Google Sheets + Telegram: review alerts you can trust
Review monitoring falls apart in the boring moments. Someone forgets to check listings, a bad review sits for days, and you only notice once refunds start showing up.
This is where Sheets Telegram alerts make life easier. E-commerce owners feel it first, but product leads and CX/reputation folks end up carrying the same load. You get clean, readable alerts and a running log without living in five dashboards.
You’ll set up an n8n workflow that pulls a watch list from Google Sheets, scrapes new reviews, summarizes sentiment with AI, logs everything back to Sheets, and pings you in Telegram with the important bits.
How This Automation Works
Here’s the complete workflow you’ll be setting up:
n8n Workflow Template: Google Sheets + Telegram: review alerts you can trust
flowchart LR
subgraph sg0["Schedule Flow"]
direction LR
n0@{ icon: "mdi:play-circle", form: "rounded", label: "Schedule Trigger", pos: "b", h: 48 }
n1@{ icon: "mdi:cog", form: "rounded", label: "Decodo", pos: "b", h: 48 }
n2@{ icon: "mdi:database", form: "rounded", label: "Get row(s) in sheet", pos: "b", h: 48 }
n3@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini Chat Model", 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/code.svg' width='40' height='40' /></div><br/>Code in JavaScript"]
n5@{ icon: "mdi:robot", form: "rounded", label: "Summarize Reviews", pos: "b", h: 48 }
n6["<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/>Alert Group"]
n7@{ icon: "mdi:swap-vertical", form: "rounded", label: "Loop Over Items", pos: "b", h: 48 }
n8@{ icon: "mdi:database", form: "rounded", label: "Store to Sheet", pos: "b", h: 48 }
n9@{ icon: "mdi:robot", form: "rounded", label: "Sentiment Analyzer", pos: "b", h: 48 }
n1 --> n4
n6 --> n7
n8 --> n7
n7 --> n1
n0 --> n2
n5 --> n6
n4 --> n9
n9 --> n8
n9 --> n5
n2 --> n7
n3 -.-> n9
n3 -.-> n5
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 n5,n9 ai
class n3 aiModel
class n2,n8 database
class n4 code
classDef customIcon fill:none,stroke:none
class n4,n6 customIcon
Why This Matters: Catching review problems before they spread
If you sell on Amazon or track multiple product URLs, reviews don’t arrive politely in one place. They land in different interfaces, at different times, with different levels of detail. So you check when you remember, copy-paste what seems important, then tell yourself you’ll “build a better system later.” Later rarely comes. Meanwhile, a shipping complaint repeats across five reviews, your team keeps running the same promo, and the damage quietly stacks up.
It adds up fast. Here’s where it usually breaks down.
- Someone has to manually open each listing or URL, which turns “quick monitoring” into about an hour of tab hopping.
- You end up reacting to the loudest review, not the most common issue, because there’s no consistent summary.
- Copying reviews into a spreadsheet invites messy formatting and missed context, so the log becomes hard to trust.
- Alerts are either too noisy or too late, and both outcomes mean you stop paying attention.
What You’ll Build: A watch list that turns reviews into clear Telegram alerts
This workflow runs on a schedule in n8n. It starts by reading your product URL watch list from Google Sheets, then processes each URL in small batches so one slow page doesn’t block everything. For each product, it uses the Decodo scraper to pull fresh review content, then a short JavaScript transform cleans and structures the data so it’s usable downstream. Next, Gemini (via an AI chat model node) and an AI chain summarize what people are saying and classify the sentiment. Finally, the workflow appends the structured result into a Google Sheets “review log” and sends a Telegram message with a concise summary plus the sentiment snapshot, so you can act immediately.
The workflow begins with a scheduled run and a simple spreadsheet lookup. Reviews get scraped, cleaned, analyzed, then written back into your log. Telegram is the “tap on the shoulder” that tells you something changed, without forcing you to go hunting.
