AI Agent Studio
Watch the plan → tool → observe loop, then write its brain in Python
What your child can do at the end
Describe the agent loop: plan, pick a tool, call it, observe, repeat
The brief
An AI agent is not magic; it is a loop. Look at the goal, decide which tool helps, call it, look at the result, and go round again until the goal is met or the step budget runs out. In this studio you give a visual agent goals that need a lookup table, a calculator and string operations, sometimes two or three in a row; you watch each phase of the loop light up, read the trace table, switch rules off to watch the agent fail, and shrink max steps until it gives up. A Python panel highlights the exact line that corresponds to each phase. Then you write choose_tool, the decision function at the heart of the agent, and pass the tests.
Skills it develops
How it is assessed
3 graded challenges inside the lab, and 8 questions at the end that check the idea rather than the clicks. Every attempt is saved, so a retry after a mistake counts as the learning it is.