Tool use / function calling

The capability that lets an AI model take real actions: the model outputs a structured request ("call this function with these arguments"), and your application decides whether to run it.

This is the core mechanism that turns a text generator into something that can actually do things. When a model needs to go beyond generating text, it outputs a structured request naming a function and its arguments: for example, {"function": "send_email", "to": "sam@example.com", "subject": "Meeting Tuesday"}. Your application receives that request, validates it, runs the code, and sends the result back to the model. The model then uses that result to continue its work. This is how chatbots become agents: tool use is what lets AI book a meeting on your calendar, look up inventory in a database, edit a file, or send an email.

Builder example

Tool use is the single capability that separates a chatbot from an agent. Every real-world action your AI product takes flows through a tool call, which makes this the most important place to put guardrails. Validate the arguments before running any function (the model can hallucinate parameters), limit which tools each workflow can access (a summarization task should not be able to send emails), and log every tool call separately from the conversation so you can audit what actually happened.

The user says, 'Book Sarah for Tuesday afternoon.' The model proposes a calendar-create call with attendee, time, title, and timezone.

Validate the fields, confirm ambiguity, and require approval before sending invites.

Common confusion: The model never executes code itself. It produces a structured request that says "I want to call this function with these arguments," and your application code is fully in control of whether and how to proceed.