Do-Calculus Intervention Engine
Ki · Single Ability
The Problem
Observational data shows a correlation between exercise and reduced anxiety, implying exercise directly causes anxiety reduction.
The Operation
This ability makes the model state claim as X causes Y. Classify as observational or interventional. If observational, list plausible common causes of both X and Y. For each, check if statistically controllable. If no valid strategy exists, reject causal claim; restate as association. Treat correlation causation is rejected.
The Structure
This ability runs on a conditional branch that routes reasoning down different paths based on what it finds. Execution cycles until the evidence set is fully consumed.
If an intervention effect is estimated from observational data without blocking confounding paths, do-calculus intervention logic was bypassed.
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