Conversation flows
Conversation flows map what the user might say and how the bot responds, including the paths nobody planned for.
AI for Kids · Class 7 · Module 8 of 9
No-code Chatbot Thinking
Designing a chatbot teaches you something surprising: most of the work is deciding what it should refuse to do.
8 sessionsSessions 57–64
4 weeksTypical pace
FoundationLevel
Class 7Artificial Intelligence
The big idea
Students map conversation flows for a school-help assistant, define the boundaries of what it should handle, and test it against the awkward things real users will actually type.
Why it matters
Conversation design is systems thinking with a friendly face. It teaches planning for the unexpected without a line of code.
Unpacked
What you will actually learn
Three core ideas, each taught with worked examples and then practised until it feels obvious.
Helpful boundaries
Helpful boundaries mean deciding what the bot will not answer, and saying so clearly instead of guessing badly.
Testing responses
Testing responses means letting other students loose on it. They will type things you would never have imagined.
Did you know?
ELIZA, built in 1966, simply reflected users’ statements back as questions — and people still formed emotional attachments to it.
Common mix-up
“A good chatbot answers everything.” A good chatbot answers its own domain well and hands over honestly when it should not.
Session by session
Your 8-session journey
Sessions 57–64 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 conversation flows.
- 2
Conversation flows
Guided teaching on conversation flows, worked through together with the teacher.
- 3
Conversation flows — practice lab
Independent practice, small challenges and one deliberate mistake to diagnose.
- 4
Helpful boundaries
Guided teaching on helpful boundaries, building directly on the previous two sessions.
- 5
Helpful boundaries — practice lab
Applied tasks that combine conversation flows and helpful boundaries in one piece of work.
- 6
Testing responses
Testing responses introduced and practised, completing the toolkit needed for the project.
- 7
Project build
Guided build session for the module project: Prototype school-help chatbot.
- 8
Test, present and reflect
Finish, test against the checklist, present the work and explain the decisions behind it.
Project lab
Prototype school-help chatbot
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 64.
Try this at home
Give your chatbot to five classmates without instructions. Log every question it handled badly — that log is your next version.
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 8 can:
- Explain and use conversation flows without prompting
- Explain and use helpful boundaries without prompting
- Explain and use testing responses without prompting
- Build and finish prototype school-help chatbot
- 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:
- conversation flow
- The mapped paths a dialogue can take.
- fallback
- The response used when the bot does not understand.
- scope
- The range of things a system is meant to handle.
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.