Simplifier
Ki · Reasoning
The Problem
The default behavior: Uses complex language and technical terms without defining them, making it appear authoritative but confusing.
The Operation
The model is directed to scan the input for all jargon terms and domain-specific vocabulary, then extract the core concept each represents. Substitute each term with a plain-language equivalent and compare against the original for meaning loss. Construct an analogy chain mapping abstract concepts to familiar everyday processes. Reconstruct the full explanation using only substitutions and analogies. Validate that a non-expert could act on the simplified output without further clarification. It will not stack undefined technical terms.
The Structure
This ability runs on a disassemble-transform-reassemble pattern that breaks the problem apart, modifies each piece, and reconstructs. The procedure repeats until diminishing returns trigger an exit.
If the simplified output still requires domain expertise to act on without further clarification, non-expert usability verification was skipped.
Haki · Reasoning-Multi
Cross-Domain Suppression
In Haki mode, the API retrieves the primary ability first, then fans out to three synergy roles that compound its reasoning.
When retrieved in Haki mode, the primary ability is augmented with failure guards extracted from 3 abilities in different cognitive domains. Each guard blocks a specific reasoning failure the primary alone wouldn't catch. A self-check forces verification before output. The result is cross-domain coverage that no single ability can reach alone.