# What is Function/Tool Calling in LLM Apps

> Understand the mechanics of LLM function calling and how granting AI access to external APIs transforms it from a passive text generator into an active, potentially vulnerable agent.

Canonical: https://codelivly.com/rooms/what-is-functiontool-calling-in-llm-apps
Last updated: 2026-10-12

| | |
|---|---|
| Level | Intermediate |
| Category | Cybersecurity |
| Lessons | 2 |
| Estimated time | 30 min |
| XP | 100 |

This module introduces the foundational concepts of Function Calling (or Tool Calling) in Large Language Models. You will explore how LLMs generate structured JSON to invoke external APIs, the architectural shift from passive text generation to active agentic workflows, and why this paradigm introduces critical new attack surfaces like parameter manipulation, unauthorized actions, and logic bypasses.

## Lessons

1. What is Function Calling and Why Models Use It (30 min)
2. How the Model Decides Which Tool to Call (30 min)

## Related

- [Learning path: AI API and Function-Calling Attacks](https://codelivly.com/learning-paths/ai-api-and-function-calling-attacks)
- [All rooms](https://codelivly.com/rooms)