by Cheng Siong Chin
How It Works Automates daily learner engagement monitoring, progress analysis, and personalized feedback delivery for training programs. Target audience: learning and development teams, corporate training managers, and online education platforms scaling instructor workload. Problem solved: manual progress tracking consumes instructor time; AI analysis identifies struggling learners early for intervention. Workflow runs daily checks on learner activity, retrieves course data and progress, analyzes engagement with OpenAI models, evaluates quiz scores, generates performance summaries, sends progress reports to learners, emails instructors on at-risk cases, generates learning paths, and triggers manager notifications. Setup Steps Configure daily schedule trigger. Connect learning management system APIs (LMS). Set OpenAI keys for progress analysis. Enable Gmail for multi-recipient notifications. Map learner risk thresholds and escalation rules. Prerequisites LMS platform credentials, OpenAI API key, learner database, email service for notifications, manager contact lists. Use Cases Corporate onboarding programs tracking employee progress, online learning platforms identifying struggling students Customization Adjust AI analysis criteria for your curriculum. Integrate Slack for instructor alerts. Benefits Reduces instructor workload by 70%, identifies at-risk learners 2 weeks early
by WeblineIndia
AI-Powered Risk Monitor: Negative News Tracker This workflow acts as an automated early-warning system for corporate risk. It pulls a list of companies from a Google Sheet, uses SerpAPI to scout the latest global news and employs Groq-powered AI to detect negative sentiment (such as lawsuits, layoffs or financial declines). New risks are archived in a master database and immediate Gmail alerts are sent for any confirmed negative news, ensuring you never miss a critical market signal. Quick Implementation Steps Import: Upload the JSON file into your n8n workflow editor. Authenticate**: Connect your Google Sheets, SerpAPI, Groq and Gmail credentials. Prepare Watchlist: Create a Google Sheet with a column named **Companies and add the entities you want to monitor. Set Database: Create a second sheet (or tab) with headers: **ID, Company, Title, Date, Reason, Severity, Link. Activate: Click **Start Workflow to run a manual check or add a Schedule Trigger for 24/7 monitoring. What It Does This workflow automates the tedious process of manual "reputation monitoring." It starts by reading a list of target companies from your Watchlist. For every company found, it performs a real-time Google News search via SerpAPI. To handle high volumes of data efficiently, it aggregates all found articles into a single stream, standardizes the formatting and generates a unique digital fingerprint (ID) for every story. The "intelligence" of the workflow lies in its deduplication and AI analysis. It cross-references every new article ID against your Processed News spreadsheet; if an article has been seen before, it is discarded. Only 100% new content reaches the Groq AI engine. The AI then acts as a financial analyst, reading the headline to determine if the news is truly negative and assigning a severity level (Low, Medium or High). Finally, the workflow acts on these insights. If the AI flags an article as negative, the data is appended to your tracking sheet for long-term auditing and a formatted HTML email is sent via Gmail to your team, containing the reasoning, severity and a direct link to the source article. Who It's For Investment Analysts** needing to track portfolio companies for "black swan" events. PR & Communications Teams** monitoring brand reputation and crisis management. Legal & Compliance Officers** tracking litigation or regulatory investigations involving partners. Sales Professionals** looking for "trigger events" (like management changes or losses) to adjust their strategy. Requirements to use this workflow n8n account: (Self-hosted or Cloud). Google Account**: For accessing Watchlists and sending Gmail alerts. SerpAPI Key**: To fetch live Google News results. Groq API Key**: To power the high-speed sentiment analysis. How It Works & Setup Guide 1. Watchlist & Credentials Ensure your Google Sheets account is connected. Your Read Watchlist node should point to a sheet where company names are listed under a header named Companies. 2. Search API Configuration Open the Fetch News node and ensure your SerpAPI key is entered in the query parameters. This node is configured to search Google News (tbm=nws) dynamically based on the company names from your list. 3. Deduplication Logic The Process Articles node uses a JavaScript snippet to create a unique ID based on the title and link. This prevents you from receiving the same alert twice if a news story stays on the front page for multiple days. 4. AI Analysis & Throttling The Analyze News node uses the Groq Chat Model. Because AI APIs can sometimes be overwhelmed by rapid requests, a Throttle API Calls node is included to pause for 2 seconds between articles, ensuring stability. 