Workflow Templates

Coinbase AI Agent instantly fetches real-time market data directly in Telegram! This workflow integrates the Coinbase REST API with Telegram (plus optional AI-powered formatting) to deliver the latest crypto price, order book, candles, and trade stats in seconds. Perfect for crypto traders, analysts, and investors who want actionable market data at their fingertips—without API keys. How It Works A Telegram bot listens for user requests (e.g., BTC-USD). The workflow calls Coinbase public endpoints (no key required) to fetch real-time data: Latest price (ticker) 24h stats (open, high, low, close, volume) Order book snapshots (best bid/ask + depth) Candlestick data (OHLCV for multiple intervals) Recent trades (executed orders) A Calculator node derives useful values like mid-price and spread. An AI or “Think” node reshapes JSON into clear, human-readable messages. A splitter ensures long messages are broken into safe Telegram chunks. The final market insights are sent instantly back to Telegram. What You Can Do with This Agent This Telegram bot gives you: ✅ Get instant price & 24h stats for any Coinbase spot pair. ✅ Monitor live order books with top bids/asks. ✅ Analyze candle data (e.g., 15m, 1h, 4h, 1d). ✅ Track recent trades to see market activity. ✅ Receive clean, structured reports—optionally AI-enhanced. Set Up Steps Create a Telegram Bot Use @BotFather on Telegram to create your bot and get an API token. Configure in n8n Import the provided workflow JSON. Add your Telegram credentials (bot token + your Telegram ID for authentication). (Optional) Add an OpenAI key if you want AI-enhanced formatting. Deploy and Test Send a query like BTC-USD to your bot. Instantly receive Coinbase spot data in Telegram! 🚀 Unlock powerful, real-time Coinbase market insights directly in Telegram—no Coinbase API key required! 📺 Setup Video Tutorial Watch the full setup guide on YouTube: 🧾 Licensing & Attribution © 2025 Treasurium Capital Limited Company Architecture, prompts, and trade report structure are IP-protected. No unauthorized rebranding or resale permitted. 🔗 For support: LinkedIn – Don Jayamaha

🪄 Prompt To Video (MagicHour API) with Music & YouTube Automate AI video creation, background music, YouTube uploads, and result logging — all from a single text prompt. ⚡ Overview This n8n template turns a text prompt into a complete AI-generated video using the MagicHour API, adds background music, generates YouTube metadata, uploads to YouTube, and logs results in Google Sheets — all in one flow. Perfect for creators, marketers, and startups producing YouTube content at scale — from daily AI Shorts to explainers or marketing clips. 🧩 Use Cases 🎥 Daily AI-generated Shorts 🧠 Product explainers 🚀 Marketing & brand automation 🔁 Repurpose blog posts into videos 💡 AI storytelling or creative projects ⚙️ How It Works Trigger when a new row is added to Google Sheets or via Chat input. Gemini parses and normalizes the text prompt. MagicHour API generates the AI video. Poll until the render completes. (Optional) Mix background audio using MediaFX. Gemini generates YouTube title, description, and tags. Upload the video to YouTube with metadata. Log YouTube URL, metadata, and download link back to Google Sheets. 🧰 Requirements Service Purpose MagicHour API Key Text-to-video generation Gemini API Key Prompt parsing & metadata YouTube OAuth2 Video uploads Google Sheets OAuth2 Trigger & logging (Optional) MediaFX Node Audio mixing 🗂️ Google Sheets Setup Column Description Prompt Text prompt for video Background Music URL (Optional) Royalty-free track Status Tracks flow progress YouTube URL Auto-filled after upload Metadata Title, tags, and description JSON Date Generated (Optional) Auto-filled with video creation date 📅 100 Daily Prompts Automation You can scale this workflow to generate one video per day from a batch of 100 prompts in Google Sheets. Setup Steps Add 100 prompts to your Google Sheet — one per row. Set the Status column for each to Pending. Use a Cron Trigger in n8n to run the workflow once daily (e.g., at 9 AM). Each run picks one Pending prompt, generates a video, uploads to YouTube, then marks it as Done. Continues daily until all 100 prompts are processed. Example Cron Expression 0 9 * * * → Runs the automation every day at 9:00 AM. Node Sequence [Schedule Trigger (Daily)] → [Get Pending Prompt from Sheets] → [Gemini Prompt Parser] → [MagicHour Video Generation] → [Optional: MediaFX Audio Mix] → [Gemini Metadata Generator] → [YouTube Upload] → [Update Row in Sheets] 💡 Optional Enhancements: Add a notification node (Slack, Discord, or Email) after each upload. Add a counter check to stop after 100 videos. Add a “Paused” column to skip specific rows. 🧠 Gemini Integration Gemini handles: JSON parsing for MagicHour requests Metadata generation (title, description, tags) Optional creative rewriting of prompts 🎧 Audio Mixing (Optional) Install MediaFX Community Node → Settings → Community Nodes → n8n-nodes-mediafx Use it to blend background music automatically into videos. 🪶 Error Handling Avoid “Continue on Fail” in key nodes Use IF branches for MagicHour API errors Add retry/timeout logic for polling steps 🧱 Node Naming Tips Rename generic nodes for clarity: Merge → Merge Video & Audio If → Check Video Completion HTTP Request → MagicHour API Request 🚀 How to Use Add MagicHour, Gemini, YouTube, and Sheets credentials Replace background music with your own track Use Google Sheets trigger or daily cron for automation Videos are created, uploaded, and logged — hands-free ⚠️ Disclaimer This template uses community nodes (MediaFX). Install and enable them manually. MagicHour API usage may incur costs based on video duration and quality. 🌐 SEO Keywords MagicHour API, n8n workflow, AI video generator, automated YouTube upload, Gemini metadata, AI Shorts, MediaFX, Google Sheets automation, AI marketing, content automation.

