Duration Realist
Ki · Reasoning
The Problem
The database migration will take two weeks, that's our best-case estimate and the team is experienced, so there's no reason to add buffer. We'll hit the deadline if everything goes according to plan.
The Operation
This ability makes the model extract every duration estimate and identify its basis: historical data, expert judgment, or optimistic assumption. Compare each estimate against historical base rates or p90 benchmarks for similar tasks. Flag estimates below the historical median as likely optimistic. Never accept best-case estimates as planning targets. If an estimate lacks historical basis, simulate impact with a 1. The reasoning applies a formal computation: adjusted range = base rate estimate +/- sqrt(variance) * z; z = confidence factor. The constraint: never accept best case estimates planning targets.
The Structure
Under the hood, the reasoning follows an anchor-drift-correct cycle that detects when reasoning has drifted from its reference point. It keeps running until the answer stops changing between iterations.
If time estimates reflect only the best-case scenario without applying any buffer multiplier, duration calibration has defaulted to optimism.
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