RSS to Telegram, AI news briefings you will read
Keeping up with AI news sounds easy until you try. You open one article, then five tabs, then you’re “researching” instead of working, and the good stuff still slips by.
This RSS Telegram automation hits hardest for marketers who need quick angles, but founders and agency leads feel it too. You get a clean, readable briefing in Telegram, so you can skim the key takeaways in about a minute and move on.
Below is the exact n8n workflow that pulls new RSS stories, extracts the full article text, summarizes it with Gemini, and sends a polished update to your chat. You’ll also see what to tweak if you want more sources or a different briefing format.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: RSS to Telegram, AI news briefings you will read
flowchart LR
subgraph sg0["AI-News Feed Flow"]
direction LR
n0@{ icon: "mdi:robot", form: "rounded", label: "Generate Report", pos: "b", h: 48 }
n1@{ icon: "mdi:brain", form: "rounded", label: "Gemini 2.5 Flash", pos: "b", h: 48 }
n2["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Send a text message"]
n3@{ icon: "mdi:play-circle", form: "rounded", label: "AI-News Feed", pos: "b", h: 48 }
n4["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/jinaAi.dark.svg' width='40' height='40' /></div><br/>Read News from AI News Website"]
n3 --> n4
n0 --> n2
n1 -.-> n0
n4 --> n0
end
%% Styling
classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef disabled stroke-dasharray: 5 5,opacity: 0.5
class n3 trigger
class n0 ai
class n1 aiModel
classDef customIcon fill:none,stroke:none
class n2,n4 customIcon
The Problem: AI News Is Important, but It’s a Time Trap
You don’t need “more content.” You need signal. The problem is that the signal is buried inside long posts, half-rewritten press releases, and articles that take 8 minutes to read just to learn one useful point. So you bounce between RSS, Twitter/X threads, newsletters, and browser bookmarks, telling yourself you’ll “save it for later.” Later never comes. Meanwhile, meetings still happen, campaigns still ship, and you’re making decisions without the latest context because your attention got spent on hunting, not understanding.
The friction compounds. Here’s where it usually breaks down.
- You end up scanning headlines instead of reading the substance, which leads to half-informed takes and wasted discussions.
- When you do read, it’s in the worst place possible: inside a browser with distractions everywhere.
- Sharing a useful article with your team turns into extra work because you still have to summarize it, add context, and paste it into chat.
- RSS is “organized,” but it still makes you do the hard part: deciding what matters and translating it into a quick brief.
The Solution: Turn New RSS Items into Gemini Briefings in Telegram
This workflow acts like a lightweight AI analyst that lives in your Telegram. It starts when an AI news site publishes a new RSS item. n8n grabs the article link, then uses Jina AI to fetch the full, cleaned article text (not just the snippet). That full text is passed into a Gemini 2.5 Flash prompt that produces a structured briefing, written to be read quickly and forwarded easily. Finally, n8n sends the formatted report to your chosen Telegram chat, group, or channel so you can skim it where you already communicate. No tab hopping. No “I’ll read it later.”
The workflow begins with an RSS trigger, pulls the article body with Jina AI, and then uses Gemini to generate the briefing. After that, Telegram gets a single message that’s already cleaned up and readable, so you can act on it immediately.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you normally check 2 sources each morning: an RSS reader and a few “must-scan” tabs. If you open 6 articles and spend about 7 minutes each (read, skim, decide, maybe share), that’s roughly 40 minutes per day. With this workflow, the “manual” part becomes almost nothing: you glance at Telegram for 2 minutes, and only open the one link that actually matters. The summary does the sorting for you, and you get your morning back.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Telegram for delivering briefings to a chat.
- Jina AI to extract clean article text.
- Google Gemini API key (get it from Google AI Studio).
Skill level: Beginner. You’ll connect a few accounts, paste API keys, and test one message end-to-end.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A new RSS story shows up. The workflow monitors an AI news RSS feed and triggers as soon as a new item is published, so you’re not polling feeds manually.
The article content gets pulled and cleaned. Instead of summarizing a short RSS excerpt, n8n sends the article URL to Jina AI and retrieves the full readable text, which means better summaries and fewer “what is this even about?” moments.
Gemini writes the briefing. Gemini 2.5 Flash receives the cleaned text and produces a structured report based on the workflow’s prompt (think: key points, why it matters, and a professional tone you can forward).
