great article, mostly focused on coding agents but applies elsewhere impo. aligns w a lot of my prior thoughts: - agents need scaffolding, n…

great article, mostly focused on coding agents but applies elsewhere impo. aligns w a lot of my prior thoughts: - agents need scaffolding, not just smarter models - failures should become durable improvements - tools/functions should be small, reusable, and logged - execution environments matter - tests and deterministic checks are essential - memory should live outside the model - agent systems should improve through use

Source: Yohei Nakajima (X) | 2026-05-11