by Fahmi Fahreza
Sign up for Decodo HERE for Discount Automatically scrape, structure, and log forum or news content using Decodo and Google Gemini AI. This workflow extracts key details like titles, URLs, authors, and engagement stats, then appends them to a Google Sheet for tracking and analysis. Whoβs it for? Ideal for data journalists, market researchers, or AI enthusiasts who want to monitor trending topics across specific domains. How it works Trigger: Workflow runs on schedule. Data Setup: Defines forum URLs and geolocation. Scraping: Extracts raw text data using the Decodo API. AI Extraction: Gemini parses and structures the scraped text into clean JSON. Data Storage: Each news item is appended or updated in Google Sheets. Logging: Records scraping results for monitoring and debugging. How to set up Add your Decodo, Google Gemini, and Google Sheets credentials in n8n. Adjust the forum URLs, geolocation, and Google Sheet ID in the Workflow Config node. Set your preferred trigger interval in Schedule Trigger. Activate and monitor from the n8n dashboard.
by Rajeet Nair
Autonomous PostgreSQL Data Quality Monitoring & Remediation Overview This workflow automatically monitors PostgreSQL database data quality and detects structural or statistical anomalies before they impact analytics, pipelines, or applications. Running every 6 hours, it scans database metadata, table statistics, and historical baselines to identify: Schema drift Null value explosions Abnormal data distributions Detected issues are evaluated using a confidence scoring system that considers severity, frequency, and affected data volume. When issues exceed the defined threshold, the workflow generates SQL remediation suggestions, logs the issue to an audit table, and sends alerts to Slack. This automation enables teams to proactively maintain database reliability, detect unexpected schema changes, and quickly respond to data quality problems. How It Works 1. Scheduled Monitoring A Schedule Trigger starts the workflow every 6 hours to run automated database quality checks. 2. Metadata & Statistics Collection The workflow retrieves important metadata from PostgreSQL: Schema metadata** from information_schema.columns Table statistics** from pg_stat_user_tables Historical baselines** from a baseline tracking table These datasets allow the workflow to compare current database conditions against historical norms. 3. Data Quality Detection Engine Three parallel detection checks analyze the database: Schema Drift Detection Identifies new tables or columns Detects removed columns or tables Detects datatype or nullability changes Null Explosion Detection Calculates null percentage per column Flags columns exceeding configured null thresholds Outlier Distribution Detection Compares current column statistics against historical baselines Uses statistical deviation (z-score) to detect abnormal distributions 4. Issue Aggregation & Confidence Scoring All detected issues are aggregated and evaluated using a confidence scoring system based on: Severity of the issue Data volume affected Historical frequency Consistency of detection Only issues above the configured confidence threshold proceed to remediation. 5. SQL Remediation Suggestions For high-confidence issues, the workflow automatically generates SQL investigation or remediation queries, such as: ALTER TABLE fixes NULL cleanup queries Outlier review queries 6. Logging & Alerting Confirmed issues are: Stored in a PostgreSQL audit table Sent as alerts to Slack 7. Baseline Updates Finally, the workflow updates the data quality baseline table, improving anomaly detection accuracy in future runs. Setup Instructions Configure a PostgreSQL credential in n8n. Replace <target schema name> in the SQL queries with your database schema. Create the following tables in PostgreSQL: Audit Table data_quality_audit Stores detected data quality issues and remediation suggestions. Baseline Table data_quality_baselines Stores historical statistics used for anomaly detection. Configure your Slack credential. Replace the placeholder Slack channel ID in the Send Alert to Team node. Optional configuration parameters can be modified in the Workflow Configuration node: confidenceThreshold maxNullPercentage outlierStdDevThreshold auditTableName baselineTableName Use Cases Database Reliability Monitoring Detect unexpected schema changes or structural modifications in production databases. Data Pipeline Validation Identify anomalies in datasets used by ETL pipelines before they propagate errors downstream. Analytics Data Quality Monitoring Prevent reporting inaccuracies caused by missing data or abnormal values. Production Database Observability Provide automated alerts when critical database quality issues occur. Data Governance & Compliance Maintain a historical audit log of database quality issues and remediation actions. Requirements This workflow requires the following services: PostgreSQL Database** Slack Workspace** n8n** Nodes used: Schedule Trigger Set Postgres Code (Python) Aggregate IF Slack Key Features Automated database health monitoring Schema drift detection** Null explosion detection** Statistical anomaly detection** Confidence-based issue filtering Automated SQL remediation suggestions Slack alerting Historical baseline learning system Summary This workflow provides an automated data quality monitoring system for PostgreSQL. It continuously analyzes schema structure, column statistics, and historical baselines to detect anomalies, generate remediation suggestions, and notify teams in real time. By automating database quality checks, teams can identify issues early, reduce debugging time, and maintain reliable data pipelines.
