Lesson 2010 of 2116
AI Tool Use: Letting the Model Call Functions
Tool/function calling lets the AI invoke real APIs you define — with constraints.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1The premise
- 2tool-use
- 3function-calling
- 4schemas
Concept cluster
Terms to connect while reading
Section 1
The premise
Tool use is how AI gets out of the chat box and into your systems. The schema you define is the contract.
What AI does well here
- Call defined functions with structured arguments.
- Pick the right tool from a small toolbox (≤5 tools).
- Handle tool results and synthesize a final answer.
- Re-call a tool when given an error response.
What AI cannot do
- Pick well from toolboxes of 30+ tools without confusion.
- Recover from tools whose schemas don't match docs.
Key terms in this lesson
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “AI Tool Use: Letting the Model Call Functions”?
Ask anything about this lesson. I’ll answer using just what you’re reading — short, friendly, grounded.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 45 min
Structured Outputs: Make the Model Return Data You Can Trust
For production apps, pretty prose is often the wrong output. Learn when to use structured outputs, function calling, and schema validation.
Creators · 9 min
Pro Search vs Default: When To Spend The Compute
Pro Search runs more queries, reads more pages, and routes to a stronger model. It is not always worth the wait — knowing when it is is the skill.
Creators · 10 min
Perplexity API: Building RAG Without Owning The Pipeline
The Perplexity API gives you cited search answers with one call. It is the cheapest way to add grounded retrieval to a product — and the limits are worth understanding.