What Is Function Calling?

Function calling bridges the gap between conversational AI and actionable software. Instead of simply generating text, an LLM with function calling can recognize when a user's request requires external data or actions — such as checking the weather, querying a database, or sending an email — and produce a structured function call with the appropriate parameters. The model does not execute the function itself; rather, it outputs a JSON object specifying the function name and arguments, which the application then executes and feeds the result back to the model for a natural language response. This pattern enables developers to build AI assistants that can perform real tasks, not just answer questions. OpenAI popularized the concept with their function calling API, and it has since been adopted by Anthropic, Google, and open-source models. Function calling is foundational to building AI agents, as it gives models the ability to take actions in the world rather than being limited to text generation.