by Gilbert Onyebuchi
This workflow automates the full invoicing and payment process using n8n and Xero. It allows businesses to generate invoices, track payments, send WhatsApp notifications, and keep records synced automatically, without manual follow-ups or repetitive admin work. Itβs designed to plug into your existing tools and scale as your operations grow. How It Works A webhook receives invoice or payment data from your app, form, or system Xero automatically creates or updates the invoice Payments are tracked and verified in real time Clients receive WhatsApp notifications for invoices, reminders, or payments All records are logged in a database and synced to Google Calendar and Google Sheets Automated responses confirm successful actions or errors Everything runs in the background once connected. Setup Connect your Xero account to n8n Set up a database (PostgreSQL via Supabase) for logging invoices and payments Connect Google Calendar for scheduling and tracking Connect Twilio WhatsApp for client notifications Point your system or payment source to the provided webhook URL No complex coding required. I guide you through the setup and ensure everything is tested. Need Help or Customization? If youβd like this workflow customized for your business or want help setting it up properly, feel free to reach out. π Connect with me on LinkedIn: π Click here to connect Iβm happy to walk you through it or adapt it to your specific use case.
by Rahul Joshi
Description Turn incoming Gmail messages into Zendesk tickets and keep a synchronized log in Google Sheets. Uses Gmail as the trigger, creates Zendesk tickets, and appends or updates a central sheet for tracking. Gain a clean, auditable pipeline from inbox to support queue. β¨ What This Template Does Fetches new emails via Gmail Trigger. βοΈ Normalizes Gmail payload for consistent fields. π§Ή Creates a Zendesk ticket from the email content. π« Formats data for Sheets and appends or updates a row. π Executes helper sub-workflows and writes logs for traceability. ππ§Ύ Key Benefits Converts emails to actionable support tickets automatically. β‘ Maintains a single source of truth in Google Sheets. π Reduces manual triage and data entry. π Improves accountability with structured logs. β Features Gmail Trigger for real-time intake. β±οΈ Normalize Gmail Data for consistent fields. 𧩠Create Zendesk Ticket (create: ticket). ποΈ Format Sheet Data for clean columns. 𧱠Log to Google Sheets with appendOrUpdate. π Execute workflow (sub-workflow) steps for modularity. 𧩠Requirements n8n instance (cloud or self-hosted). π οΈ Gmail credentials configured in n8n (with read access to the monitored inbox). βοΈ Zendesk credentials (API token or OAuth) with permission to create tickets. π Google Sheets credentials with access to the target spreadsheet for append/update. π Access to any sub-workflows referenced by the Execute workflow nodes. π Target Audience IT support and helpdesk teams managing email-based requests. π₯οΈ Ops teams needing auditable intake logs. π§Ύ Agencies and service providers converting client emails to tickets. π€ Small teams standardizing email-to-ticket flows. π§βπΌ Step-by-Step Setup Instructions Connect Gmail, Zendesk, and Google Sheets in n8n Credentials. π Set the Gmail Trigger to watch the desired label/inbox. π¨ Map Zendesk fields (description) from normalized Gmail data. π§ Point the Google Sheets node to your spreadsheet and confirm appendOrUpdate mode. π Assign credentials to all nodes, including any Execute workflow steps. π Run once to test end-to-end; then activate the workflow. β
by Reinhard Schmidbauer
Overview This template automatically exports Meta (Facebook) Ads campaign performance into Google Sheets β both daily and for historical backfills. Itβs ideal for performance marketers, agencies, and analytics teams who want a reliable data pipeline from Meta Ads into their reporting stack. What this workflow does Runs a daily cron job to pull yesterdayβs campaign-level performance from the Meta Ads Insights API. Flattens the API response and calculates key KPIs like CPL, CPA, ROAS, CTR, CPC, CPM, frequency and more. Appends one row per campaign per day to a Google Sheet (for dashboards and further analysis). Provides a separate Manual Backfill section to import historical data using a time_range parameter (e.g. last 12β24 months). Use cases Build Looker Studio / Power BI dashboards on top of a clean, daily Meta Ads dataset. Track ROAS, CPL, CPA, CTR, and frequency trends over time. Combine campaign data with CRM or ecommerce data in the same spreadsheet. Quickly backfill past performance when onboarding a new Meta Ads account. How it works Daily Incremental Flow A Schedule Trigger runs every day at 05:00. The Set config node defines ad account, date preset (yesterday), and Google Sheet details. The Meta Insights node calls the Facebook Graph insights edge at level=campaign. The Code node flattens the data and derives CPL, CPA, ROAS, and other KPIs. The Google Sheets node appends the rows to your Meta_Daily_Data sheet. Manual Backfill Flow A Manual Trigger lets you run the flow on demand. The Set backfill config node defines backfillSince and backfillUntil. The Meta Insights (time_range) node fetches performance for that historical range. The same transform logic is applied, and rows are appended to the same sheet. Prerequisites A Meta Business account with: A system user and a long-lived access token with ads_read / read_insights. A Google Sheet with a header row that matches the mapped column names. n8n credentials for: Facebook Graph API Google Sheets OAuth2 Setup steps Import this template into your n8n instance. Open the Set config and Set backfill config nodes: Set your adAccountId (e.g. act_123456789012345). Set your sheetId (Google Sheet ID) and sheet name (e.g. Meta_Daily_Data). Configure your Facebook Graph API and Google Sheets credentials in n8n. (Optional) Run the Manual Backfill section for your desired historical ranges (e.g. per quarter). Enable the workflow so the Daily Incremental section runs automatically. Customization Change level from campaign to adset or ad if you need more granular reporting. Add breakdowns (e.g. publisher_platform, platform_position) to split by platform and placement. Extend the transform code with additional KPIs or dimensions that match your reporting needs. Use a separate sheet for raw data and build dashboards on top of a cleaned or pivoted view. Consulting & support If you need help with: E-Commerce Strategy & Development** (Shopify, Shopware 6, Magento 2, SAP Commerce Cloud, etc.) Growth & Performance Marketing** (Google / Meta / Microsoft Ads, etc.) Data & Analytics Setups** (tracking, dashboards, attribution, gdpr, etc.) please reach out to Serendipity Technologies: π https://www.serendipity.at We can help you turn this workflow into a full analytics stack and reporting system tailored to your business.
by WeblineIndia
Cash Reconciliation Checker with Google Sheets, OpenAI & n8n This workflow automatically compares internal cash balances with custodian or bank balances using Google Sheets, detects mismatches by account_id, calculates balance differences, logs matched records and sends mismatched records through OpenAI for a short explanation before saving them for exception review. It is designed to help teams reduce manual reconciliation work and quickly identify balance issues. Quick Implementation Steps Import the workflow into n8n. Connect your Google Sheets OAuth2 credentials. Point the three Google Sheets nodes to: Internal balances sheet Custodian balances sheet Reconciliation / exception log sheets Ensure both source sheets use the same account_id values. Make sure balance fields are numeric: internal_balance custodian_balance Connect your OpenAI credentials. Adjust the Schedule Trigger frequency if needed. Run the workflow once and verify: matched records are logged mismatched records are analyzed and appended correctly What It Does The Cash Reconciliation Checker automates a common finance operations task: comparing balances between two separate data sources. In this workflow, one Google Sheet holds internal balances, while another holds custodian balances. The workflow fetches both datasets, standardizes the required fields and matches records using the shared account_id. After matching the accounts, the workflow calculates the difference between internal and custodian balances and checks whether the difference exceeds a built-in tolerance. If the balances match, the record is written to a reconciliation log as a successful result. If they do not match, the workflow routes the record into an exception path. For mismatches, the workflow uses OpenAI (gpt-4o-mini) to generate a short possible explanation based on the values in the record. That enriched mismatch record is then prepared and appended to a separate logging sheet for investigation and follow-up. Whoβs It For This workflow is useful for teams and professionals who regularly compare balances across systems, such as: Finance operations teams Fund administration teams Treasury teams Accounting teams Reconciliation analysts Back-office operations teams Internal controls and audit support teams It is especially useful for organizations that currently reconcile balances manually in spreadsheets and want a faster, more consistent process. Requirements to Use This Workflow Before using this workflow, make sure you have the following: Required Platforms & Accounts n8n account** Google Sheets** OpenAI API access** Required n8n Credentials You will need to configure: Google Sheets OAuth2 credentials** OpenAI credentials** Required Google Sheets Structure This workflow expects the following source data structure based on the JSON: 1) Internal Balance Sheet Must contain at least: account_id currency internal_balance 2) Custodian Balance Sheet Must contain at least: account_id currency custodian_balance 3) Reconciliation Log Sheet Should support these columns: account_id currency internal_balance custodian_balance difference abs_difference mismatch checked_at recon_status 4) Exception / Alert Sheet Should support these columns: account_id currency internal_balance custodian_balance difference abs_difference mismatch checked_at ai_explanation recon_status Data Expectations To avoid processing issues: account_id should be consistent across both source sheets Balance fields should contain numeric values only currency should be present where relevant Empty or invalid balance values may be flagged as mismatches How It Works & Set Up Step 1 β Import the Workflow into n8n Import the provided JSON file into your n8n workspace. After import, you will see the workflow named: Cash Reconciliation Checker Step 2 β Review the Flow The workflow follows this sequence: Schedule Trigger β Fetch Internal Balances β Fetch Custodian Balances β Edit Internal Fields / Edit Custodian Fields β Match Accounts by Account ID β Calculate Balance Difference β Check for Balance Mismatch βββ Matched β Log Matched Records βββ Mismatched β Generate AI Mismatch Explanation β Prepare Exception Record β Append The Data In The