5. Filtering & Alerting The Filter Negative News node is the gatekeeper. It only allows items where the AI has explicitly set is_negative to true. These items are then saved to your database and emailed to you. How To Customize Nodes Adjust Severity: While the workflow currently alerts on all negative news, you can modify the **Filter Negative News node to only allow severity == 'high' if you only want to see major crises. Refine AI Prompt: Edit the **Analyze News node to add specific keywords relevant to your industry (e.g., "clinical trial failure" for Biotech or "data breach" for Tech). Email Branding: Open the **Send Alert node to change the HTML styling or to add your company logo to the notifications. Add‑ons Slack/Teams Integration**: Add a Slack node alongside Gmail to post risk alerts into a specific "Crisis-Monitor" channel. AI Summary**: Add a second AI step to summarize the full article content if the headline analysis suggests high severity. Automated Scheduling: Replace the Manual Trigger with a **Schedule Trigger to run the tracker every hour or at the start of every business day. Use Case Examples Competitor Intelligence**: Tracking when competitors face lawsuits or product recalls. Vendor Risk Management**: Monitoring key suppliers for signs of financial distress or strikes. E-Commerce Monitoring**: Tracking news about major shipping partners or payment processors. M&A Due Diligence**: Automating the "bad news" search for companies currently under acquisition review. Public Figure Tracking**: Monitoring news for specific high-profile individuals or executives. Troubleshooting Guide | Issue | Possible Cause | Solution | | :--- | :--- | :--- | | No news being fetched | SerpAPI key missing or expired | Check the Fetch News node execution logs for a 401 or 403 error code. | | Duplicate alerts received | Sheet ID column mismatch | Ensure the Lookup Existing Articles node is looking at the correct column (ID) in your Google Sheet. | | AI fails to parse JSON | Prompt deviation | Ensure the Structured Output Parser is connected to the Analyze News node to enforce JSON formatting. | | Workflow is too slow | Throttle settings | If you have a high-tier Groq account, you can reduce the Throttle API Calls timer from 2 seconds to 0.5 seconds. | Need Help? Configuring real-time AI monitors requires a balance of speed and accuracy. If you need help tailoring the deduplication logic, expanding your watchlist or connecting these alerts to a professional CRM like Salesforce or HubSpot, we are here to assist. Contact WeblineIndia to help you build, customize or scale your business automation today!
by Cheng Siong Chin
How It Works This workflow automates athlete performance monitoring through two parallel pipelines: real-time session analysis triggered by training form submissions, and scheduled weekly performance summaries. Designed for sports coaches, athletic trainers, and performance analysts, it eliminates manual data aggregation and ensures threshold breaches and weekly trends are communicated instantly. A training session form submission stores the record to Google Sheets, fetches historical data, and combines both inputs for a Performance Analysis Agent. OpenAI analyses the combined data, updates the sheet with insights, then checks performance thresholds—triggering Slack alerts or email notifications on breach. In parallel, a weekly schedule fetches all athlete data, groups by athlete, and passes to a Weekly Summary Agent that distributes summaries via both Slack and email. Setup Steps Configure Training Session Form fields to match athlete and session data schema. Connect Google Sheets credentials to Store, Fetch, and Update Record nodes. Add OpenAI API credentials to Performance Analysis and Weekly Summary Agent nodes. Configure Slack credentials and set coaching team alert and summary channels. Add Gmail/SMTP credentials to Send Email Alert and Weekly Summary Email nodes. Define performance threshold values in the Check Performance Threshold node. Prerequisites Google Sheets with service account credentials Slack workspace with bot token Gmail or SMTP credentials Use Cases Real-time performance threshold alerts for elite athlete training programmes Customization Replace OpenAI with Anthropic Claude for analysis and summary agents Benefits Automates session analysis and insight storage immediately after each training entry
by DigiMetaLab
