Software Factories at enterprise scale: A federated platform for agentic developmentDownload the free Whitepaper
AI Native Terms

What Is Function Calling?

Written byre:cinq StaffUpdated 16 Sept 2026

Function calling is a feature that allows an AI model to use external tools and access live information to answer questions or complete tasks. Standard AI models are "locked in a box," limited to the general information they were trained on. They cannot access your company's real-time data, like inventory levels or customer order history, nor can they take actions in other software systems.

Continue readingHow it helps

How it helps#

Function calling connects the AI to your business systems, allowing it to perform specific, pre-approved actions. This transforms the AI from a general knowledge base into a practical assistant that can look up live data or trigger processes, automating real work.

How it works#

Developers provide the AI model with a list of available tools, or "functions," and descriptions of what they do. These functions could be anything from "checkdatabasefororderstatus" to "addappointmentto_calendar." When a user makes a request, the AI can intelligently determine if one of its available functions can help fulfill it.

Instead of executing the task itself, the AI generates a structured command that tells your company's software exactly which function to run. Your system then executes the function, retrieves the necessary information (like an order status), and feeds that data back to the AI. The AI then uses this fresh, specific information to provide a complete and accurate answer to the user.

Keep up with the Knowledge BaseEvery two weeks, get new terms and updated definitions straight to your inbox.

Related terms

  • AI agents

    What Are AI Agents?

    An autonomous program that understands a goal, makes a plan and carries out a series of tasks with software tools to achieve it.

  • Agentic coding

    What is agentic coding?

    Agentic coding delegates a whole task to an AI agent that plans, edits, runs tests and iterates until it is done.

Spot something we missed, got wrong or could explain better? Send us a correction or suggestion—help improve the Knowledge Base, and get credited if we publish it.