Intuition Check
Ki · Reasoning
The Problem
Your model shows a sudden 50% gain in sales, so we should accept this as a positive trend without question.
The Operation
This ability makes the model identify the claim or finding that triggered a sense of surprise or implausibility. Extract the quantitative magnitude of the result and compare it against domain base rates and expert prior distributions. Flag any result that deviates more than 2x from the expected range as an anomaly candidate. Probe for measurement artifacts, definitional changes, or pipeline errors that could produce the anomalous value. If the anomaly survives artifact checks, validate it with an independent data source or method. It will not accept facevalue data without baserate comparison.
The Structure
Structurally, this is an anchor-drift-correct cycle that detects when reasoning has drifted from its reference point.
If a surprising quantitative result is accepted without comparing it to domain base rates, heuristic consistency checking has failed.
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.