How It Works Trigger: The workflow starts automatically when a new file (PDF, DOCX, or TXT) is uploaded to a specific Google Drive folder for client briefs. Configuration: The workflow sets up key variables, such as the folder for storing reports, the account manager’s email, the tracking Google Sheet, and the error notification email. File Type Check & Text Extraction: It checks the file type and extracts the text using the appropriate method for PDF, DOCX, or TXT files. Extraction Validation: If text extraction fails or the file is empty, an error notification is sent to the designated email. AI Analysis: The extracted text is analyzed using Groq AI (Llama 3 model) to summarize the brief, extract client needs, goals, challenges, and more. Industry Research: The workflow performs additional AI-powered research on the client’s industry and project type, using Wikipedia and Google Search tools. Report Generation: The analysis and research are combined into a comprehensive, formatted report. Google Doc Creation: The report is saved as a new Google Doc in a specified folder. Logging: Key details are logged in a Google Sheet for tracking and record-keeping. Notification: The account manager receives an email with highlights and a link to the full report. Error Handling: If any step fails (e.g., text extraction), an error email is sent with troubleshooting advice. Setup Steps Google Drive Folders: Create a folder for incoming client briefs. Create a folder for storing generated client summary reports. Google Sheet: Create a Google Sheet with a sheet/tab named “Brief Analysis Log” for tracking analysis results. Google Cloud Project: Set up a Google Cloud project and enable APIs for Google Drive, Google Docs, Google Sheets, and Gmail. Create OAuth2 credentials for n8n and connect them in your n8n instance. Groq AI Credentials: Obtain API credentials for Groq AI and add them to n8n. SerpAPI (Optional, for Google Search): If using Google Search in research, get a SerpAPI key and add it to n8n. n8n Workflow Configuration: In the “Workflow Configuration” node, set the following variables: clientSummariesFolderId: Google Drive folder ID for reports. accountManagerEmail: Email address to notify. trackingSheetId: Google Sheet ID for logging. errorNotificationEmail: Email for error alerts. Connect All Required Credentials: Make sure all Google and AI nodes have the correct credentials selected in n8n. Test the Workflow: Upload a sample client brief to the monitored Google Drive folder. Check that the workflow runs, generates a report, logs the result, and sends the notification email.
by Unfenced Group
Quick Overview This workflow runs a SEEK.com.au job search via Apify on a daily schedule or on-demand form submission, deduplicates new listings, and routes results to Google Sheets, Airtable, a webhook endpoint, and digest notifications to Slack, Telegram, Discord, and Gmail. How it works Runs daily at 7 AM or starts when you submit the built-in n8n form with your SEEK search parameters. Sends the search criteria to the Apify “unfenced-group/seek-com-au-scraper” actor and retrieves the job results. Normalises each job into consistent fields (including an annualised salary estimate) and removes duplicates within the run and across previous executions. Aggregates all newly found jobs and formats a single digest message for Slack, Telegram, Discord, and email. Sends the digest to the enabled channels (Slack, Telegram, Discord webhook, and/or Gmail) based on the destination values you provided. Splits the new jobs back into individual items and, if enabled, appends/updates rows in Google Sheets, creates records in Airtable, and/or POSTs each job to your webhook URL. If the scraper returns no data and a notify URL is set, POSTs a “seek_no_results” alert to that endpoint. Setup Add an Apify credential with an API token and ensure the workflow can run the “unfenced-group/seek-com-au-scraper” actor. For scheduled runs, edit the “Scheduled Defaults” values (search query, location, days back, max results) and set any destination fields you want to use (leave as YOUR_XXX or blank to skip). If using Google Sheets, add a Google Sheets OAuth2 credential, set your spreadsheet ID and tab name, and ensure there is a URL column for matching updates. If using Airtable, add an Airtable personal access token, set the base/table IDs, and create fields that match the mapped column names (Title, Company, Location, URL, Salary Annual, etc.). If using Slack, Gmail, or Telegram, add the respective OAuth/bot credentials and set the Slack channel name, recipient email address, and Telegram chat ID. If using webhooks (generic webhook, Discord, or failure notifications), paste the target webhook URLs into webhookUrl, discordWebhookUrl, and/or notifyUrl.
by Cheng Siong Chin
How It Works This workflow automates quality event risk assessment through AI-powered multi-agent analysis with mandatory human oversight for critical decisions. Designed for quality managers, compliance officers, and risk analysts in manufacturing, healthcare, or service industries, it solves the challenge of consistent, transparent risk evaluation while maintaining human accountability. When quality events are detected, the system orchestrates specialized AI agents (traceability, risk assessment, and recall evaluation) to analyze different risk dimensions simultaneously. Results are synthesized, routed through human approval gates based on risk severity, and distributed via automated notifications. This ensures high-risk decisions receive proper scrutiny while low-risk events flow efficiently through automated channels. Setup Steps Configure NVIDIA NIM API credentials with Llama-3.1-70B-Instruct model access Set up routing logic thresholds Connect Gmail SMTP for executive alerts and Slack webhook for team notifications Configure human approval nodes with designated approver email addresses Customize AI agent prompts for industry-specific risk criteria Prerequisites NVIDIA NIM API key, Gmail account with app password Use Cases Manufacturing defect escalation, food safety incident management Customization Modify risk scoring thresholds, add industry-specific compliance agents Benefits Reduces risk assessment time by 75%, ensures consistent evaluation methodology
by Yassin Zehar
Description This workflow turns scattered user feedback into a structured product backlog pipeline. It collects feedback from three channels (Telegram bot, Google Form/Sheets, and Gmail), normalizes it, and sends it to an AI model that: Classifies the feedback (bug, feature request, question, etc.) Extracts sentiment and pain level Estimates business impact and implementation effort Generates a short summary Then a custom RICE-style priority score is computed, a Jira ticket is created automatically, a Notion page is generated for documentation, and a monthly product report is sent by email to stakeholders. It helps product & support teams move from “random feedback in multiple tools” to a repeatable, data-driven product intake process with zero manual triage. Context In most teams, feedback is: spread across emails, forms, and chat messages manually copy–pasted into Jira (when someone remembers) hard to prioritize objectively nearly impossible to review at the end of the month This workflow solves that by: Centralizing feedback from Telegram, Google Forms/Sheets, and Gmail Automatically normalizing all inputs into the same JSON structure Using AI to categorize, tag, summarize, and score each request Calculating a RICE-based priority adapted to your tiers (free / pro / enterprise) Creating a Jira issue with all the context and acceptance criteria Generating a Notion page for each feedback+ticket pair Sending a monthly “Product Intelligence Report” by email with insights & recommendations The result: less manual work, better prioritization, and a clear story of what users are asking for. Target Users This template is designed for: Product Managers and Product Owners SaaS teams with multiple feedback channels Support / CS teams that need a structured escalation path Project Managers who want objective, data-driven prioritization Any team that wants “feedback → backlog” automation without building a custom platform Technical Requirements You’ll need: Google Sheets credential Gmail credential Telegram Bot + Chat ID Google Form connected to a Google Sheet Jira credential (Jira Cloud) Notion credential OpenAI/ Anthropic credential for the AI analysis node An existing Jira project where tickets will be created A Notion database or parent page where feedback pages will be stored Workflow Steps The workflow is organized into four main sections: 1) Triggers (Multi-channel Intake) Telegram Trigger – Listens for new messages sent to your bot Google Form / Sheet Trigger – Listens for new form responses / rows Gmail Trigger – Listens for new emails matching your filter (e.g. [Feedback] in subject) All three paths send their payloads into a “Data Normalizer” node that outputs a unified structure: 2) Request Treated and Enriched (AI Analysis) Instant Reply (Telegram only) – Sends a quick “Thanks, we’re analysing your feedback” message User Enrichment – Enriches user tier based on mapping Message a Model (AI) classifies the feedback extracts tags scores sentiment, pain, business impact, effort