Receive a real test message through your own Telegram bot.
Build one thingCheck it worksChoose an extension
Module 09 / Build together
Before you start.
01
You already know
Module 07. Telegram account and prepared HTTPS n8n webhook instance.
02
Open these tools
BotFather, Telegram Trigger and Telegram Send Message in n8n.
03
Check the requirement
n8n hosting terms vary. This first bot uses a fixed response, no model API.
Module 09 / Build together
Your first small win.
Design a short factual welcome for a fictional community bot. Say it is a test bot, answers only practice FAQs and is not monitored for urgent requests. Do not invent meetup dates, links or services.
Module 09 / Build together
What happens between input and output?
1A bot is a message interface, not automatically AI.
2Telegram sends an event to an HTTPS webhook.
3The workflow chooses and sends the reply.
Module 09 / Build together
Step 01. Create your own test bot.
1Open the verified BotFather account in Telegram.
2Send /newbot and follow its name/username questions.
3Store the token privately; never paste it into the AI chat.
Module 09 / Build together
Step 02. Connect credentials.
1Create a test workflow and add Telegram Trigger.
2Put your token in n8n Telegram credentials.
3Select message events and confirm the public webhook uses HTTPS.
Module 09 / Build together
Step 03. Start a test event.
1Use the trigger test/listen control.
2Open your bot chat and send a test message.
3Inspect message.chat.id and message.text in n8n.
Module 09 / Build together
Step 04. Add one fixed reply.
1Connect Telegram with Message: Send Message.
2Set Chat ID to {{$json.message.chat.id}}.
3Use the reviewed welcome text as the message.
Module 09 / Build together
Step 05. Test in your own chat.
1Send a second message and check the reply.
2Check it returns only to the triggering chat.
3Keep the bot unpublished while testing.
Module 09 / Build together
Step 06. Choose a next step.
1Review before publishing a production workflow.
2Use a separate test bot: Telegram supports one webhook per bot.
3Add an AI summary only after this fixed reply is reliable.
Module 09 / Build together
Make the working version.
Write three practice FAQ answers for my test bot using only these fictional facts: free learning group; topics include prompts and automation; the next date is unconfirmed. For other questions say Ask the organiser. No urgent-service claims.
Module 09 / Build together
Ask for a review. Then check it.
Review this bot welcome and FAQ for invented information, ambiguous promises and inappropriate urgent-use claims. Keep it clear that this is a workshop test bot. Text: [paste].
Module 09 / Build together
Prove your result works.
1A test message appears in the trigger output.
2Reply goes to your own triggering chat.
3Unconfirmed dates stay unconfirmed.
Module 09 / Build together
When it does not work yet.
01
HTTPS webhook error
Use the prepared public HTTPS n8n address and correct WEBHOOK_URL.
02
Testing stops production
Use separate test/production bots or unpublish before testing.
Module 09 / Build together
Choose your next challenge.
01
Core complete
Show one checked output to a partner.
02
Extension 1
Route a known question with an If node.
03
Extension 2
Add a checked AI reply with explicit scope and cost controls.
Module 09 / Build together
Keep the result. Keep the evidence.
Receive a real test message through your own Telegram bot.
Save your filesSave your promptName the next change
Module 09 / Build together
Sources you can check.
01
Telegram
Create a bot
02
n8n
Telegram webhook issues
Build a bot that answers one question.
3 minutes
Outcome: Receive a real test message through your own Telegram bot. 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
n8n hosting terms vary. This first bot uses a fixed response, no model API. 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: Create a named test bot with BotFather and open its chat. 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. Create your own test bot.
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.
