Belief Network Propagator
Ki · Single Ability
The Problem
Updating the local weather model belief without network propagation leads to isolated prediction errors.
The Operation
Under this ability, the model must identify key beliefs in reasoning chain; map dependencies, which beliefs support or depend on others. Identify which belief is most directly affected by new evidence or changed premise. Update that belief, then propagate through dependency network, determine how much each connected belief should shift. Check second-order effects where shifted beliefs trigger further updates. Identify tipping points where small additional evidence would cause large cascades, flag as critical sensitivities. The constraint: never update beliefs isolation.
The Structure
The reasoning structure is a cascade propagation where effects ripple through each stage of the analysis. Execution cycles until the evidence set is fully consumed.
If a belief revision is applied locally without propagating its implications through the connected belief network, network propagation was skipped.
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