Blog
Writing & notes.
Lessons from shipping agentic AI, computer-vision, and MLOps systems to production.
May 26, 2026
Why a multi-agent system beats one big agent↗
A single do-everything agent conflates requirements, design, code, and tests into one fuzzy prompt. Splitting the work into roles makes the whole thing inspectable — and better.
May 20, 2026
Building an eKYC pipeline that doesn't fall for a printed photo↗
How detection, liveness, and recognition fit together into a face-verification flow — and why the order of those three stages matters more than the models themselves.