Amazon to Telegram, price drop alerts you can trust
Refreshing an Amazon page “one more time” is a special kind of time drain. You check, the price hasn’t moved, you forget for a few hours, and then the deal drops while you’re busy doing something else.
This is where Amazon Telegram alerts help a lot. Marketing managers watching gear for campaigns feel it. So do agency owners buying client equipment, and small ops teams trying to keep costs under control without living in a browser tab.
This workflow monitors any Amazon product page on a schedule, uses AI to extract the current price reliably, and messages you in Telegram the moment it hits your target. You’ll see how it works, what you need, and the gotchas that usually trip people up.
How This Automation Works
See how this solves the problem:
n8n Workflow Template: Amazon to Telegram, price drop alerts you can trust
flowchart LR
subgraph sg0["AI Agent Flow"]
direction LR
n0@{ icon: "mdi:swap-vertical", form: "rounded", label: "Set: Success Message", pos: "b", h: 48 }
n1@{ icon: "mdi:swap-vertical", form: "rounded", label: "Set: Error Message", pos: "b", h: 48 }
n2@{ icon: "mdi:swap-vertical", form: "rounded", label: "Config: Product & Alert", pos: "b", h: 48 }
n3@{ icon: "mdi:robot", form: "rounded", label: "AI Agent", pos: "b", h: 48 }
n4@{ icon: "mdi:cog", form: "rounded", label: "Schedule Trigger1", pos: "b", h: 48 }
n5@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini Chat Model1", pos: "b", h: 48 }
n6@{ icon: "mdi:memory", form: "rounded", label: "Memory", pos: "b", h: 48 }
n7@{ icon: "mdi:robot", form: "rounded", label: "Structured Output Parser", pos: "b", h: 48 }
n8["<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 Error"]
n9["<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 Success"]
n10@{ icon: "mdi:swap-horizontal", form: "rounded", label: "If", pos: "b", h: 48 }
n11@{ icon: "mdi:swap-horizontal", form: "rounded", label: "IF: Price = Target?", pos: "b", h: 48 }
n12["<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/httprequest.dark.svg' width='40' height='40' /></div><br/>Fetch HTML"]
n13["<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/>Parse and clean HTML"]
n10 --> n11
n10 --> n1
n6 -.-> n3
n3 --> n10
n12 --> n13
n4 --> n2
n1 --> n8
n11 --> n0
n13 --> n3
n0 --> n9
n2 --> n12
n7 -.-> n3
n5 -.-> n3
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,n7 ai
class n5 aiModel
class n6 ai
class n10,n11 decision
class n12 api
class n13 code
classDef customIcon fill:none,stroke:none
class n8,n9,n12,n13 customIcon
The Challenge: Catching real price drops without babysitting
Manual price checking looks harmless until you do the math. You open the product page, wait for Amazon to load the “real” price, double-check the seller, then repeat tomorrow. And the day after. It’s not just the minutes. It’s the mental load of remembering what your target was, which link was the right one, and whether the price you saw was even comparable to yesterday’s. Worse, the moment you actually need the discount (budget approval, purchase window, Black Friday), you’re the one stuck refreshing.
It adds up fast. Here’s where it breaks down in real teams.
- People screenshot prices or paste links into chat, and then nobody knows if the price changed since the screenshot.
- Browser extensions and basic trackers fail when Amazon tweaks layout elements or swaps in different price blocks.
- You miss short windows like lightning deals because nobody was watching at the exact right moment.
- Tracking more than a couple products turns into a messy spreadsheet that still requires manual checking.
The Fix: An AI-powered Amazon price tracker that pings Telegram
This n8n workflow runs in the background on a schedule you choose (hourly is common). Each run pulls the product page HTML, strips out the junk (scripts, styles, clutter), and hands the cleaned text to an AI model (Google Gemini in this build). Instead of relying on brittle CSS selectors, the AI reads the page like a human would and returns structured fields: product name and a numeric price. From there, the workflow validates that a price was actually extracted, compares it against your target, and sends a Telegram message only when the number is at or below your threshold. If the extraction fails, you get an error alert so you’re not assuming “no news” means “no change.” Honestly, that last part is what makes it trustworthy.
The workflow starts with a scheduled trigger and a single configuration node where you set the Amazon URL, target price, and Telegram chat ID. Then it fetches the page, cleans it, uses Gemini to extract the price, and routes to either a success Telegram alert (deal hit) or an error Telegram alert (something went wrong).
What Changes: Before vs. After
| What This Eliminates | Impact You’ll See |
|---|---|
|
|
Real-World Impact
Say you’re tracking 5 items for a campaign kit. Manually, you’ll spend maybe 5 minutes per item to open the page, check the right price, and note it down, which is about 25 minutes per round. Do that once a day and you’ve burned roughly 2 hours in a work week. With this automation: you spend about 10 minutes once to add URLs and targets, then you just wait for Telegram pings when a target hits.
Requirements
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Amazon product URL for the item you want tracked.
- Telegram bot to send messages into your chat.
- Google Gemini API key (get it from Google AI Studio / Gemini API credentials).
