Inter-Agent Metacognitive Broker
Ki · Single Ability
The Problem
Plan assumes the vendor will deliver on time without any explicit contingency for delays.
The Operation
This ability makes the model enumerate every assumption embedded in the current reasoning chain and extract each one explicitly. Classify each assumption as stated, implied, or hidden based on whether it was surfaced during reasoning. Flag all hidden assumptions and trace their influence on the current conclusion. Verify that no critical hidden assumption drives the conclusion without scrutiny. Suppress any tendency to treat unstated premises as self-evident. It will not suppress tendency treat unstated premises self evident.
The Structure
Under the hood, the reasoning follows an accumulate-classify-decide pattern that gathers evidence, categorizes it, then concludes. Execution repeats until the reasoning locks onto a stable conclusion.
If the reasoning depends on unstated premises without checking whether each being explicitly surfaced and labeled, transparency enforcement has failed.
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