Perplexity to Telegram, AI news digest your team reads
You start the day with good intentions. Then you lose 30 minutes bouncing between X threads, newsletters, and product blogs, trying to figure out what actually matters in AI.
Marketing leads feel it when they need angles for campaigns. Founders feel it because “keeping up” quietly becomes a second job. And ops folks end up pasting links into chats anyway. This Perplexity Telegram digest automation turns that mess into one clean update your team will actually read.
Below is the exact n8n workflow that pulls high-signal AI news, blocks repeats with Google Sheets, and posts a consistent daily digest to Telegram (with options for Gmail, Slack, and Google Docs too).
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Perplexity to Telegram, AI news digest your team reads
flowchart LR
subgraph sg0["Schedule Flow"]
direction LR
n0@{ icon: "mdi:play-circle", form: "rounded", label: "Schedule Trigger", pos: "b", h: 48 }
n2@{ icon: "mdi:database", form: "rounded", label: "Sheet Log", pos: "b", h: 48 }
n3["<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/perplexity.dark.svg' width='40' height='40' /></div><br/>Perplexity Daily Search (Pas.."]
n4@{ icon: "mdi:robot", form: "rounded", label: "Formatter Agent", pos: "b", h: 48 }
n5["<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/>Telegram"]
n5 --> n2
n4 --> n5
n0 --> n3
n3 --> n4
end
subgraph sg1["Flow 2"]
direction LR
n1@{ icon: "mdi:database", form: "rounded", label: "REDACTED", pos: "b", h: 48 }
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 n0 trigger
class n4 ai
class n2,n1 database
classDef customIcon fill:none,stroke:none
class n3,n5 customIcon
The Problem: “AI News” Becomes Noise (Fast)
AI moves quickly, which is exciting until you’re the one responsible for staying current. You skim ten sources, save a few links, and still feel behind because half the posts are recycled takes. Then you share updates in your team chat and realize you already sent that same story last week, just worded differently. It’s not only time. It’s credibility. Once your “daily updates” repeat themselves, people mute the channel and you’re back to square one.
The friction compounds. A little manual work every morning turns into a permanent habit you can’t drop.
- Most “daily digest” routines depend on one person’s memory, so duplicates slip in and trust drops.
- Finding high-signal stories means opening lots of tabs, then second-guessing what is actually worth sharing.
- Even when you find good stories, formatting them for Telegram so it’s readable takes longer than it should.
- If you skip a day, the backlog grows and the next update feels impossible to summarize cleanly.
The Solution: A Daily Perplexity-Powered Digest That Self-Polices Repeats
This n8n workflow runs on a schedule (preconfigured for 10AM) and asks Perplexity for the most relevant AI developments from the last 24 hours, pulling from trusted sources like OpenAI, DeepMind, HuggingFace, and MIT Tech Review. The raw findings then go through an AI formatting step using an OpenAI chat model and an “agent” style prompt, which cleans up the output, summarizes each item, and standardizes the structure so your digest always looks the same. Before anything gets posted, the workflow checks a Google Sheets archive to see what’s already been shared. If it’s a repeat (or too close to one), it gets filtered out. Finally, the workflow sends a polished message to Telegram, and can also fan out updates to Slack, Gmail, or a Google Doc if you want a searchable log.
The workflow starts with a Schedule Trigger at 10AM. Perplexity is queried via HTTP Request, then the results are merged, cleaned, and deduped against Google Sheets using simple “If” logic. After the formatter produces a readable digest, Telegram publishes it in one post (and optional side channels can receive the same digest).
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you normally spend about 45 minutes each morning: 20 minutes collecting links, 15 minutes deciding what’s real news, and 10 minutes rewriting it into a Telegram-friendly format. With this workflow, you spend about 1 minute skimming the post after it lands at 10AM, then you’re done. Perplexity + formatting runs in the background, and the Google Sheets archive stops repeats automatically. That’s roughly 3 hours back each week, without lowering quality.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Perplexity to source the daily news feed.
- Telegram to publish the digest to a group/channel.
- Google Sheets API access (get it from Google Cloud console credentials)
Skill level: Intermediate. You’ll mostly connect accounts and paste IDs/keys, but community nodes require self-hosting and basic troubleshooting.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A daily schedule kicks it off. At 10AM, n8n triggers the workflow automatically, so nobody has to remember to “send the update.”
Perplexity gathers the raw input. An HTTP request pulls AI news based on “last 24 hours” and trusted sources, which helps avoid the usual hype cycle content.
AI cleans and standardizes the digest. An OpenAI chat model plus an agent-style formatter turns the raw results into short summaries, consistent sections, and clean links. This is the difference between “a dump of URLs” and something your team can scan.
Google Sheets blocks repeats, then Telegram posts. The workflow checks a sheet of previously shared items, filters out anything that looks duplicated, and sends the final message to your Telegram channel. If you want, the same digest can be routed to Gmail, Slack, or saved into Google Docs for reference.
You can easily modify the schedule time to match your team’s standup, or change the sources Perplexity is instructed to prioritize based on your niche. See the full implementation guide below for customization options.
Common Gotchas
- Google Sheets credentials can expire or need specific permissions. If things break, check the Google Cloud console project and the sheet’s sharing settings 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
Plan on about 45 minutes if you already have your accounts and keys.
No. You’ll connect services, paste a few IDs, and adjust prompts.
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 OpenAI and Perplexity API usage, which is usually a small daily cost for one digest.
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 honestly the first thing you should tweak. Change the Schedule Trigger to your preferred time, then adjust the Perplexity query text in the HTTP Request step to emphasize your sources and topics (for example, “AI marketing tools,” “security,” or “open-source LLMs”). If you want a tighter format, edit the AI Agent/OpenAI prompt so it outputs fewer items or enforces a strict template. Common customizations include sending a shorter weekend digest, routing a “breaking news” version to Slack, and saving the final post into Google Docs for leadership review.
Usually it’s an incorrect bot token or the bot hasn’t been added to the channel with permission to post. Double-check the token in n8n credentials, confirm the chat/channel ID, and make sure Telegram didn’t restrict the bot after a permission change. If it worked yesterday and fails today, regenerate the token and update it.
A daily digest is easy for any setup; scale mainly depends on your n8n plan and how many channels you post to.
It depends on what you mean by “better.” For a daily AI digest, n8n is a stronger fit when you need branching logic (dedupe checks, conditional routing), more control over prompts, and the option to self-host because this workflow uses community nodes that require it. Zapier and Make can still do a simpler version, but you’ll often hit limits when you try to store history, merge results, and format long messages cleanly. If your goal is “one prompt, one email,” those tools might feel quicker. If your goal is a repeat-proof team digest that runs every day without babysitting, n8n is the safer bet. Talk to an automation expert if you’re not sure which fits.
Once this is running, your “AI news” habit stops depending on willpower. The workflow handles the repetitive stuff, and your team gets one reliable digest they can trust.
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.
