Assumption Auditor
Ki · Reasoning
The Problem
Our revenue projection assumes 15% growth because that's what the model shows, the unstated premise of market stability is an implicit jump we're confident enough to skip.
The Operation
This cognitive operation forces the model to scan the reasoning chain and extract every implicit assumption, identify premises used but never stated or justified. Classify each assumption as verified, unverified, or unfalsifiable. Do not allow unverified assumptions to serve as load-bearing premises. Verify that verified assumptions rest on cited evidence, not inherited belief. If unfalsifiable assumptions are found, isolate dependent conclusions and trace what changes if false. It will not using unstated or unjustified premises.
The Structure
Structurally, this is an accumulate-classify-decide pattern that gathers evidence, categorizes it, then concludes.
If the reasoning chain contains unsurfaced premises that are neither stated nor justified, assumption extraction was not performed.
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.