This workflow introduces beginners to one of the most fundamental concepts in n8n: looping over items. Using a simple use case—generating LinkedIn captions for content ideas—it demonstrates how to split a dataset into individual items, process them with AI, and collect the output for review or export. ✅ Key Features 🧪 Create Dummy Data**: Simulate a small dataset of content ideas. 🔁 Loop Over Items**: Process each row independently using the SplitInBatches node. 🧠 AI Caption Creation**: Automatically generate LinkedIn captions using OpenAI. 🧰 Tool Integration**: Enhance AI output with creativity-injection tools. 🧾 Final Output Set**: Collect the original idea and generated caption. 🧰 What You’ll Need ✅ An OpenAI API key ✅ The LangChain nodes enabled in your n8n instance ✅ Basic knowledge of how to trigger and run workflows in n8n 🔧 Step-by-Step Setup 1️⃣ Run Workflow Node**: Manual Trigger (Run Workflow) Purpose**: Manually start the workflow for testing or learning. 2️⃣ Create Random Data Node**: Create Random Data (Code) What it does**: Simulates incoming data with multiple content ideas. Code**: return [ { json: { row_number: 2, id: 1, Date: '2025-07-30', idea: 'n8n rises to the top', caption: '', complete: '' } }, { json: { row_number: 3, id: 2, Date: '2025-07-31', idea: 'n8n nodes', caption: '', complete: '' } }, { json: { row_number: 4, id: 3, Date: '2025-08-01', idea: 'n8n use cases for marketing', caption: '', complete: '' } } ]; 3️⃣ Loop Over Items Node**: Loop Over Items (SplitInBatches) Purpose**: Sends one record at a time to the next node. Why It Matters**: Loops in n8n are created using this node when you want to iterate over multiple items. 4️⃣ Create Captions with AI Node**: Create Captions (LangChain Agent) Prompt**: idea: {{ $json.idea }} System Message**: You are a helpful assistant creating captions for a LinkedIn post. Please create a LinkedIn caption for the idea. Model**: GPT-4o Mini or GPT-3.5 Credentials Required**: OpenAI Credential Go to: OpenAI API Keys Create a key and add it in n8n under credentials as “OpenAi account” 5️⃣ Inject Creativity (Optional) Node**: Tool: Inject Creativity (LangChain Tool) Purpose**: Demonstrates optional LangChain tools that can enhance or manipulate input/output. Why It’s Cool**: A great way to show chaining tools to AI agents. 6️⃣ Output Table Node**: Output Table (Set) Purpose**: Combines original ideas and generated captions into final structure. Fields**: idea: ={{ $('Create Random Data').item.json.idea }} output: ={{ $json.output }} 💡 Educational Value This workflow demonstrates: Creating dynamic inputs with the Code node Using SplitInBatches to simulate looping Sending dynamic prompts to an AI model Using Set to structure the output data Beginners will understand how item-level processing works in n8n and how powerful looping combined with AI can be. 📬 Need Help or Want to Customize This? Robert Breen Automation Consultant | AI Workflow Designer | n8n Expert 📧 robert@ynteractive.com 🌐 ynteractive.com 🔗 LinkedIn 🏷️ Tags n8n loops OpenAI LangChain workflow training beginner LinkedIn automation caption generator

