Workflow Templates

How it works Downloads markdown documents from a Google Drive folder containing private information, uses the Ollama model to identify and extract sensitive data, and stores the sanitized text in a single combined markdown document. Setup Steps Google cloud OAuth credentials for accessing google drive. A local Ollama model (currently using Ollama 3.1). Local instance of N8N (for example, running in docker).

Description: Turn your n8n workflow into an automated competitive intelligence unit. This template monitors competitor activities across blog feeds and YouTube channels to detect strategic shifts. Instead of simply aggregating links, it uses Apify to fetch full video transcripts and Google Gemini to analyze the content's underlying message, tone, and positioning. The final output is a structured strategic briefing sent to Telegram and archived in Notion for long-term research. Who is this for This workflow is designed for market researchers, founders, and content strategists who need deep insights into competitor activities without manually scrubbing video timelines or reading daily blog posts. How it works Ingest: The workflow pulls the latest articles from configured RSS feeds and searches for new videos on specific YouTube channels. Deep Dive: It automatically triggers an Apify actor to scrape the full transcript of any new video, ensuring the AI analyzes the spoken content rather than just metadata. Analyze: Google Gemini processes the consolidated text to identify core messages, hidden strategies, and suggests potential counter-tactics. Report: Telegram:** Delivers a concise HTML executive summary with direct source links. Notion:** Appends a comprehensive report to a database using formatted Notion Blocks (Headings, Toggles, and Bullet points). Requirements Apify Account:** A free account is sufficient to run the youtube-transcript-scraper. Services:** Google Gemini (PaLM), YouTube Data API, Telegram, Notion. How to set up Credentials: Configure your API keys for YouTube, Apify, Google Gemini, Telegram, and Notion. Notion Setup: Create a new Database with two properties: Name (Title) and date (Date). Copy the Database ID from the URL into the Notion node. Data Sources: Update the Channel ID in the YouTube nodes to track your target competitors. Update the Feed URL in the RSS nodes. How to customize the workflow Scale Up:** To monitor more competitors, duplicate the YouTube or RSS nodes in the "Data Sources" section and connect them to the Merge node. Adjust Analysis:* Modify the system prompt in the *Google Gemini** node to focus on specific intelligence needs (e.g., "Focus on pricing changes" or "Identify new feature releases"). Token Optimization:** Use the configuration in the Code - Data Prep node to limit the number of items processed daily if you are using free-tier API limits. Need Help or Want to Customize This? Contact me for consulting and support: Email: cuongnguyen@aiops.vn

How it works: Get multi social platform data for creators from CRM contacts. Step by step workflow to enrich CRM contacts with multi social (Instagram, Tiktok, Youtube, Twitter, Onlyfans, Twitch and more) profiles, analytics and metrics using the influencers.club API, and tailor onboarding flows and offers to increase activation rates. Set up: Hubspot (can be swapped for any DB, Salesforce, Google Sheet) Influencers.club

Description This workflow automates the process of finding new content ideas by scraping trending news and social media posts, analyzing them with AI, and delivering a summarized report to Slack. It is perfect for content marketers, social media managers, and strategists who spend hours researching trending topics manually. Who is this for Content Marketers: To discover trending topics for blogs or newsletters. Social Media Managers: To keep up with competitor activity or industry news. Market Researchers: To monitor specific keywords or brands. How it works Schedule: The workflow runs automatically on a weekly schedule (default is Monday morning). Data Collection: It uses Apify to scrape the latest news from Google Search and recent posts from specific Facebook pages. Data Processing: The results are merged, and the top 5 most relevant items are selected to prevent information overload. AI Analysis: An AI Agent (powered by OpenRouter/LLM) analyzes each article to classify it into a theme (e.g., Marketing, Technology, Strategy) and extracts 3 catchy keywords. Notification: The analyzed insights, including the theme, keywords, summary, and original URL, are formatted and sent directly to Slack. Requirements Apify Account: You need an API token and access to the Google Search Results Scraper and Facebook Posts Scraper actors. OpenRouter API Key: Used to power the AI analysis (can be swapped for OpenAI/Anthropic if preferred). Slack Account: To receive the notifications. How to set up Configure Credentials: Open the Workflow Configuration node and paste your Apify API Token and OpenRouter API Key. Connect your Slack account in the Slack node. Adjust Apify Settings: In the Apify Google news node, change the search query (currently set to "Top News" in Japanese) to your desired topic. In the Apify Facebook node, update the startUrls to the Facebook pages you want to monitor. Customize AI Prompt: (Optional) Open the AI Agent node to adjust the language or the specific themes you want the AI to classify. How to customize Change the LLM: Replace the OpenRouter model with the OpenAI or Anthropic Chat Model node if you prefer those providers. Increase Data Volume: Adjust the "Limit 5 items" Code node to process more articles at once (mind your API usage limits). Change Destination: Replace the Slack node with Notion, Google Sheets, or Email to save the ideas elsewhere. ⚠️ Crucial Checklist Before Submission The n8n team will reject templates that contain non-English text in the nodes. Please apply these changes to your workflow in the n8n editor before exporting the JSON for submission: Rename Nodes to English: Cron トリガー → Schedule Trigger Function: Slackメッセージ作成 → Format Slack Message Slack: 企画ネタ投稿 → Slack Post Function: LLMレスポンス整形 → Parse LLM Response Merge Data (統合) → Merge Data Function: データ抽出・5件制限 → Limit to 5 Items Function: Googleデータ抽出 → Extract Google Data Function: Facebookデータ抽出 → Extract FB Data Translate Code Comments & Prompts: Inside the Code nodes, ensure comments are in English (e.g., // Slackへの投稿メッセージを作成します → // Create message for Slack). Inside the AI Agent node, translate the System Prompt into English (e.g., "You are a professional content planner..." instead of "あなたはプロの..."). Even if you want the output in Japanese, the template default should usually be English, or clearly labeled as a Japanese template. Add the Mandatory Sticky Note: Add a Yellow Sticky Note to the canvas. Paste the "Description" text (from step 2 above) into this sticky note. Place it clearly next to the start of the workflow. Remove Hardcoded IDs: Ensure MASKED_USER_ID and MASKED_WEBHOOK_ID are cleared out or set to expressions that reference the user's setup.

Instagram Reel Downloader & Logger Automate Instagram Reel Downloads, Storage, and Activity Logging What does this workflow do? Handles incoming webhook requests (ideal for Instagram/Facebook API triggers). Validates the webhook via challenge-response and custom verify token. Checks for messages from yourself (filtering automated/self-triggered runs). Downloads Instagram Reels from URLs posted to the webhook. Uploads the reel to Google Drive and retrieves the download URL. Logs reel details (status, URL, and timestamp) to a Google Sheet for record-keeping. Notifies you on Telegram with the download details and Google Drive link. How does it work? Webhook: Listens for new messages/events (custom webhook endpoint for Meta). Validation: Confirms webhook subscribe/challenge and verify token from Meta API. Sender Check: Ignores messages unless they match your configured sender/recipient. Download Reel: Fetches the reel/attachment from Instagram using received URLs. Timestamp Gen: Adds a precise timestamp and ISO-based unique ID to the activity log. Upload to Drive: Saves the downloaded reel in a preset Google Drive folder. Log to Sheet: Updates a Google Sheet with the reel’s status, URL, and timestamp. Telegram Alert: Instantly notifies you when a new reel is downloaded and logged. What do I need to make this work? A registered webhook endpoint (from your Meta/Instagram app configuration). A Google Drive and Google Sheets account (OAuth2 connected to n8n). A Telegram Bot and Chat ID setup to receive download completion messages. The correct verify_token in your webhook event source matches your template (‘youtube-automation-n8n-token’ by default). Update your Drive/Sheet/Bot credentials as per your n8n instance’s environment. Why use this? Fully automates the collection and archival of Instagram Reels. Centralizes content download, backup, and activity records for your automation flows. Provides instant monitoring and archival of each event. Setup Tips: Make sure your webhook path and Meta app configuration match (/n8n-template-insta-webhook). Double-check the Google credentials and the sheet’s tab IDs/names. Replace the Telegram and Google connection credentials with your own securely. Use this as a foundation for any Instagram/Facebook-based automations in n8n, and customize as your automation stack evolves! Publish confidently, and let users know this template: Saves time, automates digital content management, and notifies users in real-time.

Amazon Product Scraper with Scrape.do & AI Enrichment > This workflow is a fully automated Amazon product data extraction engine. It reads product URLs from a Google Sheet, uses Scrape.do to reliably fetch each product page’s HTML without getting blocked, and then applies an AI-powered extraction process to capture key product details such as name, price, rating, review count, and description. All structured results are neatly stored back into a Google Sheet for easy access and analysis. This template is designed for consistency and scalability—ideal for marketers, analysts, and e-commerce professionals who need clean product data at scale. 🚀 What does this workflow do? Reads Input URLs:** Pulls a list of Amazon product URLs from a Google Sheet. Scrapes HTML Reliably:* Uses *Scrape.do** to bypass Amazon’s anti-bot measures, ensuring the page HTML is always retrieved successfully. Cleans & Pre-processes HTML:** Strips scripts, styles, and unnecessary markup, isolating only relevant sections like title, price, ratings, and feature bullets. AI-Powered Data Extraction:** A LangChain/OpenRouter GPT-4 node verifies and enriches key fields—product name, price, rating, reviews, and description. Stores Structured Results:** Appends all extracted and verified product data to a results tab in Google Sheets. Batch & Loop Control:** Handles multiple URLs efficiently with Split In Batches to process as many products as you need. 🎯 Who is this for? E-commerce Sellers & Dropshippers:** Track competitor prices, ratings, and key product features automatically. Marketing & SEO Teams:** Collect product descriptions and reviews to optimize campaigns and content. Analysts & Data Teams:** Build accurate product databases without manual copy-paste work. ✨ Benefits High Success Rate:* *Scrape.do** handles proxy rotation and CAPTCHA challenges automatically, outperforming traditional scrapers. AI Validation:** LLM verification ensures data accuracy and fills in gaps when HTML elements vary. Full Automation:** Runs on-demand or on a schedule to keep product datasets fresh. Clean Output:** Results are neatly organized in Google Sheets, ready for reporting or integration with other tools. ⚙️ How it Works Manual or Scheduled Trigger: Start the workflow manually or via a cron schedule. Input Source: Fetch URLs from a Google Sheet (TRACK_SHEET_GID). Scrape with Scrape.do: Retrieve full HTML from each Amazon product page using your SCRAPEDO_TOKEN. Clean & Pre-Extract: Strip irrelevant code and use regex to pre-extract key fields. AI Extraction & Verification: LangChain GPT-4 model refines and validates product name, description, price, rating, and reviews. Save Results: Append enriched product data to the results sheet (RESULTS_SHEET_GID). 📋 n8n Nodes Used Manual Trigger / Schedule Trigger Google Sheets (read & append) Split In Batches HTTP Request (Scrape.do) Code (clean & pre-extract HTML) LangChain LLM (OpenRouter GPT-4) Structured Output Parser 🔑 Prerequisites Active n8n instance. Scrape.do API token** (bypasses Amazon anti-bot measures). Google Sheets** with: TRACK_SHEET_GID: tab containing product URLs. RESULTS_SHEET_GID: tab for results. Google Sheets OAuth2 credentials** shared with your service account. OpenRouter / OpenAI API credentials** for the GPT-4 model. 🛠️ Setup Import the Workflow into your n8n instance. Set Workflow Variables: SCRAPEDO_TOKEN – your Scrape.do API key. WEB_SHEET_ID – Google Sheet ID. TRACK_SHEET_GID – sheet/tab name for input URLs. RESULTS_SHEET_GID – sheet/tab name for results. Configure Credentials for Google Sheets and OpenRouter. Map Columns in the “add results” node to match your Google Sheet (e.g., name, price, rating, reviews, description). Run or Schedule: Start manually or configure a schedule for continuous data extraction. This Amazon Product Scraper delivers fast, reliable, and AI-enriched product data, ensuring your e-commerce analytics, pricing strategies, or market research stay accurate and fully automated.

🔍 AI-Powered Web Research in Google Sheets with Bright Data 📋 Overview Transform any Google Sheets cell into an intelligent web scraper! Type =BRIGHTDATA("cell", "search prompt") and get AI-filtered result from every website in ~20 seconds. What happens automatically: AI optimizes your search query Bright Data scrapes the web (bypasses bot detection) AI analyzes and filters result Returns clean data directly to your cell Completes in <25 seconds Cost: ~$0.02-0.05 per search | Time saved: 3-5 minutes per search 👥 Who's it for Market researchers needing competitive intelligence E-commerce teams tracking prices Sales teams doing lead prospecting SEO specialists gathering content research Real estate agents monitoring listings Anyone tired of manual copy-paste ⚙️ How it works Webhook Call - Google Sheets function sends POST request Data Preparation - Organizes input structure AI Query Optimization - GPT-4.1 Mini refines search query Web Scraping - Bright Data fetches data while bypassing blocks AI Analysis - GPT-4o Mini filters and summarizes result Response - Returns plain text to your cell Logging - Updates logs for monitoring 🛠️ Setup Instructions Time to deploy: 20 minutes Requirements n8n instance with public URL Bright Data account + API key OpenAI API key Google account for Apps Script Part 1: n8n Workflow Setup Import this template into your n8n instance Configure Webhook node: Copy your webhook URL: https://n8n.yourdomain.com/webhook/brightdata-search Set authentication: Header Auth Set API key: 12312346 (or create your own) Add OpenAI credentials to AI nodes. Configure Bright Data: Add API credentials Configure Output Language: Manually edit the "Set Variables" Node. Test workflow with manual execution Activate the workflow Part 2: Google Sheets Function Open Google Sheet → Extensions → Apps Script Paste this code: function BRIGHTDATA(prompt, source) { if (!prompt || prompt === "") { return "❌ Must enter prompt"; } source = source || "google"; // Update with YOUR webhook URL const N8N_WEBHOOK_URL = "https://your-n8n-domain.com/webhook/brightdata-search"; // Update with YOUR password const API_KEY = "12312346"; let spreadsheetId, sheetName, cellAddress; try { const sheet = SpreadsheetApp.getActiveSheet(); const activeCell = sheet.getActiveCell(); spreadsheetId = SpreadsheetApp.getActiveSpreadsheet().getId(); sheetName = sheet.getName(); cellAddress = activeCell.getA1Notation(); } catch (e) { return "❌ Cannot identify cell"; } const payload = { prompt: prompt, source: source.toLowerCase(), context: { spreadsheetId: spreadsheetId, sheetName: sheetName, cellAddress: cellAddress, timestamp: new Date().toISOString() } }; const options = { method: "post", contentType: "application/json", payload: JSON.stringify(payload), muteHttpExceptions: true, headers: { "Accept": "text/plain", "key": API_KEY } }; try { const response = UrlFetchApp.fetch(N8N_WEBHOOK_URL, options); const responseCode = response.getResponseCode(); if (responseCode !== 200) { Logger.log("Error response: " + response.getContentText()); return "❌ Error " + responseCode; } return response.getContentText(); } catch (error) { Logger.log("Exception: " + error.toString()); return "❌ Connection error: " + error.toString(); } } function doGet(e) { return ContentService.createTextOutput(JSON.stringify({ status: "alive", message: "Apps Script is running", timestamp: new Date().toISOString() })).setMimeType(ContentService.MimeType.JSON); } Update N8N_WEBHOOK_URL with your webhook Update API_KEY with your password Save (Ctrl+S / Cmd+S) - Important! Close Apps Script editor 💡 Usage Examples =BRIGHTDATA("C3", "What is the current price of the product?") =BRIGHTDATA("D30", "What is the size of this company?") =BRIGHTDATA("A4", "Do this comapny is hiring Developers?") 🎨 Customization Easy Tweaks AI Models** - Switch to GPT-4o for better optimization Response Format** - Modify prompt for specific outputs Speed** - Optimize AI prompts to reduce time Language** - Change prompts for any language Advanced Options Implement rate limiting Add data validation Create async mode for long queries Add Slack notifications 🚀 Pro Tips Be Specific** - "What is iPhone 15 Pro 256GB US price?" beats "What is iPhone price?" Speed Matters** - Keep prompts concise (30s timeout limit) Monitor Costs** - Track Bright Data usage Debug** - Check workflow logs for errors ⚠️ Important Notes Timeout:** 30-second Google Sheets limit (aim for <20s) Plain Text Only:** No JSON responses Costs:** Monitor Bright Data at console.brightdata.com Security:** Keep API keys secret No Browser Storage:** Don't use localStorage/sessionStorage 🔧 Troubleshooting | Error | Solution | |-------|----------| | "Exceeded maximum execution time" | Optimize AI prompts or use async mode | | "Could not fetch data" | Verify Bright Data credentials | | Empty cell | Check n8n logs for AI parsing issues | | Broken characters | Verify UTF-8 encoding in webhook node | 📚 Resources Bright Data API Docs n8n Webhook Documentation Google Apps Script Reference Built with ❤️ by Elay Guez

This workflow automates reputation management for physical stores (restaurants, retail, clinics) by monitoring Google Maps reviews, analyzing them with AI, and drafting professional replies. It acts as a 24/7 customer support assistant, ensuring you never miss a negative review and saving hours of manual writing time. Who is this for? Store Managers & Owners:** Keep track of customer sentiment without manually checking Google Maps every day. Marketing Agencies:** Automate local SEO reporting and response drafting for multiple clients. Customer Support Teams:** Get instant alerts for negative feedback to resolve issues quickly. How it works Schedule: Runs every 24 hours (customizable) to fetch the latest data. Scrape: Uses Apify to retrieve the latest reviews from a specific Google Maps URL. Filter: Checks the Google Sheet database to identify only new reviews and avoid duplicates. AI Analysis: An AI Agent (via OpenRouter/OpenAI) analyzes the review text to: Generate a short summary. Draft a polite, context-aware reply based on the star rating (e.g., apologies for low stars, gratitude for high stars). Alert: Sends a Slack notification. Low Rating (<4 stars): Alerts a specific channel (e.g., #customer-support) with a warning. High Rating: Alerts a general channel (e.g., #wins) to celebrate. Save: Appends the review details, AI summary, and draft reply to the Google Sheet. Requirements n8n:** Cloud or self-hosted (v1.0+). Apify Account:* To run the *Google Maps Reviews Scraper. Google Cloud Platform:** Enabled Google Sheets API. Slack Workspace:** A webhook URL or OAuth connection. OpenRouter (or OpenAI) API Key:** For the LLM generation. How to set up Google Sheets: Create a new sheet with the following headers in the first row: reviewId, publishedAt, reviewerName, stars, text, ai_summary, ai_reply, reviewUrl, output, publishedAt date. Configure Credentials: Set up your accounts for Google Sheets, Apify, Slack, and OpenRouter within n8n. Edit the "CONFIG" Node: MAPS_URL: Paste the full Google Maps link to your store. SHEET_ID: Paste the ID found in your Google Sheet URL. SHOP_NAME: Your store's name. Slack Nodes: Select the appropriate channels for positive and negative alerts. How to customize Change the AI Persona:* Open the *AI Agent** node and modify the "System Message" to match your brand's tone of voice (e.g., casual, formal, or witty). Adjust Alert Thresholds:* Edit the *If Rating < 4** node to change the criteria for what constitutes a "negative" review (e.g., strictly < 3 stars). Multi-Store Support:** You can loop this workflow over a list of URLs to manage multiple locations in a single execution.

Create TikTok videos grounded in real human insight. One agent researches viral trends, gathers authentic audience feedback on your product to inform script creation, tests script variations with target audiences to identify the most resonant script option, generates the video, and sends it back to you on Telegram. Description Most AI video tools generate content based on assumptions and AI guesswork. That's why content often looks and feels the same. This workflow grounds every creative decision in an authentic human perspective. The process: Research trends — Apify scrapes what's actually viral on TikTok Understand your audience — Digital Twins provide real feedback on your product/concept to inform creative direction Generate informed scripts — The agent writes variations based on actual human insights, not AI assumptions Test for resonance — Digital Twins evaluate which script will genuinely connect with your target audience Produce the winner — Veo 3 generates video from the most resonant script By anchoring both the script development and selection in real human perspectives, you can create TikTok videos that actually resonate with your target audience. Triggers Telegram message** — send your product/concept to your bot to start the workflow Nodes Used Set** (Workflow Configuration) — target audience demographics Telegram Trigger** — starts the workflow with product/concept input AI Agent** — orchestrates the entire research → insight → creation → resonance testing flow OpenAI Chat Model** (GPT-4o) — powers the agent MCP Client Tool** (Apify) — scrapes trending TikTok content MCP Client Tool** (OriginalVoices) — queries Digital Twins for: Initial product/concept feedback to inform scripts Resonance testing to select the most compelling script version Code** (Parse JSON) — extracts structured output from the agent HTTP Request** (Veo 3) — generates 9:16 video via fal.ai Wait** — pauses for video generation HTTP Request** (Poll) — checks video status Telegram** — sends the finished video URL back to you Required Credentials Telegram Bot — create via @BotFather OpenAI API — for GPT-4o Apify API — for TikTok trend scraping (apify.com) OriginalVoices API — for real-time audience insights and feedback (originalvoices.ai) FAL.ai API — for Veo 3 video generation (fal.ai) Configuration Import workflow.json into n8n Edit the Workflow Configuration node: productName — your product/brand name productDescription — what your product does targetAudience — e.g., "US women, 25-40, interested in wellness and productivity" (defines which Digital Twins provide insights and resonance feedback) tone — e.g., "casual, energetic, Gen-Z friendly" Connect Telegram Bot credentials on both Telegram nodes Connect OpenAI API credentials on the Chat Model node Connect Header Auth on Apify MCP node: Header: Authorization, Value: Bearer YOUR_APIFY_TOKEN Connect Header Auth on OriginalVoices node: Header: X-Api-Key, Value: YOUR_API_KEY Connect Header Auth on Veo 3 and Poll Video Status nodes: Header: Authorization, Value: Key YOUR_FAL_API_KEY Activate the workflow Usage Send a message to your Telegram bot describing your product/concept (e.g., "meditation app that uses AI-generated soundscapes") The agent: Researches current TikTok trends Gathers authentic audience feedback on your concept from Digital Twins Writes script variations informed by real human perspectives Tests all scripts with Digital Twins of target audience to identify which one resonates most The most resonant script is sent to Veo 3 for video generation You receive the video URL, audience-informed caption, and hashtags back on Telegram Why this matters: Every creative decision — from initial direction to final script selection — is grounded in how real humans in your target demographic actually think, feel, and respond. Not AI assumptions or guesswork. Real human intelligence that ensures your content actually resonates. Customize: Audience targeting** — refine the targetAudience parameter to query specific Digital Twin demographics Trend niche** — modify the agent prompt to focus on specific hashtags or content types Script count** — adjust the prompt to generate more or fewer variations for testing Video style** — update the Veo 3 prompt for different aesthetics (cinematic, UGC, etc.) Resonance criteria** — specify what makes a script "compelling" for your use case

Pearl Hybrid Intelligence: AI draft + expert verification (across 100+ expert domains) Deliver higher-confidence answers by combining an AI assistant with professional human verification. Pearl provides access to a network of 20,000 licensed experts (including JDs, MDs, PhDs, DVMs, CPAs, engineers) across 100+ domains - Legal and Health are just examples, and the prompts can be tuned for many other areas. What this template does Lets users ask questions in a conversational format (your app sends the conversation history). Collects any missing intake details before answering. Generates a clear draft answer using AI. Sends the draft to a Pearl expert for professional verification. Returns the verified answer back to the user, including who verified it. How it works (non-technical) A user asks a question. If the assistant needs more context, it asks one focused follow-up question. Once the assistant has enough information, it drafts a complete answer. That draft is automatically reviewed by a qualified Pearl expert. The user receives the verified answer, along with expert attribution. Setup steps (10–15 minutes) Connect your OpenAI credential in n8n (used for intake + drafting). Add your Pearl MCP Server API key (used for expert verification). You can request a demo access key here: https://www.pearl.com/enterprise/contact-get-started Activate the workflow and send a test request using the example payload below. Customization The intake and draft answer prompts can be adjusted to match end-user needs (domain, tone, risk policy, compliance requirements). You can also modify the response format (fields returned, disclaimers, attribution formatting) without changing the core flow. Input payload format (conversation history) Send a JSON body like: { "model": "gpt-4o-mini", "messages": [ { "role": "user", "content": "My question..." } ] }

Product Review Analysis with BrowserAct & Gemini-Powered Recommendations. This n8n template demonstrates how to perform product review sentiment analysis and generate improvement recommendations using an AI Agent. This workflow is perfect for e-commerce store owners, product managers, or marketing teams who want to automate the process of collecting feedback and turning it into actionable insights. How it works The workflow is triggered manually. An HTTP Request node initiates a web scraping task with the BrowserAct API to collect product reviews. A series of If and Wait nodes are used to check the status of the scraping task. If the task is not yet complete, the workflow pauses and retries until it receives the full dataset. An AI Agent node, powered by Google Gemini, then processes the scraped review summaries. It analyzes the sentiment of each review and generates actionable improvement recommendations. Finally, the workflow sends these detailed recommendations via a Telegram message and an Email to the relevant stakeholders. Requirements BrowserAct** API account for web scraping BrowserAct* "Product Review Sentiment Analysis*" Template Gemini** account for the AI Agent Telegram* and *SMTP** credentials for sending messages Need Help ? How to Find Your BrowseAct API Key & Workflow ID How to Connect n8n to Browseract How to Use & Customize BrowserAct Templates Workflow Guidance and Showcase How to INSTANTLY Get Product Improvement Ideas from Amazon Reviews | BrowserAct + n8n + Gemini

Build a personal Telegram bot that looks up English vocabulary and saves every entry to Notion — supporting text, voice, and photo input. Send a word by typing, voice message, or photo. The bot auto-detects the input type: voice is transcribed via Whisper, photos are scanned via GPT-4o-mini Vision OCR. A GPT-4.1-mini agent spell-checks and returns the word's definition, translation, part of speech, and an example sentence. The translation language is fully configurable — just set TARGET_LANGUAGE in the Config node (e.g. Traditional Chinese, Japanese, Spanish). Nodes used: Telegram Trigger, HTTP Request (Telegram file API), OpenAI (Whisper + GPT-4o-mini Vision + GPT-4.1-mini), Structured Output Parser, Notion. 💡 Want more AI automation templates? Check out the Content Automation Bundle: 👉 https://jasonchuang0818.gumroad.com/l/n8n-content-automation-bundle