Sheet Step 3 β Configure the Schedule Trigger Node: Run Reconciliation on Schedule This node starts the workflow automatically using a schedule interval. What to do: Open the node Set your preferred execution frequency Example options: Every 15 minutes Hourly Daily End-of-day reconciliation schedule Use a timing pattern that fits your reconciliation process. Step 4 β Connect the Internal Balance Source Node: Fetch Internal Balances This Google Sheets node pulls records from the internal balance sheet. What to do: Connect your Google Sheets OAuth2 account Select the correct spreadsheet Select the correct sheet tab Required fields expected from this source: account_id currency internal_balance Step 5 β Connect the Custodian Balance Source Node: Fetch Custodian Balances This Google Sheets node pulls records from the custodian or bank balance sheet. What to do: Connect your Google Sheets OAuth2 account Select the correct spreadsheet Select the correct sheet tab Required fields expected from this source: account_id currency custodian_balance Step 6 β Standardize Both Datasets The workflow uses two Set nodes to clean and normalize fields before matching. Node: Edit Internal Fields This node maps and formats: account_id currency internal_balance It also converts internal_balance into a numeric value. Node: Edit Custodian Fields This node maps and formats: account_id currency custodian_balance It also converts custodian_balance into a numeric value. Why this matters This step helps ensure both datasets use a consistent field structure before comparison. Step 7 β Match Records by Account ID Node: Match Accounts by Account ID This Merge node combines both sources using: account_id What it does It aligns internal and custodian records so each account can be compared side by side. Important setup note This will only work properly if: both sheets contain matching account_id values the values are formatted consistently there are no accidental extra spaces or mismatched IDs Step 8 β Calculate the Balance Difference Node: Calculate Balance Difference This Code node performs the main reconciliation logic. What it calculates For each matched account, it creates: internal_balance custodian_balance difference abs_difference mismatch checked_at Logic used in this node The workflow uses a built-in tolerance: const TOLERANCE = 0.01; Reconciliation rule A record is treated as a mismatch if: either balance is invalid / not numeric, or the absolute difference is greater than 0.01 Output fields created account_id currency internal_balance custodian_balance difference abs_difference mismatch checked_at This is the core decision-making step in the workflow. Step 9 β Route Matched vs Mismatched Records Node: Check for Balance Mismatch This IF node checks: mismatch == true Routing behavior If mismatch = false The record is considered matched and goes to: Log Matched Records If mismatch = true The record is treated as an exception and goes to: Generate AI Mismatch Explanation This split keeps normal reconciliations separate from exception handling. Step 10 β Log Matched Records Node: Log Matched Records This Google Sheets node appends matched records to a reconciliation log sheet. Logged values include: account_id currency internal_balance custodian_balance difference abs_difference mismatch checked_at recon_status Fixed value used Matched records are saved with: recon_status = Matched This gives you a clean audit trail of successfully reconciled accounts. Step 11 β Generate AI Explanation for Exceptions Node: Generate AI Mismatch Explanation This node sends mismatch data to OpenAI (gpt-4o-mini) and asks for a short explanation. Prompt behavior in the workflow The AI is instructed to review: account ID currency internal balance custodian balance difference check timestamp It is then asked to provide the most likely cause of the mismatch from the following categories already defined in the workflow: settlement delay (T+1/T+2) pending fees or accrued interest FX conversion timing failed corporate actions bank charges not yet booked data entry error It also ends with: top 1β2 likely causes one recommended next action Why this is useful This adds context to exceptions and helps operations teams review mismatches faster. Step 12 β Prepare the Exception Record Node: Prepare Exception Record This Code node combines the AI output with the original mismatch data and formats it for logging. Fields included in the final exception record account_id currency internal_balance custodian_balance difference abs_difference mismatch checked_at ai_explanation recon_status Fixed value used Mismatch records are saved with: recon_status = Mismatch This creates a structured exception record ready for reporting or review. Step 13 β Append Mismatch Records to the Exception Sheet Node: Append The Data In The Sheet This Google Sheets node appends the prepared mismatch records into a separate sheet for follow-up. Logged values include: account_id currency internal_balance custodian_balance difference abs_difference mismatch checked_at ai_explanation recon_status This acts as your exception register for unresolved or suspicious balance breaks. Step 14 β Test Before Going Live Before enabling the workflow, run a few controlled tests. Recommended test scenarios Test 1 β Perfect match Use the same values in both sheets for one account. Expected result: record goes to Log Matched Records Test 2 β Small tolerance-safe difference Use a difference within 0.01. Expected result: record should still be treated as matched Test 3 β True mismatch Use a larger difference. Expected result: record goes through AI explanation path gets appended to exception sheet Test 4 β Invalid numeric value Use a blank or non-numeric balance. Expected result: record should be flagged as mismatch Once tests pass, you can safely activate the workflow. How To Customize Nodes This workflow is already useful as-is, but it can be adapted for different reconciliation processes. 