Product engineer · AI in development
Requirements, architecture and implementation — done by one person with AI agents. Industrial analytics, internal tools, automation of routine work.
The data is almost always already there: devices keep writing, the database keeps growing, exports pile up. What is missing is an answer to the manager's question, in plain words, on a single screen.
Decisions go into PRD and ADR documents, so six months later the team is not arguing the same point again. AI agents are in my daily work as a tool, not as a replacement for understanding the problem.
No documentation retellings: only things I shipped to production myself, or dropped after checking.
Four years in applied AI. Before that, a large Russian retailer of over a hundred thousand people and an agricultural company of fifteen hundred: using data to improve how cleaning, delivery and the stores themselves worked.
Today I work at Workwatch, a contractor at a petrochemical plant. I look for value in the low-level processes nobody examines, and I build agents that automate production tasks in code.