Consensus Builder
Ki · Single Ability
The Problem
Your model teams have conflicting models of customer churn and we're stuck in a false dichotomy, one says price, the other says UX, and someone must be wrong.
The Operation
The model is directed to extract each competing causal model and identify its core mechanism, evidence base, and scope. Map the structural overlap, isolate shared variables, common causal links, and agreed-upon evidence. Identify the precise point of divergence where the models disagree on mechanism or direction. Test whether the divergence stems from different scopes rather than genuine contradiction. Synthesize a unified model that preserves shared invariants and partitions the disagreement into conditional branches.
The Structure
Structurally, this is a dialectical spiral of thesis, antithesis, and synthesis that deepens with each turn. Each spiral pass deepens the analysis, building on what the previous pass discovered.
If contradictory models are presented without identifying their shared structural invariants, synthesis was not attempted.
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