Bias Interceptor
Ki · Reasoning
The Problem
The marketing campaign will succeed because the initial feedback loop is positive, amplifying the halo effect.
The Operation
When activated, the model must scan the current reasoning chain and identify which cognitive biases could plausibly distort it, check for anchoring, confirmation bias, halo effect, availability bias, and sunk cost. For each candidate bias, isolate the specific reasoning step where it could be operating. Flag each bias with a concrete description of what it would cause the reasoner to do differently. Demand a debiasing action for each flagged bias: seek disconfirming evidence, strip first-seen anchors, or audit the source of conviction. If no biases are identified, probe deeper, test whether absence reflects genuine objectivity or bias blind spot. If it detects allow reasoning to proceed without naming at least, it halts and corrects.
The Structure
The reasoning structure is a watchdog monitor that continuously observes the reasoning process for signs of degradation. The monitor runs continuously, checking for drift at each step.
If the reasoning proceeds without naming a single cognitive bias that could be influencing the conclusion, bias detection was skipped.
Haki · Reasoning-Multi
Cross-Domain Suppression
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, the primary ability is augmented with failure guards extracted from 3 abilities in different cognitive domains. Each guard blocks a specific reasoning failure the primary alone wouldn't catch. A self-check forces verification before output. The result is cross-domain coverage that no single ability can reach alone.
Appears in Use Cases