Attentional Blindspot Exposer
Ki · Single Ability
The Problem
The marketing team assumes the attended channels are complete, ignoring peripheral signals that might be unprocessed.
The Operation
When activated, the model must list top 3-5 information elements currently being actively processed. Enumerate all other context information not among those, this is the blindspot set. Score each blindspot item 0-10 on task relevance: could ignoring it change the conclusion? If any blindspot item scores above 6, incorporate it into active reasoning immediately. Check if any attended item is lower relevance than a blindspot item; if so, swap priority. Output one-sentence blindspot disclosure stating what was nearly missed and why. The reasoning applies a formal computation: blindspot set = all context - attended context.
The Structure
Under the hood, the reasoning follows a negative space scan that finds what is absent, not just what is present. The loop runs until all inputs are processed or no new progress emerges.
If the analysis focuses only on the salient elements without searching for what might be present but unnoticed, blindspot exposure was not performed.
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