Notas
Notas sobre decisiones de producto, evaluación de IA y sistemas operativos. Artículos escritos en inglés.
Why did candidates who said yes more often make worse matches?
Acceptance alone selected weaker two-sided matches. I reconstructed historical decisions, compared selection policies, and implemented composite selection with simulation limits made explicit.
product-decisions · backtesting
2 min de lectura
What should an AI do when one request asks for three things?
A feedback pipeline lost explanations when it completed fixes. I used labeled requests to design ordered intents and separate clarification and completion drafts.
ai-workflows · product-decisions
2 min de lectura
How do you know when an AI judge is worth trusting?
An AI judge disagreed with human reviewers. I designed a feedback loop around approved criteria, fair replay, human calibration, and visible evaluation coverage.
ai-evaluation · product-operations
2 min de lectura
Why did GraphRAG lose to simple keyword search?
Graph retrieval missed more evidence than keyword search. I traced irrelevant anchors, narrowed their selection, and recovered baseline recall while preserving relationship paths.
retrieval · ai-evaluation
2 min de lectura
Why can a correct funnel still mislead your team?
A subscription funnel showed conversion above 100%. I traced the denominator mismatch and defined cohort-based calculations with visible data gaps.
product-analytics · operations
2 min de lectura