Turn a fictional request into a short reviewable summary.
Build one thingCheck it worksChoose an extension
Module 08 / Build together
Before you start.
01
You already know
Module 07. Facilitator has prepared n8n and a working local Ollama model.
02
Open these tools
n8n Basic LLM Chain, Ollama Chat Model and local model credentials.
03
Check the requirement
Local inference uses your hardware. Hosted API alternatives may incur charges.
Module 08 / Build together
Your first small win.
Summarise this fictional request in one sentence. Use only its facts: I want the community room for a reading circle on Saturday. Time and permission are not confirmed. Mark missing facts as unknown.
Module 08 / Build together
What happens between input and output?
1The fixed workflow decides when the model runs.
2The prompt defines the output, not a guarantee.
3A person checks the summary before using it.
Module 08 / Build together
Step 01. Check the prepared model.
1Confirm Ollama is running and a suitable model is downloaded.
2Ask the facilitator to test the connection.
3Do not spend the session downloading a large model.
Module 08 / Build together
Step 02. Create the input item.
1Add Manual Trigger and Edit Fields.
2Create a String request with the fictional message.
3Execute and inspect the request field.
Module 08 / Build together
Step 03. Add the language-model step.
1Connect Basic LLM Chain.
2Choose Prompt: Define below.
3Paste the summary prompt in the user-message field.
Module 08 / Build together
Step 04. Connect the model.
1Attach Ollama Chat Model to the chain model connector.
2Use prepared Ollama credentials and the installed model name.
3If n8n is in Docker, confirm the reachable host address.
Module 08 / Build together
Step 05. Run and inspect.
1Execute once and open the chain output.
2Check the one-sentence summary and unknown facts.
3Remove added promises; do not connect a send action.
Module 08 / Build together
Step 06. Compare a second input.
1Change request to a different fictional message.
2Run again and compare outputs.
3Save the prompt and one correction beside the workflow.
Module 08 / Build together
Make the working version.
Summarise this request in one sentence, then list missing facts. Use only the input, no promises or invented dates. Request: {{$json.request}}
Module 08 / Build together
Ask for a review. Then check it.
Compare the summary with the original request. Identify unsupported facts and missing caveats. Give a corrected summary. Original: [paste]. Summary: [paste].
Module 08 / Build together
Prove your result works.
1The chain receives request from the input item.
2Summary contains no invented time or permission.
3Two different inputs produce appropriate checked summaries.
Module 08 / Build together
When it does not work yet.
01
No prompt specified
Choose Define below and verify the request expression.
02
Model connection fails
Check installed model and reachable Ollama Base URL; cloud n8n cannot see your laptop localhost.
Module 08 / Build together
Choose your next challenge.
01
Core complete
Show one checked output to a partner.
02
Extension 1
Use a structured output parser after text works.
03
Extension 2
Add an explicit approval step before any external action.
Module 08 / Build together
Keep the result. Keep the evidence.
Turn a fictional request into a short reviewable summary.
Save your filesSave your promptName the next change
Module 08 / Build together
Sources you can check.
01
n8n
Basic LLM Chain
02
n8n
Ollama credentials
03
Ollama
Quickstart
Put one AI step in a workflow.
3 minutes
Outcome: Turn a fictional request into a short reviewable summary. 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
Local inference uses your hardware. Hosted API alternatives may incur charges. 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: Run a prepared model connection on one fictional sentence. 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. Check the prepared model.
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.
