career over completing the PhD. More than fifteen years of building and running distributed systems followed, across automotive, online retail, location intelligence and embedded finance, where I currently lead engineering. In 2024 I closed the loop and completed an MSc in Artificial Intelligence at the University of Bath, with distinction.

My focus now is the practical adoption of AI in software engineering: agentic development workflows, MCP servers, spec-driven development, and the leadership decisions that determine whether any of it actually pays off. The through-line in my own work is a conservative autonomy model, where deterministic systems own the loop, the LLM advises, and a safety policy validates every action.

Much of my recent building is done by coding and review agents with me on the steering wheel: I set the architecture and the specifications, decide what must stay deterministic, choose the review lenses, and judge the evidence before anything merges. I do not measure my authorship by the lines I type; I measure it by whether I can stay accountable for the system that results.

I write about it because most of what's said about AI and engineering is either hype or doom, and the useful version is neither.

If you want to test that claim, start with the series: AI and the Industrial Revolution, best read in order.