Mediating Cognitive Structure and the Ratchet Effect in AI-Inclusive Cognitive Ecosystems

AI systems increasingly operate as cognitive ecosystems of humans, models, tools, and institutions, even when they are built and evaluated through model-centric frames. Drawing on distributed cognition (Hutchins, 1995a; Hollan et al., 2000) and recent work on externalization in LLM agents (Zhou et al., 2026), we argue that cognitive ecosystems provide a valuable unit of analysis for understanding and designing intelligent systems, where the key design target is mediating cognitive structure: the artifacts and arrangements through which an ecosystem holds and conveys task-relevant information. A trace, draft, script, research synthesis, protocol log, vision document, or test suite is mediating cognitive structure as soon as it participates in the ecosystem’s reasoning; it need not first become formal or stable.

Mediating cognitive structure stabilizes through uptake — through being consumed and relied on by downstream work. It can be strengthened through deliberate acts of validation, specification, or declaration, or through repeated use alone. Embedding into surrounding workflows, toolchains, and routines is how a stabilized structure becomes a material dependency of subsequent work, as when a typed protocol becomes the interface every later handoff is built around. Stabilization is a scoped, gradient, and reversible status conferred by uptake, never a terminal or global property of the artifact itself. Downstream work treats some version, claim, interface, routine, or artifact as a floor for a particular use. A ratchet effect occurs when stabilized structure persists across iterations in ways such that later exploration begins from a higher baseline rather than re-deriving what has already come to rest (Tomasello, 1999; Sterelny, 2012; Henrich, 2015). One engineering paradigm within this framework is deterministic infrastructure: validated artifacts that replace LLM regeneration on the production path, illustrated through a worked scientific-practice case. This unit of analysis surfaces a design opportunity often obscured by model-centric frames: the deliberate engineering of ratchet effects.