Engineering notes
Author observations, technology reviews, case breakdowns, and other ideas worth sharing.
What to Do When the Client Brings Ambiguity — Undefined Requirements?
There's a type of client every architect knows: they arrive with an idea, enthusiasm, and the phrase "you're the architect, that's what I'm paying you for." Formally the task sounds like "build me a project," but behind it lies emptiness: raw material, fragments of thought, no spec..
How I Architect Projects on a Node Basis, and Why It Works
There's a moment in designing AI systems when a document stops working. A diagram in a PDF, thirty pages of text, sections with subsections — all of it looks solid until real work begins..
AI Engineers — Elite Builders of the Future. Do They Have Moral and Ethical Requirements?
While humanity argues about whether machines will rise up, something else is happening quietly: a small group of people is getting its hands on tools that no generation before them had. AI engineers and architects today find themselves in a position history has no ready analog for — not
Where the Prototype Ends and the Product Begins: The Boundaries of AI Architecture
A working screen is 15% of the product — the rest is underwater. Six layers that never appear in a demo, yet they are precisely what separates a prototype from a product — and precisely what you are paying for.
When a Business Only Needs Architecture — and How to Hand It Off to Another Team
Passing it along. The architecture is ready, the documentation is assembled, the data model is drawn, the backlog is laid out — now the development team has to pick it up and take the system to production.
What to Look For When Hiring a Specialist for a Complex, Long-Term AI Project
The market for AI specialists today is arranged so that resumes look almost identical, while the results come from people with completely different profiles. Skills, credentials, experience, education — all of this certainly provides some confidence, but...
AvtoUM Case Study: Architecture and Development of a Digital Employee
Some projects begin with a spec. Others begin with an observation. AvtoUM was born from the second kind: a business already pays for its website, for ads, for traffic — and yet a gap yawns between the visitor's first question and the actual lead..
AI Coding Doesn't Replace the Engineer: Who Owns Architecture, Tests, and Production
AI writes code faster than I do — and that changes nothing about who owns the outcome. An honest breakdown: where assistants carry research, routine, and documentation, and where the territory begins on which there is nothing left to delegate.
Weekdays and Holidays of a Data Engineer Prototyping Enterprise AI Assistants
There's a profession that's barely mentioned at conferences, described in three lines in job postings, and yet nothing launches on a project without it. It's the Data Engineer who builds prototypes of enterprise AI assistants..
How to Test an AI Agent Before Launch: Scenarios, Boundaries, and an Error Log
94% of answers "accepted by the user" — yet the agent promised nonexistent refunds for a week. Demos show capabilities, evaluation shows boundaries. How to build a test matrix, refusal scenarios, and an error log so you don't roll back a pilot.
A Resume Is Not a Competency: Why the Market Needs a Skills Graph and Explainable Match
The classic resume was conceived as a tool for honestly telling your story. Today it has turned into a genre of fiction: every second candidate writes it for a specific job posting, every third employer reads between the lines..