Workflow logic
Workflow logic sequences steps and decisions, making explicit what happens automatically and what does not.
AI for Kids · Class 9 · Module 7 of 9
Automation and Agents
An agent that acts on your behalf needs to know when to stop and ask.
8 sessionsSessions 49–56
4 weeksTypical pace
AppliedLevel
Class 9Artificial Intelligence
The big idea
Students map an agentic workflow where AI performs multiple steps, then design the human approval points and error handling that make delegation safe rather than reckless.
Why it matters
Agentic systems are becoming ordinary. Understanding where humans must stay in control is the critical judgement.
Unpacked
What you will actually learn
Three core ideas, each taught with worked examples and then practised until it feels obvious.
Human approval points
Human approval points sit wherever an action is expensive, irreversible or affects other people.
Error handling
Error handling plans for the step that fails, the ambiguous answer and the loop that never ends.
Did you know?
Aviation solved this decades ago with checklists and mandatory confirmations. Agentic AI design is rediscovering the same principles.
Common mix-up
“Full automation is the goal.” The goal is appropriate automation. Some decisions should always require a person.
Session by session
Your 8-session journey
Sessions 49–56 of the 72-session year, at two one-hour sessions per week.
- 1
Warm-up and big picture
Where this module fits, what you will build, and a hands-on starter that gets everyone curious about workflow logic.
- 2
Workflow logic
Guided teaching on workflow logic, worked through together with the teacher.
- 3
Workflow logic — practice lab
Independent practice, small challenges and one deliberate mistake to diagnose.
- 4
Human approval points
Guided teaching on human approval points, building directly on the previous two sessions.
- 5
Human approval points — practice lab
Applied tasks that combine workflow logic and human approval points in one piece of work.
- 6
Error handling
Error handling introduced and practised, completing the toolkit needed for the project.
- 7
Project build
Guided build session for the module project: Mapped and demonstrated agentic workflow.
- 8
Test, present and reflect
Finish, test against the checklist, present the work and explain the decisions behind it.
Project lab
Mapped and demonstrated agentic workflow
Every module ends with something the student built themselves and can demonstrate. This is the piece that goes into their portfolio and gets explained out loud at the end of session 56.
Try this at home
Map your workflow and mark every step where a mistake would be hard to undo. Each mark is an approval gate.
It is finished when
- It works from start to finish without breaking
- You can explain every part of it in your own words
- You tested it and improved at least one thing afterwards
- Someone else used or understood it without your help
By the end of this module
Students finishing Module 7 can:
- Explain and use workflow logic without prompting
- Explain and use human approval points without prompting
- Explain and use error handling without prompting
- Build and finish mapped and demonstrated agentic workflow
- Test your own work and correct what you find
- Talk an adult through what you made and why
Word bank
The vocabulary introduced here, in plain language:
- agent
- An AI system that takes multi-step actions towards a goal.
- approval gate
- A point requiring human sign-off.
- error handling
- Planned responses to things going wrong.
Module challenge
Think you have got this?
0 XPLevel 1 · Curious Beginner
6 quick questions drawn from this module — vocabulary, the project you build, and a myth-or-fact round. Every wrong answer explains itself, so a mistake still teaches you something.
Your child's free trial is one message away.
Tell us your child’s class and what they enjoy. We will suggest the closest program fit—no pressure and no upfront payment.