liveBook · Manning

Semantic function

A semantic function is a callable operation whose behavior is specified by a natural-language prompt and executed through interaction with a large language model.

How 2 Manning books explain it

AI Agents in Action

A semantic function is a function whose behavior is specified by a prompt or profile and executed through interaction with a large language model.

How it is used
Deploys prompt-defined behavior as an executable action for LLM applications, plugins, chat interfaces, and agents.
How deep it goes
Explains templates, variables, plugins, invocation, and composition with native functions, but does not detail model internals.
Examples
Uses movie recommendations, creative writing, meal planning, database lookup, and tree-of-thought answer evaluation.
What you can do after
Build it from scratch with Semantic Kernel, parameterize prompts, register plugins, invoke functions, and combine prompts with code actions.

Read how AI Agents in Action explains semantic function →

Generative AI in Action

A semantic function is a Semantic Kernel callable operation defined by a natural-language prompt and input parameters.

How it is used
Provides callable application capabilities that Semantic Kernel can combine to fulfill a natural-language goal.
How deep it goes
Defines the role and orchestration of semantic functions but does not show their prompt definitions or input-parameter syntax.
Examples
Uses database interactions, API calls, and email operations as examples of application capabilities.
What you can do after
Apply it via Semantic Kernel to expose application operations for AI-driven orchestration.

Read how Generative AI in Action explains semantic function →

Related concepts

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.