Write a clear prompt and improve a neighbourhood invitation.
Build one thingCheck it worksChoose an extension
Module 01 / Build together
Before you start.
01
You already know
No technical experience.
02
Open these tools
An available AI chat tool or a partner.
03
Check the requirement
Use an existing permitted account. No API key needed.
Module 01 / Build together
Your first small win.
Write a friendly invitation under 60 words. Fictional practice facts: Saturday, 10:00, community room, free entry. Do not add speakers, food or booking links. Leave missing details blank.
Module 01 / Build together
What happens between input and output?
1A prompt supplies the job and the facts.
2The model drafts language from learned patterns.
3You check claims before sharing.
Module 01 / Build together
Step 01. Choose a small task.
1Pick an invitation, checklist or plain-language explanation.
2Choose a result you can check yourself.
3Write down the confirmed facts.
Module 01 / Build together
Step 02. Give a clear instruction.
1Name the task and the audience.
2Supply facts, limits and the desired format.
3Use the quick-win prompt in a fresh chat.
Module 01 / Build together
Step 03. Check the draft.
1Underline every factual claim.
2Compare it with the four supplied facts.
3Remove anything the model added.
Module 01 / Build together
Step 04. Revise one thing.
1Ask for a shorter version without changing facts.
2Read the new draft again.
3Save the prompt, draft and correction in one note.
Module 01 / Build together
Make the working version.
Rewrite my invitation in simpler English, under 40 words. Keep only Saturday, 10:00, community room and free entry. Do not add promises or links. Return one title and the message.
Module 01 / Build together
Ask for a review. Then check it.
Compare this invitation with the confirmed facts: Saturday, 10:00, community room, free entry. List unsupported claims and missing information. Do not invent replacements. Invitation: [paste draft].
Module 01 / Build together
Prove your result works.
1Contains all four supplied facts.
2Has no invented event details.
3A neighbour can understand it on first reading.
Module 01 / Build together
When it does not work yet.
01
Added details
Delete unsupported claims, then request a facts-only revision.
02
Vague request
Add the audience, length and exact facts.
Module 01 / Build together
Choose your next challenge.
01
Core complete
Show one checked output to a partner.
02
Extension 1
Compare two tools on the same prompt.
03
Extension 2
Create a reusable invitation checklist.
Module 01 / Build together
Keep the result. Keep the evidence.
Write a clear prompt and improve a neighbourhood invitation.
Save your filesSave your promptName the next change
Module 01 / Build together
Sources you can check.
01
NIST
Generative AI Profile
One useful draft. One human check.
3 minutes
Outcome: Write a clear prompt and improve a neighbourhood invitation. 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
Use an existing permitted account. No API key needed. 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: A short invitation using only four fictional facts. 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 a small task.
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.
12 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.
