Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. DO NOT use for design rationale or history (use why instead), or for proving a change is safe to ship (use blast-radius instead). Triggers: how does X work, walk me through X, where should this live, critique this architecture, whats wrong with this design.