Developer API

Confidence Policy

Defines how overall confidence is calculated from relevance, logic, and refinement signals. Weights control the influence of each signal in the final confidence score.

Properties of Confidence Policy

NameTypeDescription
FitWeightdecimalControls how strongly overall relevance influences confidence. Relevance represents how well the evaluated data aligns with the intended outcome.
LogicTrueWeightdecimalControls the influence of logic when conditions evaluate as true. Higher values increase confidence when logic validates the result.
LogicFalseWeightdecimalControls the influence of logic when conditions evaluate as false. Higher values increase the impact of logic rejection on confidence.
LogicAlignmentWeightdecimalControls how much logic coverage influences confidence. This reflects how much of the evaluated data space logic meaningfully governed.
SeparationWeightdecimalControls how strongly statistical deviation from the average candidate influences confidence. Higher values increase confidence when a result is significantly better than the overall distribution of evaluated candidates.
SeparationUsesAbsoluteDeviationboolDetermines how separation evaluates statistical deviation among candidates. Enable to reward any extreme deviation from the average (both unusually strong and unusually weak results); disable to reward only candidates that outperform the average. This setting is intended for advanced scoring scenarios.

404 - Not Found