What problem does it solve?
Helps you turn messy explanations of systems, features, workflows, concepts, pages, decisions, or problems into a structurally useful account that centers on the single most load-bearing part instead of a flat list or chronology.
Core Features & Use Cases
- Primary-part reduction: Selects one semantic center using a prioritized test set (removal, governance, purpose, weight, decision) and makes the chosen test explicit.
- Typed relation mapping: Maps secondary parts to the primary part with a fixed taxonomy of relation types (dependency, input/output, parent/child, source/consumer, cause/effect, owner/owned, trigger/result, semantic grouping, constraint/enabler, sequence/timeline, contrast/tradeoff).
- Structured output + one-sentence finish: Produces a consistent explanation skeleton ending in a single forced-form reduction sentence.
- Anti-pattern resistance: Prevents common failure modes like “everything is important,” visibility/recency/sequence confusion, and symmetric “A and B both explain each other” blur.
Quick Start
Ask your agent to run semantic-center analysis on the system you are trying to explain, and require the final answer to be the one-sentence reduction plus a typed relation map around the selected primary part.