Knowledge boundaries
Knowledge boundaries define what the assistant covers and what it must decline, so it never invents an answer to look useful.
AI for Kids · Class 9 · Module 6 of 9
Chatbots and Knowledge
The most trustworthy assistant is one that knows exactly what it does not know.
8 sessionsSessions 41–48
4 weeksTypical pace
AppliedLevel
Class 9Artificial Intelligence
The big idea
Students design a subject-help assistant with defined knowledge boundaries, a conversation design that guides users, and fallbacks for the moments it cannot help.
Why it matters
Designing for the failure cases, not just the happy path, is the mark of serious system thinking.
Unpacked
What you will actually learn
Three core ideas, each taught with worked examples and then practised until it feels obvious.
Conversation design
Conversation design guides users towards what the system can genuinely do, rather than leaving them to guess.
Testing and fallback
Testing and fallback: handle the unclear question, the out-of-scope question and the deliberately awkward one.
Did you know?
Grounding an assistant in a specific set of documents, rather than relying on model memory, sharply reduces invented answers.
Common mix-up
“Saying ‘I do not know’ makes it look weak.” Users trust a system that admits limits far more than one caught inventing.
Session by session
Your 8-session journey
Sessions 41–48 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 knowledge boundaries.
- 2
Knowledge boundaries
Guided teaching on knowledge boundaries, worked through together with the teacher.
- 3
Knowledge boundaries — practice lab
Independent practice, small challenges and one deliberate mistake to diagnose.
- 4
Conversation design
Guided teaching on conversation design, building directly on the previous two sessions.
- 5
Conversation design — practice lab
Applied tasks that combine knowledge boundaries and conversation design in one piece of work.
- 6
Testing and fallback
Testing and fallback introduced and practised, completing the toolkit needed for the project.
- 7
Project build
Guided build session for the module project: Subject-help assistant prototype.
- 8
Test, present and reflect
Finish, test against the checklist, present the work and explain the decisions behind it.
Project lab
Subject-help assistant prototype
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 48.
Try this at home
Write ten questions your assistant should refuse. Test all ten and check it refuses gracefully rather than guessing.
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 6 can:
- Explain and use knowledge boundaries without prompting
- Explain and use conversation design without prompting
- Explain and use testing and fallback without prompting
- Build and finish subject-help assistant prototype
- 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:
- grounding
- Tying answers to a trusted source of information.
- scope boundary
- The defined edge of what a system handles.
- graceful failure
- Failing clearly and helpfully.
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.