What You’re Building
| What Gets Automated | What You’ll Achieve |
|---|---|
|
|
Expected Results
Say you track 20 product URLs. Manually, even a quick scan can take about 5 minutes per URL (open, scroll, skim, note), so you’re at roughly 100 minutes every check. If you do that five days a week, that’s about 8 hours of pure monitoring. With this workflow, you spend maybe 10 minutes maintaining the Google Sheets watch list, then each scheduled run does the scraping, sentiment, summary, and Telegram alerts automatically while you keep working.
Before You Start
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Google Sheets for the URL watch list and review log
- Telegram to receive review alerts in real time
- Decodo API credentials (get it from your Decodo account dashboard)
- Gemini API key (get it from Google AI Studio/console)
- Telegram bot token + chat ID (create a bot in BotFather, then capture your chat ID)
Skill level: Intermediate. You won’t write “software,” but you will install a community node and paste a few API keys into the right places.
Want someone to build this for you? Talk to an automation expert (free 15-minute consultation).
Step by Step
A scheduled run kicks it off. n8n starts the workflow at the interval you choose (hourly, daily, whatever fits your catalog and volume).
Your Google Sheet provides the “watch list.” The workflow reads rows that contain product URLs (Amazon listings or other pages you track), which keeps the whole system easy to maintain for non-technical teammates.
Each URL is scraped and cleaned. n8n loops through your URLs in batches, pulls the latest review content through Decodo, then runs a JavaScript transform to normalize fields (so summaries don’t get confused by messy text).
AI produces sentiment and a concise summary. Gemini analyzes the extracted reviews, labels sentiment, and generates a human-readable recap you can actually act on.
Results get logged and pushed to Telegram. The workflow appends each processed item into a Google Sheets log, then sends a Telegram message with the summary and sentiment snapshot.
You can easily modify the sentiment rules to only alert on negative reviews, or change the summary prompt to match your brand language. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Scheduled Trigger
Set up the workflow to run on a schedule so it can fetch review URLs and process them automatically.
- Add and open Scheduled Run Trigger.
- Keep the default Rule configuration if you plan to customize the schedule later in n8n’s UI.
- Connect Scheduled Run Trigger to Retrieve Sheet Rows to start the data flow.
Step 2: Connect Google Sheets
Pull the list of target URLs and write processed results back to a spreadsheet.
- Open Retrieve Sheet Rows and select your Google Sheet.
- Set Document to the sheet named
decodoand Sheet tolist urls. - Credential Required: Connect your googleSheetsOAuth2Api credentials in Retrieve Sheet Rows.
- Open Append to Spreadsheet and set Operation to
append. - Set Document and Sheet to your destination IDs, currently
[YOUR_ID]. - Map columns to expressions: Url =
{{ $('JavaScript Transform').item.json.url }}, Sentiment ={{ $json.sentimentAnalysis.category }}, List Review ={{ $json.reviews }}. - Credential Required: Connect your googleSheetsOAuth2Api credentials in Append to Spreadsheet.
Step 3: Batch and Scrape Review Data
Process the sheet rows in manageable batches and scrape each URL for reviews.
- Open Batch Loop Items and set Batch Size to
5. - Ensure Retrieve Sheet Rows connects to Batch Loop Items, and Batch Loop Items connects to Decodo Scraper.
- Open Decodo Scraper and set Operation to
amazon. - Set URL to
{{ $json.url }}so each row drives a scrape. - Credential Required: Connect your decodoApi credentials in Decodo Scraper.
url because Decodo Scraper reads {{ $json.url }} directly.Step 4: Transform Reviews and Run AI Analysis
Normalize the scraped data, run sentiment analysis, and generate a summary with Gemini.
- Open JavaScript Transform and keep the provided JavaScript Code to build the
reviewstext block and carry forward theurl. - Ensure JavaScript Transform outputs to Sentiment Evaluation.
