Classifiers
Reusable decision classifiers for decision models such as TypeSafe's Jev and the open-weight Kev. Each classifier asks one constrained question about a state, and your code acts on the answer. Chains show how classifiers combine, with branches driven by outcomes.
Educational catalog. Nothing here calls a model. Example outcomes are illustrative judgments written for teaching, not model outputs, scores or accuracy claims. Sourced documentation is labelled separately.
Classifiers
2 classifiersScoreGrounding
Retrieved passage relevance
Score how useful each retrieved passage is for answering the question.
IncludeBorderlineExclude
Used in 1 chain
ChoiceGrounding
Answer groundedness
Check whether the sources support each claim in a drafted answer.
SupportedContradictedNot addressedNeeds a person
Used in 1 chain
Decision chains
1 chainComplete flows that reuse the classifiers above, with branches driven by outcomes.