Skill level: Beginner. You’ll connect credentials, paste a URL, set a target price, and test a run.
Need help implementing this? Talk to an automation expert (free 15-minute consultation).
The Workflow Flow
A schedule kicks it off. The Cron trigger runs at the interval you choose, then loads your settings from a single config node (Amazon URL, target price, Telegram chat ID).
The product page is fetched and cleaned. n8n grabs the HTML with an HTTP Request, then a code step removes unnecessary markup so the AI receives mostly the content that matters.
AI extracts a structured price. The AI Agent uses the Gemini chat model plus a structured output parser to return predictable JSON fields like productName and priceValue. A quick validation check confirms the price is usable before doing any comparisons.
Telegram gets the right message. If the price is at or below your target, the workflow formats a success alert with the name, price, and link, then sends it. If extraction fails, it routes to an error message so you know to investigate.
You can easily modify the schedule frequency and the alert message format based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Scheduled Trigger
Set up the scheduled trigger to start the monitoring run on a recurring interval.
- Add the Scheduled Automation Trigger node to your workflow canvas.
- Configure the schedule parameters in Scheduled Automation Trigger to match your desired monitoring frequency.
- Connect Scheduled Automation Trigger to Define Product & Alert.
Step 2: Connect the Web Data Source
Define the product and target URL, then retrieve and clean the product page content.
- In Define Product & Alert, set the product name, URL, and any alert parameters you need for tracking.
- Connect Define Product & Alert to Retrieve Web Page.
- In Retrieve Web Page, set the request URL to the product page (use the value defined in Define Product & Alert if applicable).
- Connect Retrieve Web Page to Clean HTML Content.
- In Clean HTML Content, add code to strip unnecessary HTML and return the clean text for AI evaluation.
Step 3: Set Up AI Price Evaluation
Use the AI agent to analyze the cleaned content and determine the price outcome.
- Add AI Decision Agent and connect Clean HTML Content to it.
- Attach Gemini Chat Model as the language model for AI Decision Agent.
- Attach Conversation Memory Buffer as the memory source for AI Decision Agent.
- Attach Structured Output Reader as the output parser for AI Decision Agent.
- Configure AI Decision Agent prompts or system instructions to extract the current price and compare against the target.
Step 4: Configure Routing and Alerts
Route AI decisions through conditional checks and send success or error alerts via Telegram.
- Connect AI Decision Agent to Branch Logic Check.
- Set conditions in Branch Logic Check to decide whether to proceed to price validation or send an error path.
- Connect the “true” output of Branch Logic Check to Validate Price Threshold, and the “false” output to Assign Error Notice.
- Configure Validate Price Threshold conditions for your target price comparison.
- Connect Validate Price Threshold to Assign Success Notice.
- Connect Assign Success Notice to Dispatch Success Alert and Assign Error Notice to Dispatch Error Alert.
Step 5: Test and Activate Your Workflow
Validate the full flow from scheduled trigger to Telegram alerts and then activate it for production use.
- Click Execute Workflow to run a manual test from Scheduled Automation Trigger.
- Confirm the execution path: Scheduled Automation Trigger → Define Product & Alert → Retrieve Web Page → Clean HTML Content → AI Decision Agent → Branch Logic Check.
- Verify that either Dispatch Success Alert or Dispatch Error Alert sends the correct Telegram message.
- If the output is correct, toggle the workflow to Active to enable scheduled monitoring.
Watch Out For
- Telegram credentials can expire or the bot can lose permission to post in a group chat. If things break, check the bot is still in the chat and confirm the chat ID is correct 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.
Common Questions
About 30 minutes if you already have your Telegram bot and Gemini key.
Yes. You’ll mostly paste values into the config node and connect two credentials, then run a test execution to confirm messages arrive.
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 Google Gemini API usage, which depends on how often you check and how large the pages are.
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.
Start in the Define Product & Alert (config) node and adjust the URL, target price, and chat ID. If you want multi-channel alerts, duplicate the Dispatch Success Alert node and add Email (Send Email) or another chat tool. To track multiple products, replace the single URL with a Google Sheets read and pass each row into Retrieve Web Page so every item runs through the same extraction and threshold check.
Usually it’s the bot token or chat ID. Regenerate the token in BotFather if needed, then update the Telegram credential in n8n and make sure the bot can post in that chat (especially for groups). If it fails only sometimes, Telegram rate limits can show up when you send many messages quickly, so batching or reducing frequency helps.
It scales to a lot of products, but your limits will come from how often you run it and your AI/API usage.
Often, yes, because this workflow needs a few things that are awkward in simpler tools: cleaning HTML, using an AI model with structured output, then validating and branching based on the result. n8n handles that logic cleanly without turning into a maze of paid “paths.” You also have the option to self-host, which changes the economics if you’re checking prices frequently. Zapier or Make can still work if you’re using a dedicated price tracking service that already outputs a clean price (so your automation is basically “if price < target, send Telegram”). If you’re unsure, Talk to an automation expert and describe your tracking volume.
Once this is live, deal hunting becomes passive. The workflow watches, validates, and pings you with the exact link when it’s time to buy.
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.