How It Works The workflow runs on a monthly trigger to collect both current-year and multi-year historical HDB data. Once fetched, all datasets are merged with aligned fields to produce a unified table. The system then applies cleaning and normalization rules to ensure consistent scales and comparable values. After preprocessing, it performs pattern mining, anomaly checks, and time-series analysis to extract trends and forecast signals. An AI agent, integrating OpenAI GPT-4, statistical tools, and calculator nodes, synthesizes these results into coherent insights. The final predictions are formatted and automatically written to Google Sheets for reporting and downstream use. Setup Steps 1) Configure fetch nodes to pull current-year HDB data and three years of historical records. 2) Align and map column names across all datasets. 3) Set normalization and standardization parameters in the cleaning node. 4) Add your OpenAI API key (GPT-4) and link the model, forecasting tool, and calculator nodes. 5) Authorize Google Sheets and configure sheet and cell mappings for automated export. Prerequisites Historical data source with API access (3+ years of records) OpenAI API key for GPT-4 model Google Sheets account with API credentials Basic understanding of time series data Use Cases Real Estate: Forecast property prices using multi-year historical HDB/market data with confidence intervals Finance: Predict market trends by aggregating years of transaction or pricing records Customization Data Source: Replace HDB/fetch nodes with stock prices, sensor data, sales records, or any historical dataset Analysis Window: Adjust years fetched (2-5 years) based on data availability and prediction horizon Benefits Automation: Monthly scheduling eliminates manual data gathering and analysis Consolidation: Merges fragmented year-by-year data into unified historical view

What Problem Does It Solve? Customers often ask product questions or prices in comments. Businesses waste time replying manually, leading to delays. Some comments only need a short thank-you reply, while others need a detailed private response. This workflow solves these by: Replying with a friendly public comment. Sending a private message with details when needed. Handling compliments, complaints, and unclear comments in a consistent way. How to Configure It Facebook Setup Connect your Facebook Page credentials in n8n. Add the webhook URL from this workflow to your Facebook App/Webhook settings. AI Setup Add your Google Gemini API key (or swap for OpenAI/Claude). The included prompt is generic — you can edit it to match your brand tone. Optional Logging If you want to track processed messages, connect a Notion database or another CRM. How It Works Webhook catches new Facebook comments. AI Agent analyzes the comment and categorizes it (question, compliment, complaint, unclear, spam). Replying: For questions/requests → public reply + private message with full details. For compliments → short thank-you reply. For complaints → apology reply + private message for clarification. For unclear comments → ask politely if they need help. For spam/offensive → ignored (no reply). Replies and messages are sent instantly via the Facebook Graph API. Customization Ideas Change the AI prompt to match your brand voice. Add forwarding to Slack/Email if a human should review certain replies. Log conversations in Notion, Google Sheets, or a CRM for reporting. Expand to Instagram or WhatsApp with small adjustments. If you need any help Get In Touch

How it works When a meeting ends in Fireflies, the transcript is automatically retrieved and sent to OpenAI for analysis. The AI evaluates objection handling, call effectiveness, and extracts key objections raised during the conversation. It then generates specific objection handlers for future calls. The analysis is formatted into a structured report and sent to both Slack for immediate visibility and Google Drive for centralized storage. Set up steps Prerequisites: Fireflies account with API access OpenAI API key Slack workspace Google Drive connected to n8n Configuration: Connect Fireflies webhook to trigger on meeting completion Add OpenAI API key in the AI analysis nodes Configure Slack channel destination for feedback delivery Set Google Drive folder path for report storage Adjust AI prompts in sticky notes to match your objection categories and sales methodology

