AI-Assisted Engineering Should Track the Epistemic Status and Temporal Validity of Architectural Decisions

TL;DR

This paper emphasizes the importance of tracking the epistemic status and temporal validity of architectural decisions in AI-assisted engineering, proposing a formal framework to improve decision reliability and prevent trust inflation.

Contribution

It introduces the First Principles Framework (FPF), formalizes evidence aggregation with fuzzy logic, and demonstrates the need for temporal accountability in architectural decisions.

Findings

20-25% of decisions had stale evidence within two months

Validated the need for temporal accountability in decision tracking

Proposed formal criteria for evidence aggregation operators

Abstract

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 G\"odel 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.