Core
Tool / Function Calling
Tool calling is how a language model reaches outside itself: it emits a structured request (a tool name plus JSON arguments) that your application executes and feeds back. The model is only as capable as the tools you give it and as reliable as your validation, because the arguments it produces are model output and must never be trusted blindly.
a free account unlocks the core curriculum tier · no card
Related course lessons
- Design tools around narrow customer operations →
20 min · Free
Harness Engineering for FDEs · syllabus - Lab: build a baseline you can reproduce →
45 min · Free with sign-in
Production AI Agents for FDEs · syllabus - Design read tools that answer a specific decision →
22 min · Free with sign-in
Production AI Agents for FDEs · syllabus
Related concepts
Practise this in questions
LLM & GenAI FundamentalsWhat are the failure modes of tool/function calling, and how do you handle them in production? →medium · Free with sign-inAI Security, Privacy & GovernanceWalk me through the OWASP LLM Top 10, which two risks would you prioritize for an enterprise agent deployment? →medium · FreeRAG & Agent System DesignWhen is an agent the wrong answer? Argue against building one. →easy · FreeAI Security, Privacy & GovernanceWhat is 'excessive agency' in an agentic system, and what controls actually limit it? →easy · FreeRAG & Agent System DesignDesign a customer-support agent with order-status and returns tools. How do you keep it safe and useful? →medium · FreeAI Security, Privacy & GovernanceHow do tool poisoning and prompt injection apply to MCP servers and agentic AI, and how do you defend them? →medium · Free