About
I'm Xabier Ariznabarreta. Born and raised in Madrid. I did high school at Trinity College in San Sebastián de los Reyes and now study AI Engineering at Universidad Francisco de Vitoria.
I started building AI projects at the beginning of my second year of the degree and shipped my first production agent a few months later. Since then I've sent several to production: commercial agents integrated with Salesforce, MCP servers with security-review loops, Android field assistants, multilingual institutional tooling.
The work was useful. It was also a teacher. The bugs were instructive, the customers were patient, and the experience showed me where the bottleneck is — not in the engineering, but in the science underneath.
So I'm pivoting to research. Working on my first empirical paper (an ablation study of agent-harness components), going through ARENA in parallel, and using this site as the public notebook for both.
What you'll find here
Four kinds of posts:
- Technical deep-dives — rigorous explanations of LLM concepts, transformer internals, mech interp, eval methodology.
- Research notes — work-in-progress on the harness-ablation paper.
- Production lessons — honest case studies from systems I've shipped, expensive mistakes included.
- Meta journey — reflections on the builder-to-researcher pivot at 19.
Elsewhere
The links above are the canonical me. If you see a Xabier Ariznabarreta account somewhere that isn't linked here, it isn't me.