← Back to glossaryarchitecture
Tool use
Tool use (or function calling) is a language model's ability to call external functions with structured arguments — e.g. an API, a database query, or a skill.
Also known as: Function Calling
In detail
This is what lets the LLM leave pure chat mode and act. The flow:
- We define a tool: name, description, JSON schema of arguments.
- On a request, the LLM decides whether and with what arguments to call the tool.
- We execute the call, return the result.
- The LLM uses the result for its answer.
Claude and GPT-4 support this natively. We use it for RAG search, CRM lookups, calendar bookings.
Related terms
- EmbeddingAn embedding is a numeric representation of text (or an image) in a high-dimensional space where similar content sits close together — the foundation of semantic search and RAG.
- Multi-agentMulti-agent refers to an architecture where several specialized AI agents collaborate — a router decides who takes over, and they hand off tasks cleanly.
- RAGRAG (Retrieval-Augmented Generation) is a technique where the language model retrieves relevant documents from your knowledge base before each answer and uses them as the basis for its response — so the agent stays current and answers with sources.