- In Sentiment Evaluation, set Input Text to
{{ $json.reviews }}. - Open Review Summary Chain to keep default options for summarization.
- Verify Gemini Chat Engine is connected as the language model for both Sentiment Evaluation and Review Summary Chain.
- Credential Required: Connect your googlePalmApi credentials in Gemini Chat Engine (AI credentials should be added to the parent model node, not the chain or sentiment nodes).
results[0].content.results.reviews path to match your live response.Step 5: Configure Outputs and Notifications
Send results to Google Sheets and alert Telegram with sentiment and summary details.
- Confirm Sentiment Evaluation outputs to both Append to Spreadsheet and Review Summary Chain.
- Open Telegram Alert Notice and set Chat ID to your Telegram ID or group, replacing
[YOUR_ID]. - Keep the Text field as is to include dynamic values:
{{ DateTime.now().format('yyyy-MM-dd') }},{{ $('Sentiment Evaluation').item.json.sentimentAnalysis.category }},{{ $('JavaScript Transform').item.json.url }}, and{{ $json.output.text }}. - Credential Required: Connect your telegramApi credentials in Telegram Alert Notice.
- Note the loop-back design: Append to Spreadsheet and Telegram Alert Notice both connect back to Batch Loop Items to continue batch processing.
Step 6: Test and Activate Your Workflow
Validate that the workflow processes a batch correctly and sends outputs before enabling production runs.
- Click Execute Workflow to run from Scheduled Run Trigger and verify items flow to Retrieve Sheet Rows.
- Confirm a batch is created in Batch Loop Items and review the scrape output in Decodo Scraper.
- Check that Append to Spreadsheet appends new rows and Telegram Alert Notice sends a message with a summary.
- If results look correct, switch the workflow Active toggle on to run on schedule.
Troubleshooting Tips
- Google Sheets credentials can expire or lack access to the right file. If appends fail, check the connected Google account and confirm the Sheet ID and tab name match exactly.
- If you’re using Wait nodes or external scraping, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Telegram bot issues are usually simple: the bot isn’t in the chat, the chat ID is wrong, or the token was regenerated. Test-send a message from the Telegram node before you trust alerts.
- Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.
Quick Answers
About 45 minutes if you already have your API keys.
No. You’ll mostly paste credentials and confirm mappings, and the included transform code ships with the workflow.
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 and Decodo usage costs, which depend on how many pages you scrape.
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 the main reason to use n8n here. You can adjust the JavaScript Transform to change which fields you keep, then extend the Gemini prompt in the “Gemini Chat Engine” step to add things like themes, toxicity, or “top 3 complaints.” Many teams also add a filter right after “Sentiment Evaluation” so only negative (or only 1-star) results trigger Telegram, while everything still gets appended to the Google Sheets log.
Usually it’s permissions. The connected Google account can open the spreadsheet in a browser, but n8n wasn’t authorized for that same file, or the sheet/tab name changed. Reconnect the Google Sheets credential in n8n, then re-check the Sheet ID and worksheet name in both the “Retrieve Sheet Rows” and “Append to Spreadsheet” nodes.
On self-hosted n8n, there’s no execution cap; the limit is your server and how fast Decodo and Gemini respond.
Often, yes, because this isn’t just “move data from A to B.” You’re batching URLs, scraping, transforming data, then running sentiment and summarization before logging and alerting, which is the kind of multi-step flow that gets awkward (and expensive) on simpler automation tools. n8n also lets you self-host, which matters here because Decodo is a community node and the workflow is designed with self-hosting in mind. If you only needed “new row in Sheets → send Telegram message,” Zapier or Make would be fine. For review monitoring at any real scale, the control you get in n8n is worth it. If you want a second opinion on stack fit, Talk to an automation expert.
Once this is running, reviews stop being a surprise. You get the signal in Telegram, the paper trail in Sheets, and a lot more calm during the week.
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.
