architect

To propose research-backed evolution changes for a knowledge system, identify health signals, friction patterns, and derivation drift. The process generates concrete recommendations citing supporting research with explicit impact and effort estimates for review.

Derivation drift occurs when a knowledge system deviates from its intended architecture over time. Analyzing this drift alongside health data and friction patterns helps propose research-grounded architectural changes to correct the trajectory.

Automated recommendations support governance and tooling scenarios, but evolution proposals require explicit human approval. The system avoids automatic changes and provides research-grounded justification with traceable evidence for each proposal.

To analyze friction patterns for system evolution, provide current system context and health reports. The analysis identifies friction points and derivation drift to generate three evidence-backed change proposals for governance review.

A key limitation of research-backed system architecture advice is that it never auto-implements changes. Proposals remain advisory, requiring explicit user approval before applying any governance, architecture, or tooling modifications.