🤖 Automated SEO Audit with a Team of AI Specialists This workflow performs a comprehensive, automated monthly SEO and performance audit for any website. It uses a "team" of specialized AI agents to analyze data from multiple sources, aggregates their findings, and generates a final strategic report. Every month, it automatically fetches data from Google Analytics, Google Search Console, and Google PageSpeed Insights, and also performs a live crawl of the target website's homepage. Key Features Fully Automated**: Runs on a schedule to deliver monthly reports without manual intervention. Multi-Source Analysis**: Gathers data from four key marketing sources for a 360° view. AI Agent Team**: Uses a sophisticated multi-agent system where each AI specializes in one area (Analytics, Performance, Technical SEO). Master Analyst**: A final AI agent synthesizes all specialist reports into a single, actionable strategic plan. Automated Storage**: All individual and final reports are automatically saved to a designated Google Sheet. ⚙️ Setup Instructions To use this template, you must configure your credentials and set your target website. 1. Set Your Target Domain (Crucial!): Find the Set Target Website node at the beginning of the workflow. In the "Value" field, replace https://www.your-website.com with the URL of the website you want to audit. This will update the URL across the entire workflow automatically. 2. Configure the Schedule Trigger: Click on the Schedule Trigger node to set when you want the monthly report to run. 3. Connect Your Google Credentials: Google Analytics**: Select your credential in the Get a report node. Google Search Console**: Select your credential in the Search Console (HTTP Request) node. Google Sheets*: Select your credential in *all Google Sheets nodes. Google PageSpeed API Key**: Go to the "Credentials" tab in n8n and create a new "Generic Credential" with the type "API Key - Query Param". Name it Google API Key. The "Parameter Name" must be key. Paste your PageSpeed API key into the "API Key" field. Go back to the PageSpeed Insight node, select "API Key - Query Param" for Authentication, and choose your new credential. 4. Connect OpenAI Credentials: This template uses multiple OpenAI Chat Model nodes. Configure each one with your OpenAI API key. 5. Set Your Google Sheet: In each of the Google Sheets nodes, replace the hardcoded "Document ID" with the ID of your own Google Sheet where you want to store the reports. 🔬 Workflow Explained Phase 1: Data Collection: The Schedule Trigger starts the workflow. Four parallel branches collect data from Google Analytics, PageSpeed Insights, Search Console, and a direct website crawl. Phase 2: Data Processing & Specialist Analysis: Each data source is processed by a dedicated Code node to format the data. The formatted data is then sent to a specialized AI agent (ANALYTICS SPECIALIST, PERFORMANCE SPECIALIST, etc.) for in-depth analysis. Phase 3: Report Aggregation: A Merge node waits for all four specialist reports to be completed. A DATA AGGREGATOR node then combines them into a single, comprehensive package. Phase 4: Master Synthesis & Storage: The final MASTER ANALYST agent receives the aggregated data and produces a high-level strategic summary with actionable recommendations. This final report is then saved to Google Sheets.

Revolut Extracts Analyzer This n8n template processes Revolut statements, normalizes transactions, and uses AI to categorize expenses automatically. Use cases include detecting subscriptions, separating internal transfers, and building dashboards to track spending. How it works Get Categories from Supabase** Download & Transform** Loop Over Items** LLM Categorizer** Insert into Supabase** How to use Start with the manual trigger node or replace it with a schedule/webhook. Connect Google Drive to provide Revolut CSV files. Ensure Supabase has tables for transactions and categories. Extend with notifications, reports, or BI tools. Requirements Google Drive for CSV files Supabase tables for categories & transactions LLM provider (OpenAI/Gemini)

