Defining AI-Native Systems: Autonomy as Revision Authority
This work clarifies a vague term for system designers and researchers, offering a foundational framework for classifying and building AI-native systems.
The paper provides a precise technical definition of AI-native systems, defining them by the AI's revision authority over system implementations rather than model capability, and requires an escalation detector, verification, and verified fallback.
AI has begun to write systems code: agents now synthesize, verify, and deploy system components. Despite this shift, "AI-native" remains a marketing term with no precise technical definition. This paper gives it one. We define AI-nativeness along a single axis---authority over the system's own decisions rather than by the capability of the underlying AI models. Building on a decision-level model of a system, we distinguish occupancy (who executes a decision) from revision authority (who may change it), organize revision authority into a ladder---self-tuning, self-rewriting, self-architecting and define a system as AI-native when an AI autonomously rewrites the system's own implementations. The definition further requires an escalation detector, a verification procedure, and a verified fallback, while leaving purpose and correctness human-owned.