Tool Use
Definition
The ability of an AI model to interact with external tools and APIs — such as web search, code interpreters, calculators, and databases — to accomplish tasks beyond its inherent capabilities.
Tool use transforms language models from pure text generators into capable agents that can take real-world actions. When a model encounters a task it cannot solve with language alone (like performing precise calculations, accessing current information, or executing code), it can generate structured calls to external tools and incorporate their results. Major implementations include ChatGPT's plugins and code interpreter, Claude's tool use, and frameworks like LangChain and function calling APIs. Common tools include web search, code execution, file management, database queries, and third-party API calls. Tool use is fundamental to the AI agent paradigm and enables models to overcome limitations like math errors, knowledge cutoffs, and inability to interact with external systems.
Related Terms
Code Generation
The use of AI models to automatically write, complete, translate, or debug programming code based on...
AI Agent
An AI system that can autonomously plan, make decisions, and take actions to accomplish goals, often...
Prompt Engineering
The practice of crafting effective instructions and inputs for AI models to elicit desired outputs, ...
API
Application Programming Interface — in the AI context, a standardized way for developers to send req...