1) Customize the Schedule Trigger Node: Run Reconciliation on Schedule You can change: frequency execution window time of day reconciliation cycle Useful if you want: intraday reconciliation end-of-day checks batch finance controls 2) Change Matching Logic Node: Match Accounts by Account ID Currently matches on: account_id You can modify your data model and workflow if you want to include additional matching dimensions such as: account + currency account + region account + entity Only do this if your sheet structure supports it. 3) Adjust the Tolerance Threshold Node: Calculate Balance Difference Current tolerance: const TOLERANCE = 0.01; You can change this if your business allows different variance thresholds. Example customizations 0 β exact reconciliation only 0.01 β cent-level tolerance 1 β whole-unit tolerance custom threshold based on asset class or currency 4) Expand the AI Explanation Logic Node: Generate AI Mismatch Explanation You can customize the prompt to include: business rules escalation notes internal SOP references suggested ownership routing severity classification This is helpful if you want the AI output to be more operationally specific. 5) Add More Fields to Logging Nodes: Log Matched Records Append The Data In The Sheet You can extend the output to include additional columns such as: legal entity desk custodian name region portfolio ID reviewer status resolution notes Only add fields that exist in your upstream data or are intentionally created in the workflow. 6) Improve Exception Classification Node: Prepare Exception Record You can enhance this node to add labels like: low severity medium severity high severity requires same-day review possible FX issue possible operational break This can help organize exception handling more efficiently. Add-ons This workflow can be extended with additional automation features depending on your operational needs. 1) Slack Alerts for Mismatches Send a real-time alert whenever a mismatch is detected. Useful for: finance ops teams treasury teams urgent exception monitoring 2) Email Notification Summary Send a daily or hourly summary of all mismatches to stakeholders. Useful for: finance managers controllers operations leads 3) Severity Scoring Add logic to classify mismatches by size or business impact. Useful for: prioritization faster review queues escalation workflows 4) Auto-Assignment to Reviewers Automatically assign mismatch cases to specific team members based on: currency entity account range custodian Useful for structured exception management. 5) Dashboard Reporting Push matched and mismatched records into a reporting dashboard. Useful for: reconciliation KPIs trend monitoring operational oversight 6) Multi-Currency or Multi-Entity Expansion Extend the workflow to support more entities, accounts or balance sources. Useful for: growing operations teams fund administrators larger finance environments Use Case Examples Below are some of the main ways this workflow can be used. There can absolutely be many more use cases depending on how your reconciliation process is structured. 1) Daily Internal vs Custodian Cash Reconciliation Automatically compare daily internal records against custodian balances and flag any balance breaks for investigation. 2) End-of-Day Treasury Balance Checks Run the workflow at the end of each business day to ensure treasury balances match external sources before close. 3) Exception Monitoring for Fund Operations Identify mismatched fund cash balances and create a structured exception sheet with AI-generated review notes. 4) Reconciliation Logging for Audit Trail Maintain a consistent log of matched and mismatched records for reporting, controls and audit readiness. 5) Early Warning for Data Quality Issues Use mismatches to spot operational problems such as missing values, incorrect balances or inconsistent source data. 6) Lightweight Finance Automation for Spreadsheet-Based Teams Support teams that still work mainly in spreadsheets but want to reduce repetitive reconciliation effort using automation. Troubleshooting Guide | Issue | Possible Cause | Solution | |---|---|---| | No records are being compared | One or both Google Sheets nodes are not returning data | Check that both source sheets contain rows and the correct sheet tabs are selected | | Records are not matching correctly | account_id values differ between the two source sheets | Make sure account_id values are identical and formatted consistently in both sheets | | All rows are being flagged as mismatches | Balance fields contain text, blanks or invalid values | Ensure internal_balance and custodian_balance contain numeric values only | | Small rounding differences are creating mismatches | Tolerance is too strict for your use case | Update the tolerance value in Calculate Balance Difference | | Matched records are not being logged | Google Sheets append node is not configured correctly | Verify the target spreadsheet, sheet tab and credentials in Log Matched Records | | Mismatch records are not being saved | Exception logging sheet is missing expected columns | Confirm the target sheet includes all mapped fields, including ai_explanation