Access live KuCoin Spot Market data instantly in Telegram! This workflow integrates the KuCoin REST API with Telegram and an optional GPT-4.1-mini formatter, delivering real-time insights like latest prices, 24h stats, order book depth, trades, and candlesticks — all structured into clean Telegram messages. 🔎 How It Works A Telegram Trigger listens for user commands. User Authentication validates the Telegram ID against an allowlist. A SessionId is generated from the chat ID to support memory across turns. The KuCoin AI Agent orchestrates API requests: 24h Stats → /api/v1/market/stats?symbol=BTC-USDT Order Book Depth → /api/v1/market/orderbook/level2_100?symbol=BTC-USDT Latest Price → /api/v1/market/orderbook/level1?symbol=BTC-USDT Best Bid/Ask → /api/v1/market/orderbook/level1?symbol=BTC-USDT Klines (Candles) → /api/v1/market/candles?symbol=BTC-USDT&type=15min&limit=20 Recent Trades → /api/v1/market/histories?symbol=BTC-USDT Average Price (via Ticker) → /api/v1/market/orderbook/level1?symbol=BTC-USDT Utility Tools process results: Calculator → spreads, % changes, averages. Think → reshapes JSON, selects fields, formats outputs. Message Splitter breaks outputs >4000 chars (Telegram limit). Final report is sent back via Telegram SendMessage in human-readable format. ✅ What You Can Do with This Agent Get 24h rolling statistics (open, high, low, close, last, volume). Retrieve full order book depth (20, 100 levels) or best bid/ask. Monitor real-time latest prices with spreads. Analyze candlestick data (OHLCV) across supported intervals. View recent public trades with price, size, side, and time. Use average price proxies from bid/ask + last trade. Receive structured Telegram reports — not raw JSON. 🛠️ Setup Steps Create a Telegram Bot Use @BotFather to create a bot and copy its token. Configure in n8n Import KuCoin AI Agent v1.02.json. Update User Authentication node with your Telegram ID. Add Telegram API credentials (bot token). Add OpenAI API key. (Optional) Add KuCoin API key Deploy & Test Activate the workflow in n8n. Send a query like BTC-USDT to your bot. Instantly receive structured KuCoin Spot Market insights in Telegram. 📤 Output Rules Responses grouped into Price, 24h Stats, Order Book, Klines, Trades. No raw JSON (only human-readable summaries). No financial advice or predictions. Always fetch directly from KuCoin’s official API. 📺 Setup Video Tutorial Watch the full setup guide on YouTube: If you want, I can also update embed links & thumbnails elsewhere to match this. ⚡ Unlock KuCoin Spot Market insights in Telegram — fast, reliable, and API-key free. 🧾 Licensing & Attribution © 2025 Treasurium Capital Limited Company Architecture, prompts, and trade report structure are IP-protected. No unauthorized rebranding permitted. 🔗 For support: Don Jayamaha – LinkedIn

