SkyAICampus
HomePracticeLearnCode LabFocus
SkyAICampus
PrivacyTermssupport@skyaicampus.com© 2026 SkyAI Campus
Log inSign up

Learn

HomePracticeConcept cardsCode LabSky Tutor

Review

Revise todayMistake notebookProgress

Focus

Campus ForestFocus roomsSquads

Questions or feedback?
support@skyaicampus.com

  1. 1Tool use
  2. 2Agent loops
  3. 3Memory and context
  4. 4Safety and evaluation
← Agentic AI

Lesson 1 of 4

Tool use

Watch, read the card, then practise. Tool calling · Structured outputs

Video coming soon

The video for this lesson is being recorded.

Meanwhile, the notes below and the 60-second cards cover the same ideas.

Practise this topic
  • Tool calling

    With tool calling, the model asks your program to run a function (search, calculator, database) and uses the result.

    Remember: Clear tool descriptions → correct tool calls.

  • Structured outputs

    Structured outputs make the model reply in a fixed shape, like JSON with named fields, so code can read it.

    Remember: Never act on model output you haven't validated.

Try the example in Code Lab

tools = {"add": lambda a, b: a + b, "mul": lambda a, b: a * b}
call = {"name": "mul", "args": {"a": 6, "b": 7}}
print(tools[call["name"]](**call["args"]))
Next: Agent loops →

In this lesson

  • Tool calling
  • Structured outputs

Practise this topic

5 questions at your level. The best way to make it stick.

Practise 5 questions