and recon_status | | AI explanation is blank | OpenAI credentials or model configuration issue | Reconnect your OpenAI credentials and verify the model is available | | Workflow fails after import | Credentials are not connected in your environment | Reassign all credential-dependent nodes after importing the workflow | | Workflow does not run automatically | Schedule Trigger is not active or workflow is disabled | Activate the workflow and confirm the schedule settings | | Numeric values look wrong in output | Source sheet values are stored with symbols or formatting | Remove currency symbols, commas or text formatting from balance columns | Need Help? If you want help setting up, customizing or extending this workflow, our n8n workflow automation team at WeblineIndia can help you move faster. We can help you with: n8n workflow setup and deployment Google Sheets and finance operations automations OpenAI-powered exception handling Slack / email alert integrations dashboard and reporting extensions custom reconciliation logic production-grade workflow improvements
by Hiroshi Hashimoto
AI Palm Health Tracker β Overview This workflow receives palm images sent via LINE and provides AI-generated health insights. Step-by-step process: 1.User sends a palm image via LINE 2.Webhook receives the image 3.Image is saved to Google Drive 4.Past records are checked in Google Sheets If this is the first submission: β AI will perform a palm reading If previous records exist: β Retrieve the latest saved image β Validate that two images are available β AI performs a comparison analysis All results are saved in Google Sheets and sent back to the user via LINE.
by Abdul Matheen
Description: This workflow automates the entire student exam evaluation process using AI and Google Workspace tools β no manual correction needed! Teachers simply submit a form with their name and a scanned copy of a studentβs answer sheet. The flow then: Uses Gemini Document Analysis to extract answers from the scanned sheet. Passes the extracted answers to an AI Evaluation Agent, equipped with the Question Paper and Correct Answer Sheet (connected via Google Docs tools). The AI cross-checks each student answer, counts correct and incorrect responses, and calculates the total marks. The results are recorded in two Google Sheets: A Summary Sheet with overall student performance (Name, Teacher, Total Marks, etc.) A Detailed Report Sheet logging each question, correct answer, studentβs answer, and correctness status. This workflow turns the tedious task of exam evaluation into a seamless AI-driven automation β ensuring speed, accuracy, and transparency in academic grading. Highlights: β AI Document Understanding (Gemini Model) β Intelligent Answer Comparison β Automated Mark Calculation β Real-Time Google Sheets Update β No Code β Fully Built in n8n
by satoshi
Monitor employee stress levels from Slack and tasks to Google Sheets This workflow functions as an automated "Chief Wellness Officer," helping HR teams and managers prevent employee burnout before it happens. It aggregates data from communication channels and work tools to provide an AI-driven daily assessment of employee well-being, while prioritizing privacy through data anonymization. Who is this for HR & People Operations Teams** wanting to track organizational health trends without invading personal privacy. Remote-first Companies** where physical cues of burnout are harder to spot. Team Managers** looking for data-backed insights to support their direct reports. What it does Daily Trigger: Runs automatically every morning (default: 2 AM) to analyze the previous day's activity. Data Collection: Fetches public Slack messages to analyze communication tone. Retrieves attendance data (work hours, late arrivals) and task completion rates via API. AI Analysis: Uses OpenAI to process the data, predicting a "Stress Level" based on sentiment and workload metrics. Privacy-First Reporting: Hashes employee IDs to anonymize data, then logs stress scores to Google Sheets for trend analysis. Direct Intervention: If the AI detects "High" stress, it sends a private, empathetic DM to the employee on Slack offering support or counseling resources. Requirements n8n** (Self-hosted or Cloud) Slack** Workspace (with a Bot User OAuth Token). OpenAI** API Key. Google Sheets** (for the dashboard). Postgres** (optional, for logging counseling actions). HR/Task Management Tools** (e.g., Jira, Asana, BambooHR) accessible via API. How to set up Configure Credentials: Set up your credentials for Slack, OpenAI, Google Sheets, and Postgres in n8n. Prepare Google Sheet: Create a sheet with headers: employee_hash, department, stress_score, stress_level, and analysis_date. Connect Data Sources: The workflow uses HTTP Request nodes as placeholders for Attendance and Task data. You must update these URLs to point to your specific HRIS or Project Management tool APIs (or replace them with native n8n nodes like Asana or Jira). Update Slack Settings: Ensure the Slack node has the correct permissions (channels:history, chat:write, users:read) and target channel/user mapping. How to customize Adjust Sensitivity:* Modify the system prompt in the *AI Stress Level Prediction node to change how "High" stress is defined. Change Data Sources:* Replace the generic HTTP Request nodes with specific n8n nodes for services like *Harvest, **Jira, or Trello depending on your stack. Modify Action:** Instead of a direct DM, you can change the final step to alert a manager or create a ticket in a sensitive HR service desk.
