Skip to content
How to ThinkIn the Age of AI
Principlev1PR-1116

Evaluate cognitive agents by how they contribute…

Evaluate cognitive agents by how they contribute to the portfolio's overall properties (diversification, correlation, coverage) rather than by individual performance alone, as portfolio-level risk emerges from relationships between components.

Why This Is a Principle

This derives from The behavior of a system arises from its structure… (system behavior arises from structure, not intentions) and Every system is perfectly designed to get the results… (systems are designed to get their results). It prescribes evaluating at the system level rather than component level. This is a strong principle because it's clearly derived (from systems thinking axioms), highly actionable (changes evaluation criteria), and general (applies to any portfolio of agents or systems).