Eduardo
García-Garzón
Head of AI · Shakers · Madrid
About
I lead AI at Shakers, a talent marketplace in Madrid. My team builds the matching and agent systems behind 15,000 freelancers and 600 companies, under EU AI Act rules. I did a PhD in psychometrics first, which taught me to measure what actually matters. Here I write about what breaks when AI reaches production.
Book a 30-min chat→Latest
More writing
- Your eval suite is a measurement instrumentOctober 9, 2026
Evals are written like unit tests and behave like psychological tests. A century of measurement theory already named the failures teams keep rediscovering.
- Benchmark contamination has an older nameOctober 5, 2026
SRE-Bench spent five thousand expert hours keeping its questions secret. Testing has handled that problem for forty years and calls it something else.
- Average adoption returns less than averageSeptember 16, 2026
Ask how the AI programme is going and you get a percentage of people. The denominator is wrong, and the mathematics of the right one is unforgiving.
Newsletter