This position paper argues that AI-assisted software engineering requires explicit mechanisms for tracking the epistemic status and temporal validity of architectural decisions. LLM coding assistants generate decisions faster than teams can validate them, yet no widely-adopted framework distinguishes conjecture from verified knowledge, prevents trust inflation through conservative aggregation, or detects when evidence expires. We propose three requirements for responsible AI-assisted engineering: (1) epistemic layers that separate unverified hypotheses from empirically validated claims, (2) conservative assurance aggregation grounded in the Gödel t-norm that prevents weak evidence from inflating confidence, and (3) automated evidence decay tracking that surfaces stale assumptions before they cause failures. We formalize these requirements as the First Principles Framework (FPF), ground its aggregation semantics in fuzzy logic, and define a quintet of invariants that any valid aggregation operator must satisfy. Our retrospective audit applying FPF criteria to two internal projects found that 20-25% of architectural decisions had stale evidence within two months, validating the need for temporal accountability. We outline research directions including learnable aggregation operators, federated evidence sharing, and SMT-based claim validation.

翻译：本立场论文主张，人工智能辅助的软件工程需要显式机制来追踪架构决策的认知状态与时间有效性。LLM编码助手生成决策的速度远超团队验证能力，然而目前尚无被广泛采用的框架能够区分推测与已验证知识、通过保守聚合防止信任膨胀或检测证据何时失效。我们为负责任的人工智能辅助工程提出三项要求：(1) 认知分层机制，将未验证假设与经验证主张分离；(2) 基于Gödel t-范数的保守保证聚合，防止薄弱证据导致置信度虚高；(3) 自动化证据衰减追踪，在陈旧假设引发故障前予以揭示。我们将这些要求形式化为第一性原理框架（FPF），基于模糊逻辑确立其聚合语义，并定义有效聚合算子必须满足的五元不变式。通过对两个内部项目应用FPF标准进行回顾性审计，发现20-25%的架构决策在两个月内出现证据陈旧化，这验证了时间问责机制的必要性。我们进一步提出包括可学习聚合算子、联邦证据共享和基于SMT的主张验证在内的研究方向。