Telegram receives the final update. The workflow sends a formatted message to your chosen Telegram destination, so your “news inbox” becomes a chat thread you can skim, search, and share.
You can easily modify the RSS feed source and the briefing format based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the RSS Feed Trigger
This workflow starts by polling an AI news RSS feed for new articles.
- Add and open AI News RSS Trigger.
- Set Feed URL to
https://www.artificialintelligence-news.com/feed/. - In Poll Times, keep Mode as
everyMinuteto check frequently. - Leave Flowpast Branding as-is; it’s a sticky note for documentation.
Step 2: Connect Jina AI for Article Extraction
Next, the workflow fetches full article content from each RSS item.
- Add and open Fetch Article Content.
- Set URL to the expression
{{ $json.link }}. - Credential Required: Connect your jinaAiApi credentials.
- Ensure AI News RSS Trigger is connected to Fetch Article Content.
Step 3: Set Up AI Summarization and Prompting
The LLM chain uses Gemini to synthesize a Telegram-ready briefing from the scraped article content.
- Open Gemini Flash Model and connect it to Compose Daily Brief as the language model.
- Credential Required: Connect your googlePalmApi credentials in Gemini Flash Model.
- Open Compose Daily Brief and set Text to the full prompt provided, starting with
You are an expert AI Technology Analyst.... - Confirm the input placeholders in the prompt use expressions like
{{ $json.title }},{{ $json.content }}, and{{ $json.publishedTime }}. - Ensure Fetch Article Content connects to Compose Daily Brief on the main path.
Step 4: Configure Telegram Delivery
The final message is delivered as an HTML-formatted Telegram update.
- Add and open Dispatch Telegram Update.
- Set Text to the expression
{{ $json.text }}. - Set Chat ID to
[YOUR_ID](replace with your Telegram chat or channel ID). - In Additional Fields, set Parse Mode to
HTML. - Credential Required: Connect your telegramApi credentials.
Step 5: Test and Activate Your Workflow
Verify the end-to-end flow and then enable production runs.
- Click Execute Workflow to run a manual test from AI News RSS Trigger.
- Confirm Fetch Article Content returns the scraped article content from the RSS item.
- Verify Compose Daily Brief outputs a single Telegram-ready HTML message.
- Check Telegram to ensure Dispatch Telegram Update posts the formatted briefing.
- Toggle the workflow to Active to enable continuous polling.
Common Gotchas
- Telegram bot credentials can expire or be pointed at the wrong chat. If things break, check the bot token and Chat ID in the Telegram node first.
- If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.
Frequently Asked Questions
About 30 minutes if you already have your API keys.
No. You’ll paste credentials, choose a chat, and run a test message. The workflow logic is already built.
Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in Gemini API usage and Jina AI usage, which depend on how many articles you process.
Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.
Yes, and it’s one of the best upgrades. Duplicate the RSS trigger node, point it at another feed URL, and connect it into the same “Fetch Article Content” step. Most people also tweak the “Compose Daily Brief” prompt so the output groups stories by theme and keeps a consistent length. If you want one single daily message instead of one-per-article, you can add a schedule trigger plus a small buffer (for example, store items in Google Sheets, then summarize them in one batch).
Usually it’s the bot token or the Chat ID. Regenerate the Telegram bot token (or re-copy it carefully) and update the credentials in n8n, then confirm the chat really allows the bot to post. If you’re sending to a group, the bot often needs to be added first and sometimes needs admin permission to post. One more thing: if your Gemini step produces empty output because the article fetch failed, Telegram will look “broken” even though the real issue is upstream.
A lot, as long as your API limits can keep up.
Often, yes, because this workflow benefits from a few n8n strengths. You can run more complex logic without paying extra for branching, and self-hosting removes execution caps (your server becomes the limit). n8n also makes it easier to control the “shape” of the data going into the AI prompt, which matters for summary quality. Zapier or Make can still be fine for a simple RSS → message zap, but once you add full-text extraction plus structured AI output, you’ll appreciate the flexibility. Talk to an automation expert if you want help choosing.
Set this up once and your news comes to you, already summarized and already readable. The workflow handles the repetitive stuff, and you keep your attention for work that actually moves things forward.
Need Help Setting This Up?
Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.
