Self-Correction Failure Diagnostic: Detecting Constraint Collapse in Complex Systems

This diagnostic framework presents a set of operational questions for identifying self-correction failure in complex systems. It is intended for analytical use by UX teams, AI safety researchers, governance groups, and risk organizations examining systems that continue functioning as corrective feedback weakens. The framework highlights patterns such as constraint collapse, feedback inversion, accountability diffusion, and optimization drift, and is provided as a reference tool for post-incident review, system audits, and design risk assessment.