Pablo Albaladejo

Writing

Notes on building production software with AI agents — LLM evals, GEO, agentic development, and observability. Every claim links to a verifiable artifact.

GEO: how AI agents find you — a same-day case study 2026-07-18

Observability for LLM pipelines: from streams to sinks 2026-07-11

Evaluating LLM outputs in production: 22 benchmarks, a 90% gate 2026-07-04

Shipping production software with AI agents 2026-06-27

ALSO PUBLISHED

Writing on other platforms.

Stop Chatting, Start Specifying: Spec-Driven Design with Kiro IDE ↗ Kiro blog Dec 2025

Observable AI Streaming on AWS ↗ dev.to · 4-part series Feb 2025