Package org.egothor.methodatlas.ai

Class OptimizedSecurityTaxonomy

java.lang.Object
org.egothor.methodatlas.ai.OptimizedSecurityTaxonomy
public final class OptimizedSecurityTaxonomy extends Object
Provides the optimized built-in taxonomy used to guide AI-based security classification when prompt compactness and model reliability are prioritized.

This class supplies a condensed taxonomy definition intended for use with AiOptions.TaxonomyMode.OPTIMIZED. In contrast to DefaultSecurityTaxonomy, this variant is structured to improve AI classification consistency by reducing prompt verbosity while preserving the same controlled category set and classification intent.

Design Goals

  • minimize prompt length without changing the supported taxonomy
  • increase deterministic model behavior
  • reduce ambiguity in category selection
  • preserve professional terminology and decision rules

The taxonomy text returned by this class is intended to be embedded directly into AI prompts and therefore favors concise, machine-oriented instruction structure over explanatory prose.

This class is a non-instantiable utility holder.

See Also:

  • Method Details

    • text

      public static String text()
      Returns the optimized built-in taxonomy text used for AI classification.

      The returned taxonomy is a compact instruction set designed for large language models performing security classification of JUnit test methods. It preserves the same controlled tag set as the default taxonomy while presenting the rules in a shorter, more model-oriented structure.

      The taxonomy defines:

      • the meaning of a security-relevant test
      • the mandatory security umbrella tag
      • the allowed category tags
      • selection rules for assigning taxonomy tags
      • guidance for use of the optional owasp tag
      • the required SECURITY: <property> - <scenario> display name format

      This optimized variant is suitable when improved model consistency or shorter prompt size is more important than human-oriented explanatory wording.

      Returns:
      optimized taxonomy text used to instruct AI classification
      See Also: