HumationHuman + Automation
Back to Catalog

Track Singapore COE prices with AI forecasting & smart buy recommendations via Telegram

Cheng Siong ChinCheng Siong Chin
48 views
2/3/2026
email-processinggmailslack-notificationsopenaiai-categorization
Official Page

Introduction

Automates Singapore COE price tracking with AI forecasts and buy/wait recommendations. Weekly scraping collects LTA data, enriches with economic indicators, predicts 6-month trends, and alerts users via Telegram/email—helping car buyers and fleet managers make data-driven purchase decisions while avoiding manual tracking.

How it Works

Weekly trigger scrapes LTA COE → validates → stores in Google Sheets → calculates indicators → AI forecasts trends → multi-scenario analysis → generates buy/wait signals → sends actionable alerts.

Setup Steps

  1. Add OpenAI/NVIDIA API credentials in n8n
  2. Authenticate Google Sheets and create spreadsheet
  3. Configure Telegram bot or Gmail SMTP
  4. Set weekly trigger (Thursday 9AM SGT post-bidding)
  5. Adjust alert thresholds in conditional nodes

Workflow

Schedule Trigger → Scrape COE → Validate → Store Sheets → Fetch Historical → Calculate Indicators → AI Prediction → Merge Economics → Multi-Scenario Analysis → Compare Conditions → Generate Dashboard → Send Alerts

Workflow Steps

  1. Scraping: Fetch LTA COE results with retry logic
  2. Validation: Check completeness, flag anomalies
  3. Storage: Append timestamped records to Sheets
  4. Enrichment: Calculate moving averages, volatility, seasonality
  5. AI Analysis: Forecast next 6 months with confidence intervals
  6. Decision Engine: Output buy/wait/monitor recommendation
  7. Reporting: Create dashboard and send alerts via Telegram/email

Prerequisites

OpenAI/NVIDIA API key, Google Sheets access, Telegram bot token or Gmail, basic COE category understanding

Use Cases

First-time buyers timing purchases, fleet operators coordinating bulk acquisitions

Customization

Add SMS alerts via Twilio, integrate loan calculators for total cost analysis

Benefits

Saves 5+ hours monthly, captures 10–18% price dips, provides predictive insights (potential $10K–$25K savings)

n8n Workflow: Track Singapore COE Prices with AI Forecasting & Smart Buy Recommendations via Telegram

This n8n workflow automates the process of fetching, analyzing, and forecasting Singapore Certificate of Entitlement (COE) prices. It leverages AI to provide smart buy recommendations and sends daily updates and alerts directly to your Telegram chat.

What it does

This workflow performs the following key steps:

  1. Scheduled Trigger: Runs daily to initiate the data fetching process.
  2. Fetch COE Data: Makes an HTTP request to an external API (likely a data source for Singapore COE prices) to retrieve the latest price information.
  3. Process COE Data: Uses a Code node to parse and structure the fetched COE data, extracting relevant fields.
  4. Store Data in Google Sheets: Appends the processed COE data to a specified Google Sheet for historical tracking.
  5. Store Data in Airtable: Adds the processed COE data to an Airtable base, potentially for further management or display.
  6. AI Forecasting and Recommendation (AI Agent): Utilizes an AI Agent (powered by an OpenRouter Chat Model) to analyze the historical data, forecast future COE prices, and generate smart buy recommendations.
  7. Filter Recommendations: An If node checks if a "Buy" recommendation has been generated by the AI.
  8. Send Telegram Notification (Buy Recommendation): If a "Buy" recommendation is present, it sends a detailed message to a Telegram chat, including the recommendation and relevant COE data.
  9. Send Telegram Notification (Daily Update): Regardless of a buy recommendation, it sends a daily summary of the latest COE prices and the AI's forecast to a Telegram chat.
  10. Email Notification (Buy Recommendation): If a "Buy" recommendation is present, it also sends an email notification with the recommendation details.
  11. No Operation (for non-buy recommendations): A "No Operation" node handles cases where no "Buy" recommendation is made, allowing the workflow to continue without sending redundant notifications.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Google Sheets Account: A Google Sheets spreadsheet to store historical COE data.
  • Airtable Account: An Airtable base to store COE data.
  • Telegram Bot Token: A Telegram bot and its token to send messages.
  • OpenRouter API Key: An API key for OpenRouter to power the AI Chat Model.
  • Email Service: SMTP credentials or another email service configured in n8n for sending email notifications.
  • External COE Data API: Access to an API that provides Singapore COE price data. (The specific URL for this API will need to be configured in the HTTP Request node).

Setup/Usage

  1. Import the workflow: Download the JSON and import it into your n8n instance.
  2. Configure Credentials:
    • Set up your Google Sheets credential.
    • Set up your Airtable credential.
    • Set up your Telegram credential with your bot token.
    • Set up your OpenRouter credential with your API key.
    • Configure your Email (SMTP) credential.
  3. Configure Nodes:
    • HTTP Request (ID: 19): Update the URL to your COE data API endpoint.
    • Google Sheets (ID: 18): Specify your Spreadsheet ID and Sheet Name.
    • Airtable (ID: 2): Specify your Base ID and Table Name.
    • Code (ID: 834): Review and adjust the JavaScript code if your COE data API response structure differs, to correctly extract and format the data.
    • AI Agent (ID: 1119): Ensure the prompt for the AI Agent is tailored to your desired forecasting and recommendation logic.
    • Telegram (ID: 49): Update the Chat ID to your Telegram chat or group ID.
    • Send Email (ID: 11): Configure the recipient email address, subject, and body as needed.
  4. Activate the Workflow: Once all credentials and nodes are configured, activate the workflow. It will run automatically according to the schedule set in the "Schedule Trigger" node.

Related Templates

Moderate your Discord server using chatGPT-5 & Google Sheets (Learning system)

Discord AI Content Moderator with Learning System This n8n template demonstrates how to automatically moderate Discord messages using AI-powered content analysis that learns from your community standards. It continuously monitors your server, intelligently flags problematic content while allowing context-appropriate language, and provides a complete audit trail for all moderation actions. Use cases are many: Try moderating a forex trading community where enthusiasm runs high, protecting a gaming server from toxic behavior while keeping banter alive, or maintaining professional standards in a business Discord without being overly strict! Good to know This workflow uses OpenAI's GPT-5 Mini model which incurs API costs per message analyzed (approximately $0.001-0.003 per moderation check depending on message volume) The workflow runs every minute by default - adjust the Schedule Trigger interval based on your server activity and budget Discord API rate limits apply - the batch processor includes 1.5-second delays between deletions to prevent rate limiting You'll need a Google Sheet to store training examples - a template link is provided in the workflow notes The AI analyzes context and intent, not just keywords - "I cking love this community" won't be deleted, but "you guys are sht" will be Deleted messages cannot be recovered from Discord - the admin notification channel preserves the content for review How it works The Schedule Trigger activates every minute to check for new messages requiring moderation We'll fetch training data from Google Sheets containing labeled examples of messages to delete (with reasons) and messages to keep The workflow retrieves the last 10 messages from your specified Discord channel using the Discord API A preparation node formats both the training examples and recent messages into a structured prompt with unique indices for each message The AI Agent (powered by GPT-5 Mini) analyzes each message against your community standards, considering intent and context rather than just keywords The AI returns a JSON array of message indices that violate guidelines (e.g., [0, 2, 5]) A parsing node extracts these indices, validates them, removes duplicates, and maps them to actual Discord message objects The batch processor loops through each flagged message one at a time to prevent API rate limiting and ensure proper error handling Each message is deleted from Discord using the exact message ID A 1.5-second wait prevents hitting Discord's rate limits between operations Finally, an admin notification is posted to your designated admin channel with the deleted message's author, ID, and original content for audit purposes How to use Replace the Discord Server ID, Moderated Channel ID, and Admin Channel ID in the "Edit Fields" node with your server's specific IDs Create a copy of the provided Google Sheets template with columns: messagecontent, shoulddelete (YES/NO), and reason Connect your Discord OAuth2 credentials (requires bot permissions for reading messages, deleting messages, and posting to channels) Add your OpenAI API key to access GPT-5 Mini Customize the AI Agent's system message to reflect your specific community standards and tone Adjust the message fetch limit (default: 10) based on your server activity - higher limits cost more per run but catch more violations Consider changing the Schedule Trigger from every minute to every 3-5 minutes if you have a smaller community Requirements Discord OAuth2 credentials for bot authentication with message read, delete, and send permissions Google Sheets API connection for accessing the training data knowledge base OpenAI API key for GPT-5 Mini model access A Google Sheet formatted with message examples, deletion labels, and reasoning Discord Server ID, Channel IDs (moderated + admin) which you can get by enabling Developer Mode in Discord Customising this workflow Try building an emoji-based feedback system where admins can react to notifications with ✅ (correct deletion) or ❌ (wrong deletion) to automatically update your training data Add a severity scoring system that issues warnings for minor violations before deleting messages Implement a user strike system that tracks repeat offenders and automatically applies temporary mutes or bans Expand the AI prompt to categorize violations (spam, harassment, profanity, etc.) and route different types to different admin channels Create a weekly digest that summarizes moderation statistics and trending violation types Add support for monitoring multiple channels by duplicating the Discord message fetch nodes with different channel IDs Integrate with a database instead of Google Sheets for faster lookups and more sophisticated training data management If you have questions Feel free to contact me here: elijahmamuri@gmail.com elijahfxtrading@gmail.com

Cj Elijah GarayBy Cj Elijah Garay
98

Track software vulnerability patents with ScrapeGraphAI, Matrix, and Intercom

Software Vulnerability Patent Tracker ⚠️ COMMUNITY TEMPLATE DISCLAIMER: This is a community-contributed template that uses ScrapeGraphAI (a community node). Please ensure you have the ScrapeGraphAI community node installed in your n8n instance before using this template. This workflow automatically tracks newly-published patent filings that mention software-security vulnerabilities, buffer-overflow mitigation techniques, and related technology keywords. Every week it aggregates fresh patent data from USPTO and international patent databases, filters it by relevance, and delivers a concise JSON digest (and optional Intercom notification) to R&D teams and patent attorneys. Pre-conditions/Requirements Prerequisites n8n instance (self-hosted or n8n cloud, v1.7.0+) ScrapeGraphAI community node installed Basic understanding of patent search syntax (for customizing keyword sets) Optional: Intercom account for in-app alerts Required Credentials | Credential | Purpose | |------------|---------| | ScrapeGraphAI API Key | Enables ScrapeGraphAI nodes to fetch and parse patent-office webpages | | Intercom Access Token (optional) | Sends weekly digests directly to an Intercom workspace | Additional Setup Requirements | Setting | Recommended Value | Notes | |---------|-------------------|-------| | Cron schedule | 0 9 1 | Triggers every Monday at 09:00 server time | | Patent keyword matrix | See example CSV below | List of comma-separated keywords per tech focus | Example keyword matrix (upload as keywords.csv or paste into the “Matrix” node): topic,keywords Buffer Overflow,"buffer overflow, stack smashing, stack buffer" Memory Safety,"memory safety, safe memory allocation, pointer sanitization" Code Injection,"SQL injection, command injection, injection prevention" How it works This workflow automatically tracks newly-published patent filings that mention software-security vulnerabilities, buffer-overflow mitigation techniques, and related technology keywords. Every week it aggregates fresh patent data from USPTO and international patent databases, filters it by relevance, and delivers a concise JSON digest (and optional Intercom notification) to R&D teams and patent attorneys. Key Steps: Schedule Trigger: Fires weekly based on the configured cron expression. Matrix (Keyword Loader): Loads the CSV-based technology keyword matrix into memory. Code (Build Search Queries): Dynamically assembles patent-search URLs for each keyword group. ScrapeGraphAI (Fetch Results): Scrapes USPTO, EPO, and WIPO result pages and parses titles, abstracts, publication numbers, and dates. If (Relevance Filter): Removes patents older than 1 year or without vulnerability-related terms in the abstract. Set (Normalize JSON): Formats the remaining records into a uniform JSON schema. Intercom (Notify Team): Sends a summarized digest to your chosen Intercom workspace. (Skip or disable this node if you prefer to consume the raw JSON output instead.) Sticky Notes: Contain inline documentation and customization tips for future editors. Set up steps Setup Time: 10-15 minutes Install Community Node Navigate to “Settings → Community Nodes”, search for ScrapeGraphAI, and click “Install”. Create Credentials Go to “Credentials” → “New Credential” → select ScrapeGraphAI API → paste your API key. (Optional) Add an Intercom credential with a valid access token. Import the Workflow Click “Import” → “Workflow JSON” and paste the template JSON, or drag-and-drop the .json file. Configure Schedule Open the Schedule Trigger node and adjust the cron expression if a different frequency is required. Upload / Edit Keyword Matrix Open the Matrix node, paste your custom CSV, or modify existing topics & keywords. Review Search Logic In the Code (Build Search Queries) node, review the base URLs and adjust patent databases as needed. Define Notification Channel If using Intercom, select your Intercom credential in the Intercom node and choose the target channel. Execute & Activate Click “Execute Workflow” for a trial run. Verify the output. If satisfied, switch the workflow to “Active”. Node Descriptions Core Workflow Nodes: Schedule Trigger – Initiates the workflow on a weekly cron schedule. Matrix – Holds the CSV keyword table and makes each row available as an item. Code (Build Search Queries) – Generates search URLs and attaches meta-data for later nodes. ScrapeGraphAI – Scrapes patent listings and extracts structured fields (title, abstract, pub. date, link). If (Relevance Filter) – Applies date and keyword relevance filters. Set (Normalize JSON) – Maps scraped fields into a clean JSON schema for downstream use. Intercom – Sends formatted patent summaries to an Intercom inbox or channel. Sticky Notes – Provide inline documentation and edit history markers. Data Flow: Schedule Trigger → Matrix → Code → ScrapeGraphAI → If → Set → Intercom Customization Examples Change Data Source to Google Patents javascript // In the Code node const base = 'https://patents.google.com/?q='; items.forEach(item => { item.json.searchUrl = ${base}${encodeURIComponent(item.json.keywords)}&oq=${encodeURIComponent(item.json.keywords)}; }); return items; Send Digest via Slack Instead of Intercom javascript // Replace Intercom node with Slack node { "text": 🚀 New Vulnerability-related Patents (${items.length})\n + items.map(i => • <${i.json.link}|${i.json.title}>).join('\n') } Data Output Format The workflow outputs structured JSON data: json { "topic": "Memory Safety", "keywords": "memory safety, safe memory allocation, pointer sanitization", "title": "Memory protection for compiled binary code", "publicationNumber": "US20240123456A1", "publicationDate": "2024-03-21", "abstract": "Techniques for enforcing memory safety in compiled software...", "link": "https://patents.google.com/patent/US20240123456A1/en", "source": "USPTO" } Troubleshooting Common Issues Empty Result Set – Ensure that the keywords are specific but not overly narrow; test queries manually on USPTO. ScrapeGraphAI Timeouts – Increase the timeout parameter in the ScrapeGraphAI node or reduce concurrent requests. Performance Tips Limit the keyword matrix to <50 rows to keep weekly runs under 2 minutes. Schedule the workflow during off-peak hours to reduce load on patent-office servers. Pro Tips: Combine this workflow with a vector database (e.g., Pinecone) to create a semantic patent knowledge base. Add a “Merge” node to correlate new patents with existing vulnerability CVE entries. Use a second ScrapeGraphAI node to crawl citation trees and identify emerging technology clusters.

vinci-king-01By vinci-king-01
45

Generate verified job offer letters with OpenAI, Gmail and Slack

📄 AI-Powered Verified Job Offer Letter Generator Description Creating job offer letters manually is time-consuming, error-prone, and difficult to scale. This AI-powered workflow automates the entire job offer letter process — from validating candidate emails to generating and delivering professional PDF offer letters. This intelligent workflow eliminates repetitive drafting, reduces human errors, and ensures offer letters are sent only to verified email addresses, helping HR teams move faster while maintaining professionalism and accuracy. --- What This Workflow Does Transforms manual offer letter creation into a seamless, automated HR process: 📝 Capture Candidate & Job Details – Receives candidate name, email, job role, salary, joining date, and company details via webhook or form. 📧 Email Verification – Validates the candidate’s email address before sending any communication to prevent delivery errors. 🧠 AI-Powered Offer Letter Generation – Uses AI to generate a clear, professional, and structured job offer letter. 📄 HTML Offer Letter Formatting – Converts the AI-generated content into a clean and readable HTML layout. 📑 PDF Generation – Automatically converts the offer letter into a professional PDF document. 📧 Offer Letter Delivery – Sends the PDF offer letter directly to the verified candidate email. 🗂️ Document Storage – Saves a copy of the offer letter for internal records and future reference. 🔁 Confirmation Response – Returns a success response confirming completion. --- Key Features 🤖 AI Offer Letter Writing – Generates professional, ready-to-send offer letters automatically. 📧 Email Verification Built-In – Ensures offer letters are only sent to valid email addresses. 📑 PDF Generation – Creates clean, official-looking offer letters. ⚙️ End-to-End Automation – No manual drafting, formatting, or sending required. 📂 Centralized Record Keeping – Keeps copies of all generated offer letters. 🔄 Flexible Triggering – Can be triggered from HR systems, forms, or internal tools. --- Perfect For 🏢 HR & Recruitment Teams – Automate offer letter creation and delivery. 🚀 Startups & Growing Companies – Send professional offer letters without extra admin work. 🏫 Staffing & Hiring Agencies – Generate offer letters quickly for multiple candidates. 💻 Remote & Distributed Teams – Ensure consistent communication across locations. 🧠 Operations Teams – Maintain accurate records and reduce manual errors. --- What You’ll Need Required Integrations 🌐 Webhook Trigger – Receives candidate and job details. 🤖 OpenAI – Generates offer letter content. 📧 VerifyEmail – Validates candidate email addresses. 📄 HTMLCSS to PDF – Converts HTML into PDF offer letters. 📧 Gmail – Sends the offer letter email. ☁️ Google Drive (optional) – Stores generated offer letters. --- Optional Enhancements 🎨 Brand Customization – Add company logo, colors, and formatting to offer letters. 🧾 HR System Integration – Connect with ATS or HR tools for automatic triggering. 🌍 Multilingual Offer Letters – Generate offer letters in different languages. 🔐 Approval Step – Add internal approval before sending offer letters. 📊 Audit Logging – Store offer letter data in Google Sheets or databases. 📎 Additional Attachments – Include policies or onboarding documents with the offer letter. --- Quick Start 1️⃣ Import the workflow template into your n8n workspace 2️⃣ Connect credentials for OpenAI, VerifyEmail, Gmail, and HTMLCSS to PDF 3️⃣ Send test candidate data to the webhook 4️⃣ Review the generated PDF offer letter 5️⃣ Activate the workflow and start sending offer letters automatically --- Customization Options 1️⃣ Offer Letter Tone – Adjust AI prompt for formal or friendly tone. 2️⃣ Company Branding – Customize HTML layout and styling. 3️⃣ Email Content – Modify subject line and email message. 4️⃣ PDF Layout – Adjust spacing, fonts, and structure. 5️⃣ Storage Location – Change where offer letters are saved. 6️⃣ Validation Rules – Extend email or input checks. --- Expected Results ⚡ Faster Hiring Process – Generate offer letters in minutes. 🤖 Consistent Quality – Every offer letter follows a professional format. 📧 Error-Free Delivery – Verified emails reduce failed communication. 🗂️ Organized Records – All offer letters stored automatically. 🏢 Professional Candidate Experience – Clean, official documents every time. --- Workflow Structure Visualization 📝 Candidate & Job Details ↓ 📧 Email Verification ↓ 🧠 AI Offer Letter Generation ↓ 📄 HTML Formatting ↓ 📑 PDF Conversion ↓ 📧 Email Delivery ↓ 🔁 Confirmation Response --- 🚀 Ready to Automate Job Offer Letters? Import this template today and let AI handle offer letter creation, verification, and delivery — so your team can focus on hiring the right talent faster. ✨ ---

Jitesh DugarBy Jitesh Dugar
5