generates a short summary & acceptance criteria JSON Parse / Merge – Merges AI output back into the original feedback object 3) Priority Calculation & Jira Ticket Creation Priority Calculator applies a RICE-style formula using: pain level business impact implementation effort user tier weight assigns internal priority: P0 / P1 / P2 / P3 maps to Jira priority: Highest / High / Medium / Low Create Jira Issue – Creates a ticket with: summary from AI description including raw feedback, AI analysis, and RICE breakdown labels based on tags priority based on the calculator Post-processing – Prepares a clean payload for notifications & logging IF (Source = Telegram) – Sends a rich Telegram message back to the user with: Jira key + URL category, priority, RICE score, tags, and estimated handling time Append to Google Sheet (Analytics Log) – Logs each feedback with: source, user, category, sentiment, RICE score, priority, Jira key, Jira URL Create Notion Page – Creates a documentation page linking: the feedback the Jira ticket AI analysis acceptance criteria 4) Monthly Reporting (Product Intelligence Report) Monthly Trigger – Runs once a month Query Google Sheet – Fetches all feedback logs for the previous month Aggregate Monthly Stats – Computes: feedback volume breakdown by category / sentiment / source / tier / priority average RICE, pain, and impact top P0/P1 issues and top feature requests Message a Model (AI) – Generates a written “Product Intelligence Report” with: executive summary key insights & trends top pain points strategic recommendations Parse Response: Extracts structured insights + short summary Create Notion Report Page with: metrics, charts-ready tables, insights, and recommendations Append Monthly Log to Google Sheet – Stores high-level stats for historical tracking Send Email with a formatted HTML report to stakeholders with: key metrics top issues recommendations link to the full Notion report Key Features Multi-channel intake: Telegram + Google Forms/Sheets + Gmail AI-powered triage: automatic category, sentiment, tags, and summary RICE-style priority scoring with tier weighting Automatic Jira ticket creation with full context Notion documentation for each feedback and for monthly reports Google Sheets analytics log for exploration and dashboards Monthly “Product Intelligence Report” sent automatically by email Designed to be adaptable: you can plug in your own labels, tiers, and scoring rules Expected Output When the workflow is running, you can expect: A Jira issue created automatically for each relevant feedback A confirmation email A Telegram confirmation message when the feedback comes from Telegram A Google Sheet filled with normalized feedback and scoring data A Notion page per feedback/ticket with AI analysis and acceptance criteria Every month: a Notion “Monthly Product Intelligence Report” page a summary email with key metrics and insights for your stakeholders How it works Trigger – Listens to Telegram / Google Forms / Gmail Normalize – Converts all inputs to a unified feedback format Enrich with AI – Category, sentiment, pain, impact, effort, tags, summary Score – Computes RICE-style priority and maps to Jira priority Create Ticket – Opens a Jira issue + Notion page + logs to Google Sheets Notify – Sends Telegram confirmation (if source is Telegram) Report – Once a month, aggregates everything and sends a Product Intelligence Report Tutorial Video Tutorial video: Watch the Youtube Tutorial video About me I’m Yassin a Project & Product Manager Scaling tech products with data-driven project management. 📬 Feel free to connect with me on Linkedin
by Rahul Joshi
Quick Overview This workflow polls a Google Sheets milestone tracker every 15 minutes, calculates milestone-based invoice amounts, uses OpenAI (gpt-4o-mini) to draft invoice messaging, emails the invoice via Gmail with an approval link, then records approval in Google Sheets and notifies an accounts Slack channel. How it works Runs every 15 minutes and reads milestone rows from a Google Sheets “Milestones” tab. Filters for milestones where % Complete is at or above the Invoice Trigger % and the Invoice Status is Pending. Calculates the billable amount, generates an invoice ID, and asks OpenAI (gpt-4o-mini) to return a JSON invoice narrative, payment terms, email subject, and HTML email body. Builds an approval URL token, generates a styled HTML invoice document, and sends the invoice email to the client via Gmail with an Approve Invoice button. After the email step returns an approval