Skip to content
AIOpenAlt AI Labs

Automate a news channel: RSS to Telegram with n8n

A free starter challenge. Build an n8n workflow that reads an RSS feed on a schedule, keeps only the items you care about, and posts them to your own Telegram channel.

  1. 1Learn
  2. 2Do
  3. 3Submit
  4. 4Results
Category
AI
Lesson
25 min
Effort
~4h
Prize
Free
Closes in
 

Learn

25 min lesson

What you'll learn

How to build your first automation in n8n: a workflow that reads news from an RSS feed, keeps only what matters, and posts it to your own Telegram channel on a schedule. This is the same pattern companies use to watch prices, job posts and competitors.

The pieces

  • n8n is a visual tool for workflows: boxes called nodes, joined by lines. Use n8n Cloud on a free trial, or run it yourself if you know how.
  • An RSS feed is a list of the latest posts from a site, in a format machines can read. Most news sites have one. Try 24.kg, Kaktus.media, a blog you like, or a job board.
  • A Telegram bot posts for you. Create one by messaging @BotFather and sending /newbot. It gives you a token: treat it like a password.
  • A Telegram channel you create, with the bot added as an administrator so it can post.

Build it in this order

  1. Schedule Trigger. Run every hour, or twice a day. Start with "every minute" while testing, then slow it down.
  2. RSS Read. Paste the feed URL. Run the node and look at the output: title, link, date, summary.
  3. Filter. Keep only items that matter to you, for example titles containing "IT", "стартап" or "грант". Run it and check that something passes and something is dropped.
  4. Remove duplicates. Without this, the same story posts every hour. Use the Remove Duplicates node set to skip items seen in previous runs, keyed on the link.
  5. Telegram. Action: send message. Chat ID: your channel's @username. Text: the title, a blank line, then the link. Use the expression editor to drag fields in.

Run the whole workflow by hand. When the post appears in your channel, switch the workflow to Active.

Keep it tidy

Rename every node so someone else can read the workflow: "Every 2 hours", "Kaktus RSS", "Only grants", "Post to channel". Store the bot token as an n8n credential, never in a text field.

Export the workflow

From the workflow menu, choose Download. You get a JSON file. Open it and search for your bot token; it should not be there, because credentials are stored separately. If it is, remove it before sharing.

Before you submit

Let it run on schedule for at least a day, so the channel shows several automatic posts at different times. Make the channel public and copy its t.me link. Upload the workflow JSON to a public Google Drive link or a GitHub Gist, and submit both links.

Finish the lesson to unlock submitting.

Sign in to start learning

Do

about 4h of work

The task

Automation is one of the fastest skills to turn into paid work: shops, media and agencies all want someone who can make information move on its own. In this challenge you build a real workflow in n8n. On a schedule, it reads an RSS feed, filters the items by a rule you choose, skips anything it has already posted, and sends the rest to a public Telegram channel you created, through a bot you made with BotFather. You leave it running long enough to prove it works on its own, and you export the workflow so others can see how it is built.

Deliverables

  1. 01The public t.me link to your Telegram channel
  2. 02The workflow exported as JSON, at a public Google Drive or GitHub Gist link
  3. 03A screenshot of the workflow canvas with every node named

Acceptance criteria

Judged against exactly these

  • The workflow starts with a Schedule Trigger and reads at least one RSS feed
  • A filter step keeps only items that match a rule you chose, and the write-up says what the rule is
  • Duplicates are handled, so the same item is not posted twice
  • The channel shows several automatic posts made at different times over at least one day
  • Every node has a descriptive name
  • The exported JSON contains no bot token or other credential

Rules

  • Complete the lesson first. The submit form unlocks once you mark it done.
  • Submit a link to your work: a public GitHub repo or PR for code challenges; YouTube, Google Drive or Docs, Figma, Notion or a live site for everything else.
  • AI tools are allowed and encouraged. Plagiarised or copied work is disqualified.
  • The work must be made during the challenge window. For code, the commit history must show it.
  • An AI reviewer pre-scores every entry against the acceptance criteria. A human makes the final decision.
  • On payout, Alt AI Labs receives a licence to use the winning work (MIT for code). Non-winning entries stay yours.
  • Do not include secrets, API keys or anyone's personal data.
  • Post only to a channel you own. Link to the original article rather than copying it in full.
n8nautomationtelegramrss

Submit

Sign in and complete the lesson to submit. Entry is free.

Sign in

Results

  1. 01

    AI pre-score

    AI reviews your write-up against the acceptance criteria. It cannot open your link, so explain your work clearly.

  2. 02

    Human decision

    A human reviews the work itself and makes the final call. The AI score is advisory.

  3. 03

    Win

    There is no cash prize. Winning work is shown to the organization behind the challenge.

Posted by

Alt AI Labs