Tool Use
AI models calling external functions and APIs
What is Tool Use?
The ability of AI models to call external functions, APIs, or tools during generation to accomplish tasks beyond pure text output. An LLM with tool use can search the web, run code, query databases, send emails, or interact with smart contracts. This transforms AI from a text generator into an action-taking system, essential for building AI agents that actually get things done in Web3 and beyond.
How it works
Key takeaways
-
LLM decides which external tool to call
-
Bridges AI knowledge with real-time data
-
Foundation for agents and function calling
Real-world example
A user asks 'What's the weather in Madrid?' The LLM can't check weather itself, but with tool use it calls a weather API, gets live data, and returns 'Madrid: 28°C, sunny.' The model decided to call the tool on its own.