result, updates the milestone status to Sent, appends a record to the Google Sheets “Invoice Log” tab, and stamps the approval timestamp in the Milestones tab. Posts a Slack message to the accounts team with the milestone ID and approval timestamp, and sends a Slack alert if the workflow errors. Setup Add Google Sheets OAuth2 credentials and replace the spreadsheet document ID and sheet tabs for both the “Milestones” and “Invoice Log” operations. Add an OpenAI credential (used with the gpt-4o-mini model) and adjust the prompt/model if you want different invoice wording. Add a Gmail OAuth2 credential and update the recipient address in the Gmail node (CLIENT_EMAIL@example.com) to your client email field or target address. Add Slack OAuth2 credentials and replace both Slack channel IDs (error alerts and accounts notifications) with your workspace channels. Replace YOUR_N8N_WEBHOOK_BASE_URL in the approval URL builder with your live n8n base URL and ensure your Milestones sheet includes the required columns (Milestone ID, Contract ID, Client Name, % Complete, Invoice Trigger %, Contract Value ($), Invoice Status, Currency).
by Avkash Kakdiya
How it works This workflow runs on a schedule to monitor HubSpot deals with upcoming contract expiry dates. It filters deals that are 30, 60, or 90 days away from expiration and processes each one individually. Based on the remaining days, it sends personalized email reminders to contacts via Gmail. It also notifies account managers in Slack and creates follow-up tasks in ClickUp for tracking. Step-by-step Schedule and filter expiring deals** Schedule Trigger – Runs the workflow at defined intervals. Get all deals – Fetches deals and contract expiry data from HubSpot. Filter Deals – Calculates days left and keeps only 30, 60, or 90-day expiries. Process deals and fetch contacts** Loop Over Deals – Iterates through each filtered deal. Fetch Associated Contact With Deal – Retrieves linked contact IDs via API. Get Contact Details – Pulls contact email and basic info from HubSpot. Route and send reminder emails** Switch – Routes deals based on days left (30, 60, 90). 30 day mail – Sends urgent renewal reminder via Gmail. 60 day mail – Sends friendly renewal notification email. 90 day mail – Sends early awareness email. Merge – Combines all email paths into a single output. Notify team and create follow-ups** Nofity Account Manager – Sends Slack alert with deal and contact details. Create Follow-up Task – Creates a ClickUp task for renewal tracking. Why use this? Prevent missed renewals with automated tracking and alerts Improve customer retention through timely communication Reduce manual CRM monitoring and follow-ups Keep teams aligned with Slack notifications and task creation Scale contract management without increasing workload
by Avkash Kakdiya
How it works: This workflow fetches sent campaign data from Brevo on a schedule, calculates key metrics (open rate, click rate, bounce rate), and stores results in Google Sheets. It then filters to a rolling 7-day window, runs an AI analysis to generate an executive summary with performance highlights and recommendations, and delivers a structured HTML report by email to stakeholders. Step-by-step: Data collection Schedule Trigger – Fires the workflow on your chosen day and time. HTTP Request (Brevo) – Fetches sent campaign data via the Brevo API. Transform Data – Calculates open rate, click rate, and bounce rate per campaign. Write to Google Sheets – Appends processed results to the historical database. Data preparation Read from Google Sheets – Retrieves the latest stored campaign records. Filter to 7-day window – Narrows data to the last 7 days for trend analysis. Aggregate Results – Summarises campaign performance across the window. AI analysis AI Summary Engine – Evaluates trends and generates an executive summary. LLM (Groq or alternative) – Provides the AI model for analysis. Format AI Output – Structures the summary for use in the report. Report delivery Build HTML Report – Compiles metrics, highlights, and recommendations into a styled email. Send via Gmail – Delivers the final report to stakeholder recipients. Why use this? Automates the full reporting lifecycle from data pull to inbox delivery. Surfaces top-performing campaigns and list health issues without manual review. Keeps a growing historical database for long-term trend tracking. Easily adjustable reporting window, thresholds, and notification channels. Works with any AI provider — swap Groq for any compatible LLM.
