Tools & Integration · Software component
Semantic Function
Software componentTools & IntegrationOrchestration & Toolsarc:SemanticFunction
A callable capability function implemented as a parameterized natural-language prompt template executed by an LLM service, used for analysis, judgement or generation.
Responsibility. Performs a language-understanding or generation task by rendering its prompt template and calling an LLM.
Also known as: Prompt function, LLM function, Semantic kernel function, Primitive operator (Semantic Kernel)
Relationships
deployed on structural
is configured by structural
invokes dependency
is invoked by dependency
Design guidance
- SHOULD be used for tasks resisting rule-based programming (sentiment, urgency, personalized responses), leaving deterministic data access to native functions.
- SHOULD consume structured data returned by native functions rather than retrieving facts itself.
Classification
- Patterns
- Semantic-native function compositionPrompt-as-function
- Technologies
- Semantic Kernel
- Quality attributes
- Flexibility (ISO/IEC 25010)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
- Risks mitigated
- Brittle rule-based code for nuanced language tasks
Sources
- Ch2.5: T. Nguyen, "Semantic Kernel," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 2.5. ISBN: 9798244538229.
- Ch5.4: T. Nguyen, "Hierarchical Planning Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.4. ISBN: 9798244538229.