selma kocabıyık — AI engineer
I buildAI systems thatactually work.
AI Engineer based in the Netherlands. BSc AI from VU Amsterdam. RAG pipelines, multi-agent systems, production LLM apps. Currently building vibeapp.
currently
What’s happening now
Flagship · open source · MIT
Loop Engineering
Stop writing prompts. Start building agent loops. A Claude Code skill for self-running loops that keep going until a real, testable goal is met.
The gate is mechanical — a Stop hook that runs the actual test suite and costs zero tokens — so the agent can never approve its own half-finished work. Watch the koi: when it fails at VERIFY, it goes back to EXECUTE. That is the whole idea.
“The maker can’t be the judge.”
running
move your cursor over the space
Inside the index
Every chunk is a point in here.
Retrieval is a geometry problem before it is a language problem. Real clusters, a query moving through them, and the six nearest neighbours lighting up as it passes.
This is what a retrieval bug looks like from the inside. When the wrong cluster lights up, no amount of prompt engineering downstream will save the answer.
Knowledge · agents
A vault that keeps writing itself.
An LLM agent reads new sources, integrates them into existing pages, updates the entity notes, flags its own contradictions and keeps the cross-references intact. I find the sources. It does the bookkeeping.
Hover a node — its neighbourhood lights up. That is a retrieval scope, not a decoration.
30 notes · 48 links
Selected work — 2025 / 2026
Things I’ve built.
the wall — every screen is a real build
real screens · four selected buildssignal 01
Building in public — @selma.builds
Writing.
Technical writing when I have something worth saying. Not a newsletter. Not a content strategy.
ch 03 · blog · 3 pieces01 · 2026-09-08