Consensus Checker
Ki · Single Ability
The Problem
The project team reached consensus in 20 minutes. Nobody objected. But three members had serious reservations they never voiced, because the loudest voice in the room had already committed. Hidden dissent, buried by social pressure, left the decision unchallenged.
The Operation
When activated, the model must identify all stakeholder positions, extract each party's core claim and supporting evidence. Map areas of genuine agreement versus surface agreement masking hidden dissent. Quantify consensus strength per sub-issue as a ratio of aligned versus misaligned stakeholders. Verify that minority positions have been heard by checking whether dissenting evidence was addressed. If consensus is below 70%, partition disagreement into resolvable versus fundamental and rank compromise options. The reasoning applies a formal computation: consensus strength = aligned stakeholders / (aligned + misaligned). The constraint: never conflate vocal agreement with actual consensus probe for.
The Structure
Structurally, this is an accumulate-classify-decide pattern that gathers evidence, categorizes it, then concludes.
If all stakeholders appear to agree without any dissenting position being surfaced, consensus checking has defaulted to apparent agreement.
Haki · Multi Ability
Synergy Topology
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, these four abilities don't run in sequence. They merge into a single injection where the dependency grounds the reasoning context, the amplifier sharpens the primary's output, and the alternative provides a fallback path if the primary's topology cannot converge. The result is a multi-angle reasoning scaffold that covers failure modes no single ability can reach alone.
Appears in Use Cases