Function Calling
A model capability where the AI generates structured JSON arguments for predefined functions rather than free-form text. Function calling provides a reliable bridge between natural language understanding and programmatic execution.
Function calling is the mechanism that makes tool use reliable at scale. Instead of hoping the model outputs parseable text, you define function schemas with typed parameters, and the model returns structured JSON that your application code can execute directly. Most major model providers including OpenAI, Anthropic, and Google support function calling natively.
For engineering teams building AI-powered products, function calling is the preferred pattern for any workflow where the model needs to trigger backend actions. It eliminates fragile regex parsing, reduces hallucinated outputs, and gives you type safety at the boundary between AI and application logic. When designing functions for your agent, keep schemas simple, use descriptive parameter names, and provide clear descriptions. The quality of your function definitions directly correlates with how reliably the model calls them correctly.
Related Terms
Model Context Protocol (MCP)
An open standard that defines how AI models connect to external tools, data sources, and services through a unified interface. MCP enables agents to dynamically discover and invoke capabilities without hardcoded integrations.
Tool Use
The ability of an AI model to invoke external functions, APIs, or services during a conversation to perform actions beyond text generation. Tool use transforms language models from passive responders into active problem solvers.
Agentic Workflow
A multi-step process where an AI agent autonomously plans, executes, and iterates on tasks using tools, reasoning, and feedback loops. Agentic workflows go beyond single-turn interactions to accomplish complex goals.
ReAct Pattern
An agent architecture that interleaves Reasoning and Acting steps, where the model thinks about what to do next, takes an action, observes the result, and repeats. ReAct combines chain-of-thought reasoning with tool use in a unified loop.
Chain of Thought
A prompting technique that instructs the model to break down complex problems into sequential reasoning steps before producing a final answer. Chain of thought significantly improves accuracy on math, logic, and multi-step tasks.
Tree of Thought
An advanced reasoning framework where the model explores multiple solution paths simultaneously, evaluates each branch, and selects the most promising approach. Tree of thought enables more thorough problem-solving than linear chain-of-thought reasoning.