Run a reviewed weekly-plan workflow from fictional notes.
Build one thingCheck it worksChoose an extension
Module 12 / Build together
Before you start.
01
You already know
Modules 06–11 or their core outputs. A prepared n8n model connection.
02
Open these tools
n8n, approved note text, a language-model chain; optional bot only after approval.
03
Check the requirement
Use the prepared local model or a checked API budget. External delivery is optional.
Module 12 / Build together
Your first small win.
Use these fictional notes to suggest three next actions: organise books; ask organiser about room permission; draft an invitation after permission. Mark dependencies. Do not send or book anything. Return Action | Evidence | Approval needed.
Module 12 / Build together
What happens between input and output?
1Your notes supply the evidence.
2A workflow or agent prepares a draft.
3Human review decides whether any action follows.
Module 12 / Build together
Step 01. Define a small success.
1Pick one weekly plan, not a life-management system.
2Choose three fictional notes from your second brain.
3Write what a useful checked output should contain.
Module 12 / Build together
Step 02. Create a manual input.
1Add Manual Trigger and Edit Fields in n8n.
2Create a String notes containing labelled note text.
3Keep contact details and credentials out of it.
Module 12 / Build together
Step 03. Connect the summariser.
1Use the working Basic LLM Chain from Module 08.
2Apply the evidence-and-approval prompt.
3Keep the configured model and test one input.
Module 12 / Build together
Step 04. Inspect the plan.
1Check each action against a named note.
2Remove invented deadlines and completed-action claims.
3Mark actions blocked by missing permission.
Module 12 / Build together
Step 05. Add an approval decision.
1Create a Boolean approved field only after human review.
2Use an If node to gate any later delivery.
3When false, end with a draft-only output.
Module 12 / Build together
Step 06. Run the final two tests.
1Run once with approved=false and confirm nothing sends.
2Review and test approved=true only in your own test chat if connected.
3Save the workflow, prompt, test evidence and next improvement.
Module 12 / Build together
Make the working version.
Create a weekly plan only from these labelled notes: {{$json.notes}}. Return Action | Evidence note | Dependency | Approval needed. Use at most three actions. Mark missing facts unknown. Produce a draft only; do not claim to send, book or finish work.
Module 12 / Build together
Ask for a review. Then check it.
Audit this capstone plan against its notes. Identify invented facts, missing dependencies and actions needing permission. Return Pass/Revise with reasons. Do not approve on my behalf. Notes: [paste]. Plan: [paste].
Module 12 / Build together
Prove your result works.
1Every action cites an input note.
2Unapproved run has no external send path.
3You can explain the trigger, model step and approval gate.
Module 12 / Build together
When it does not work yet.
01
Too many moving parts
Return to manual input and one model step.
02
Approval default is true
Set false by default and test the blocked path first.
Module 12 / Build together
Choose your next challenge.
01
Core complete
Show one checked output to a partner.
02
Extension 1
Add a schedule only after manual tests pass.
03
Extension 2
Add logs and a small failure-recovery path.
Module 12 / Build together
Keep the result. Keep the evidence.
Run a reviewed weekly-plan workflow from fictional notes.
Save your filesSave your promptName the next change
Module 12 / Build together
Sources you can check.
01
n8n
Basic LLM Chain
02
n8n
If node
03
NIST
Generative AI Profile
Connect your notes to a useful next action.
3 minutes
Outcome: Run a reviewed weekly-plan workflow from fictional notes. 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 the prepared local model or a checked API budget. External delivery is optional. 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 notes into a short next-action list. 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. Define a small success.
3 minutes
Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.
Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.
Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.
Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.
Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.
Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.
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.
6 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.