by Cheng Siong Chin
Introduction Automates scholarship tracking by scraping university sites, assessing eligibility via AI, and publishing results to WordPress or Slack. Eliminates manual searches for students, counselors, and education platforms, enabling scalable curation and timely notifications. How it Works Webhook triggers parallel scraping of NUS, NTU, SIT, SUTD → merge data → AI evaluates eligibility → aggregate qualified scholarships → generate summaries → post to WordPress/Slack → send email notifications with appeal options. Setup Steps Configure OpenAI credentials and eligibility prompt template Update HTTP requests with university URLs and selectors Add WordPress site URL and API credentials Create Slack webhook and notification channel Configure Gmail/SMTP for email notifications Workflow Webhook → Scrape 4 Universities (Parallel) → Merge Data → Prepare Context → AI Eligibility Check → Aggregate Results → Generate Summary → Check Status → Publish Slack/Email/WordPress → Handle Appeals Workflow Steps Scraping: Fetch scholarship pages from four universities simultaneously Merge: Combine data into a unified dataset AI Processing: Analyze eligibility criteria, deadlines against student profile Aggregation: Consolidate qualified scholarships with match scores Publishing: Post to WordPress, send Slack/email with results Appeals: Webhook handles rejection appeals with AI review Prerequisites OpenAI API key, WordPress site with REST API, Slack workspace with webhook, Gmail/SMTP credentials, student profile data (GPA, citizenship, major) Use Cases Counselors automating recommendations for 100+ students, financial aid offices aggregating departmental opportunities Customization Add universities (SMU, SUSS, international institutions), include government schemes (MOE, Edusave, Mendaki) Benefits Saves 10+ hours weekly per counselor, monitors 50+ scholarships automatically, provides AI eligibility matching (85%+ accuracy)
by Cheng Siong Chin
Introduction Automates Singapore COE price tracking, predicts trends using AI, and recommends optimal car purchase timing. Scrapes LTA data biweekly, analyzes historical trends, forecasts next 6 bidding rounds, and sends alerts when buying windows appear—saving time and identifying cost-saving opportunities. How it Works Biweekly trigger scrapes LTA COE data → processes historical trends → AI predicts 6-month prices → compares current vs forecast → generates buy/wait recommendations → alerts sent via Gmail or Telegram. Setup Steps Add NVIDIA/OpenAI API credentials in n8n Connect Google Sheets for data storage Authenticate Gmail/Telegram for notifications Schedule trigger for Wednesdays 8PM SGT Configure alert thresholds in conditional nodes Workflow Schedule Trigger → HTTP Request (Scrape LTA) → Data Processing → Google Sheets (Store) → AI Prediction → Analysis Engine → Conditional Logic → Gmail/Telegram Notification Workflow Steps Scraping: Extract COE prices from OneMotoring Processing: Calculate moving averages, volatility, seasonal trends Storage: Save to Google Sheets with timestamps Prediction: AI forecasts next 6 bidding rounds Analysis: Compare current vs predicted prices, generate recommendation Notification: Alerts via email/Telegram Prerequisites NVIDIA/OpenAI API key, Google account (Sheets), Gmail/Telegram for notifications, basic COE category knowledge Use Cases First-time buyers monitoring price dips, fleet managers timing bulk purchases Customization Add economic indicators, integrate car loan calculators, track parallel imported car prices Benefits Saves hours of manual monitoring, captures 10–15% price dips, provides data-driven purchase timing (potential $5K–$15K savings)