by Jitesh Dugar
Verified User Profile Creation - Automated Email Validation & PDF Generation Overview This comprehensive automation workflow streamlines the user onboarding process by validating email addresses, generating professional profile PDFs, and delivering them seamlessly to verified users. π― What This Workflow Does: Receives User Data - Webhook trigger accepts user signup information (name, email, city, profession, bio) Validates Email Addresses - Uses VerifiEmail API to ensure only legitimate email addresses proceed Conditional Branching - Smart logic splits workflow based on email verification results Generates HTML Profile - Creates beautifully styled HTML templates with user information Converts to PDF - Transforms HTML into professional, downloadable PDF documents Email Delivery - Sends personalized welcome emails with PDF attachments to verified users Data Logging - Records all verified users in Google Sheets for analytics and tracking Rejection Handling - Notifies users with invalid emails and provides guidance β¨ Key Features: β Email Verification - Prevents fake registrations and maintains data quality π Professional PDF Generation - Beautiful, branded profile documents π§ Automated Email Delivery - Personalized welcome messages with attachments π Google Sheets Logging - Complete audit trail of all verified users π Smart Branching - Separate paths for valid and invalid emails π¨ Modern Design - Clean, responsive HTML/CSS templates π Secure Webhook - POST endpoint for seamless form integration π― Perfect Use Cases: User registration systems Community membership verification Professional certification programs Event registration with verified attendees Customer onboarding processes Newsletter signup verification Educational platform enrollments Membership card generation π¦ What's Included: Complete workflow with 12 informative sticky notes Pre-configured webhook endpoint Email verification integration PDF generation setup Gmail sending configuration Google Sheets logging Error handling guidelines Rejection email template π οΈ Required Integrations: VerifiEmail - For email validation (https://verifi.email) HTMLcsstoPDF - For PDF generation (https://htmlcsstopdf.com) Gmail OAuth2 - For email delivery Google Sheets OAuth2 - For data logging β‘ Quick Setup Time: 15-20 minutes π Skill Level: Beginner to Intermediate Benefits: β Reduces manual verification work by 100% β Prevents spam and fake registrations β Delivers professional branded documents automatically β Maintains complete audit trail β Scales effortlessly with user growth β Provides excellent user experience β Easy integration with any form or application Technical Details: Trigger Type:** Webhook (POST) Total Nodes:** 11 (including 12 documentation sticky notes) Execution Time:** ~3-5 seconds per user API Calls:** 3 external (VerifiEmail, HTMLcsstoPDF, Google Sheets) Email Format:** HTML with binary PDF attachment Data Storage:** Google Sheets (optional) License: MIT (Free to use and modify) π BONUS FEATURES: Comprehensive sticky notes explaining each step Beautiful, mobile-responsive email template Professional PDF styling with modern design Easily customizable for your branding Ready-to-use webhook endpoint Error handling guidelines included Perfect for: Developers, No-code enthusiasts, Business owners, SaaS platforms, Community managers, Event organizers Start automating your user verification process today! π
by AFK Crypto
Try It Out! The SOL/USDT Multi-Timeframe AI Market Analyzer and Trader with Telegram Approval is your fully automated Solana trading assistant powered by AI, AFK Crypto, and Telegram. It runs hourly by default, fetches real-time market data for the SOL/USDT pair, and uses AI-driven logic to determine optimal entry, exit, and risk management strategies. You receive a Telegram approval message that lets you confirm or reject the trade instantly. Once approved, the bot executes trades via your AFK Crypto Wallet and keeps monitoring for Take-Profit or Stop-Loss triggers β sending alerts directly to Telegram when theyβre hit. This system combines automation with manual oversight, giving you AI precision with human approval control. How It Works Hourly Trigger β The workflow initiates every hour to analyze the current market status. Fetch SOL Market Data (Crypto Compare) β Retrieves multiple timeframe data (1m, 5m, 1h) for trend, momentum, and volatility analysis. AI Market Analyzer β Processes data through an AI agent to identify: Market sentiment (bullish, bearish, neutral) Recommended position: LONG / SHORT / HOLD Stop-Loss and Take-Profit levels Confidence rating and reasoning Balance Check (AFK Crypto) β Verifies wallet balance via /v1/wallets/balances?chain=solana and calculates position size based on 1% risk. Telegram Approval Message β Sends a Telegram message containing