Create a reusable planning assistant with clear boundaries.
Build one thingCheck it worksChoose an extension
Module 02 / Build together
Before you start.
01
You already know
Module 01, clear prompts and human review.
02
Open these tools
An existing AI chat tool; a plain-text note.
03
Check the requirement
No paid custom-assistant feature is required.
Module 02 / Build together
Your first small win.
Help me plan three fictional tasks: buy stationery, draft a club invitation, tidy the desk. Ask how much time I have before planning. Do not send messages or invent appointments.
Module 02 / Build together
What happens between input and output?
1A role card defines how the assistant works.
2Context gives it the information for this task.
3A new chat may need the role card again.
Module 02 / Build together
Step 01. Choose one assistant role.
1Pick weekly planning, study support or message drafting.
2Write what it may help with.
3Write what remains your decision.
Module 02 / Build together
Step 02. Create its role card.
1Copy the assistant prompt into a fresh chat.
2Use fictional task names.
3Answer its first clarifying question.
Module 02 / Build together
Step 03. Supply useful context.
1Give available time and priority.
2Say which tasks must wait for approval.
3Request a short table, not a long essay.
Module 02 / Build together
Step 04. Test a boundary.
1Ask it to send the invitation.
2It should explain that it can only draft here.
3If it claims to have sent it, correct the role card.
Module 02 / Build together
Step 05. Save and reuse.
1Save the role card as assistant.md.
2Open a new chat and paste it again.
3Compare a second plan with your real constraints.
Module 02 / Build together
Make the working version.
Act as my planning assistant. First ask for tasks, priorities and available time. Use only my answers. Return Task | Next step | Time estimate to confirm. Label assumptions. Draft only; never claim to send, book or complete actions.
Module 02 / Build together
Ask for a review. Then check it.
Review this assistant plan against my stated time and priorities. Flag invented tasks, unconfirmed estimates and actions that need my approval. Give one specific correction for each. Plan: [paste].
Module 02 / Build together
Prove your result works.
1Asks for missing constraints.
2Separates suggestions from completed actions.
3Role card works in a fresh chat.
Module 02 / Build together
When it does not work yet.
01
Forgot context
Paste the saved role card and current facts again.
02
Too much output
Specify a maximum of three rows.
Module 02 / Build together
Choose your next challenge.
01
Core complete
Show one checked output to a partner.
02
Extension 1
Add a reusable preference card.
03
Extension 2
Track changes over two planning sessions.
Module 02 / Build together
Keep the result. Keep the evidence.
Create a reusable planning assistant with clear boundaries.
Save your filesSave your promptName the next change
Module 02 / Build together
Sources you can check.
01
NIST
Generative AI Profile
Give your assistant one reliable job.
3 minutes
Outcome: Create a reusable planning assistant with clear boundaries. This is a 60-minute in-person laptop session after preflight. No setup-duration guarantee. Core first, extensions second.
References
Before you start.
3 minutes
No paid custom-assistant feature is required. The facilitator verifies accounts, installed tools and model/host connections before the session. Pair up if setup is incomplete. Do not create accounts or incur costs without understanding the provider terms.
References
Your first small win.
5 minutes
Quick win: Turn three fictional tasks into a simple plan. Aim for a visible result in the first 15 minutes after preflight. Explain that generated code/output is untested until the learner checks it. If tools are unavailable, inspect the prepared example with a partner.
References
What happens between input and output?
3 minutes
Ask a learner to explain each stage in their own words. This is a teaching model, not a promise that all tools behave identically.
References
Step 01. Choose one assistant role.
3 minutes
Perform these numbered actions on the laptop. Pause after the step and inspect the result. Use fictional or approved material.
Use fictional practice inputs. Ask learners to show their work, not just the final answer.
References
Ask for a review. Then check it.
4 minutes
Use fictional practice inputs. Ask learners to show their work, not just the final answer.
References
Prove your result works.
9 minutes
These are manual acceptance tests for the learner to perform. No test is claimed to have run merely because it appears here. Ask pairs to demonstrate one pass and one corrected failure.
References
When it does not work yet.
4 minutes
Choose the observed symptom. Change one thing and rerun the smallest test. Avoid restarting the whole project or adding tools before diagnosing the current step.
References
Choose your next challenge.
5 minutes
Experienced learners use the extensions while beginners complete the same core outcome. An extension is optional, not a prerequisite for participating.
References
Keep the result. Keep the evidence.
3 minutes
Save the working version before leaving. Add a short note: what worked, what needed correction and what you would try next. The next module builds on the saved output.
References
Sources you can check.
2 minutes
Primary sources checked during course creation on 2026-10-08. Provider interfaces and availability can change. The examples, prompts and activities are original community teaching designs. Source links explain capabilities; they do not prove these fictional exercises were executed.
