Tool Use & Function Calling - Interactive Visualization

Function calling lets LLMs invoke external tools - search, code execution, databases, APIs - by outputting structured JSON that the host application executes. The result is fed back to the model for incorporation. Modern LLMs support parallel tool calls, invoking multiple functions simultaneously. This demo animates the full tool use loop step by step.

• Tool selection: the LLM chooses which function to call based on the user query
• Structured JSON output: see the exact function name and arguments the model emits
• Execution and callback: the host runs the tool and returns results to the conversation
• Parallel tool calls: multiple functions dispatched simultaneously in a single model turn

Part of the EngineersOfAI Interactive 3D - free interactive visualizations covering every major concept in machine learning and AI engineering. Hover any element for a plain-English explanation. No code required.