AI insights and trade details with ββ Approveβ or ββ Declineβ buttons. Trade Execution (AFK Trade API) β If approved, executes trade instantly via /v1/trade/swap using your AFK Crypto wallet. Live Trade Monitoring β Monitors SOL price in real-time. Once Take-Profit or Stop-Loss conditions are met: The position auto-closes. A Telegram notification is sent summarizing results and updated balance. How to Use Import the workflow into your n8n workspace. Add your credentials: AFK Crypto API Key β For balance and trading operations. Telegram Bot Token + Chat ID β For sending messages and approvals. Crypto Compare API Key β For fetching market data. Edit βFetch SOL Market Dataβ Node: Update the endpoint if you want different timeframes or markets. Set the schedule: Default trigger = every hour (modifiable in the βEvery Hourβ node). Deploy and activate. The bot will send you hourly market analyses via Telegram β allowing you to approve or skip each suggested trade. (Optional) Extend This Workflow Auto Mode:** Allow the AI to auto-trade when confidence > 90%. Portfolio Sync:** Log every trade and PnL automatically to Notion or Airtable. Risk Adjuster:** Dynamically modify the 1% risk per trade based on balance or volatility. Multi-Pair Trading:** Expand to include ETH/USDT or BTC/USDT using the same logic. Requirements AFK Crypto Wallet + API Key** Telegram Bot Token + Chat ID** Crypto Compare API Key** n8n Instance** with HTTP Request, AI, and Telegram nodes enabled AFK APIs Used GET https://api.afkcrypto.com/v1/wallets/balances?chain=solana POST https://api.afkcrypto.com/v1/trade/swap Summary The SOL/USDT Multi-Timeframe AI Market Analyzer and Trader with Telegram Approval workflow is an intelligent trading automation system that merges AI analytics, Telegram decision prompts, and AFK Crypto execution. It empowers you to make data-driven trading decisions β with AI doing the heavy lifting and you retaining the final say before every trade. A perfect hybrid between automation and control, optimized for active Solana traders who value precision and security. Our Website: https://afkcrypto.com/ Check our blogs: https://www.afkcrypto.com/blog
by Raghvendra dixit
Description This workflow intelligently scans your inbox, detects whether an email is marketing or genuine, and takes the right action automatically. Marketing Emails : Deleted instantly and logged in Google Sheets for tracking. Non-Marketing Emails : Receive a customized, polite reply crafted using AI. Tracking : Every action (delete/reply) is recorded for auditing and reference. Accounts & Tools n8n instance (self-hosted or cloud). Google account with: Gmail API access (for reading, deleting, and replying). Google Sheets API access (for logging deleted/replied emails). IMP/SMTP credentials (if using IMAP trigger instead of Gmail API). Google Gemini (PaLM) API key to classify emails and generate replies. Setup instructions Create a n8N account on cloud or install it locally. follow the quick start guide this Define your trigger point for your workflow as how or when this needs to run. Currently IMAP has been used to detect if any email is received and if so, trigger the workflow Now, we need to setup the google account which allows our workflow to read emails. Follow this guideline to setup gmail account Next step is to add an AI tool which is google gemini here. To set up and use, see this guideline Since AI response is in text, we need a parser tool to read a specific value from text Setup a categorization tool like this Next is to send or delete email and for this, an existing gmail setup is going to work In the last, we need to set a connection for sheet to keep the logs. Adding any sheet to workflow can be seen as google sheet integration How it work Once any emails is received, IMAP detects and starts the workflow. Now, email is passed to AI model to see if this email is a marketing email or not. Also, is its not a marketing email, it generates a tailored response. Currently, sender, subject and body of email is being scanned and marked as marketing based on model's feedback. Since AI response is in text format, using a formattor to parse it Next step is to read its category as if it is a marketing email Based on email type, there are 2 steps: delete email if it is a marketing email Read the response from previos node and send that as reply Last step is track this activity as which emails is deleted or replied. In terms of structure of sheet, it has 2 tabs deleted emails & replied emails and both have 2 columns Email ID subject Future Use it to categories emails for wider range like job applications, bills, customer supprt and tailor replies for each categories seperately Logging can done in wider sources like databases etc In case if we are logging on sheet, a further enhancements like follow up emails etc can be done