🖥️ Automated Website Uptime Monitor with Email Alerts & GitHub Status Page Update This n8n workflow continuously monitors your website’s availability, sends email alerts when the server goes down, and automatically updates a status page (index.html) in your GitHub repository to reflect the live status. 📌 Good to Know The workflow checks your website every 2 minutes (interval configurable). If the website is down (503, bad response, or error) → it sends an email alert and updates the GitHub-hosted status page to show Down. If the website is up (200) → it updates the GitHub-hosted status page to show Up. The email notification includes an HTML-formatted alert page. You can use GitHub Pages to host the status page publicly. ℹ️ What is GitHub Pages? GitHub Pages is a free hosting service provided by GitHub that lets you publish static websites (HTML, CSS, JS) directly from a GitHub repository. You can use it to make your index.html status page publicly accessible with a URL like: ⚡ How to Set Up GitHub Pages for Your Status Page Create a new repository on GitHub (recommended name: status). Add a blank index.html file (n8n workflow will later update this file). Go to your repository → Settings → Pages. Under Source, select the branch (main or master) and folder (/root). Save changes. Your status page will now be live at: https://<USERNAME>.github.io/status ✅ Prerequisites An n8n instance (self-hosted or cloud). A GitHub account & repository (to host the status page). A Gmail account (or any email service supported by n8n – example uses Gmail). Access to the target website URL you want to monitor. ⚙️ How it Works Schedule Trigger → Runs every 2 minutes. HTTP Request → Pings your website URL. Switch Node → Evaluates the response status (200 OK vs error/503). Code Node → Generates a dynamic HTML status page (Up/Down). GitHub Repo & File → Github Repo Name Should be https://github.com/<OWNER_NAME>/status (recommended) & Must have(required) a blank file named as index.html before triggering this flow. GitHub Node → Updates/commits the index.html file in your repository. Gmail Node → Sends an email alert if the site is down. 🚀 How to Use Import the workflow JSON into your n8n instance. Configure credentials for: GitHub (Personal Access Token with repo permissions). Gmail (or your preferred email service). Replace the following: https://app.yourdomain.com/health → with your own website URL. example@gmail.com → with your email address (or distribution list). GitHub repo details → with your repository where index.html will live. Deploy the workflow. (Optional) Enable GitHub Pages on your repo to serve index.html as a live status page. 🛠 Requirements n8n v1.0+ GitHub personal access token Gmail API credentials (or SMTP/email service of your choice) 🎨 Customising this Workflow Interval** → Change schedule from 2 minutes to any desired frequency. Email Content** → Modify HTML alert template in the Gmail node. Status Page Styling** → Edit the HTML/CSS in the Code node to match your branding. Error Handling** → Extend Switch node for other status codes (e.g., 404, 500). Multiple Websites** → Duplicate HTTP Request + Switch nodes for multiple URLs. 👤 Who Can Use It? DevOps & SRE Engineers** → For automated uptime monitoring. Freelancers/Developers** → To monitor client websites. Startups & SMEs** → For a free, lightweight status page without paid tools. Educators/Students** → As a hands-on learning project with n8n. 🌟 Key Features 🔄 Automated uptime checks (configurable interval). 📧 Email notifications on downtime. 📝 Dynamic HTML status page generation. 🌍 GitHub Pages integration for public visibility. ⚡ Lightweight & cost-effective (no paid monitoring tool needed). 🔗 Tools Integration n8n** – Orchestration & automation. GitHub** – Version control + hosting of status page. Gmail** – Email notifications. HTTP Request** – Website availability check. 📈 Example Use Cases Personal website monitoring with public status page. Monitoring SaaS apps & notifying support teams. Internal company services uptime dashboard.

Description  Automatically ingests new employee data, extracts relevant signals, scores attrition risk, and notifies HR/managers with structured insights and recommended actions. Built on Azure OpenAI Chat with Structured Output Parser and true/false routing for escalation. What This Template Does  Trigger for new data: Starts when a new profile, survey, or report file is added. Download & extract: Retrieves the file and converts PDFs/text into analyzable content. Analyze signals: Uses Azure OpenAI Chat to interpret sentiment, workload, performance notes, feedback, and changes (role, compensation, manager, location). Structured parsing: Maps to fields like risk_score, risk_level, key_drivers, recommended_interventions, escalation_required. Logic routing: Applies thresholds (e.g., risk_score ≥ 0.7) and flags for urgent follow-up. Email alerts: Drafts and sends tailored notifications to HR/manager with action steps. Key Signals Considered  Sentiment & language: Negative tone, burnout cues, disengagement in feedback. Activity trends: Drop in participation, delayed responses, meeting absenteeism. Performance & goals: Recent rating changes, missed OKRs, quality issues. Role & compensation: Lateral moves, pay gaps vs. market, stalled progression. Managerial context: Team churn, conflict mentions, low recognition frequency. Features  Azure OpenAI Chat: Interprets unstructured text into consistent risk fields. Structured Output Parser: Guarantees schema for downstream decisions. Conditional Logic (true/false): Threshold checks for escalation. Memory: Maintains context across multiple files per employee for trend-aware scoring. Calculate avg span: Computes tenure or recency metrics used in risk scoring. Email Composer & Sender: Generates and dispatches HR-ready alerts. Requirements  n8n instance with access to employee data sources (Drive, Inbox, HR folder). Extract From PDF configured for clean text output. Azure OpenAI credentials (e.g., GPT‑4o‑mini) connected to Chat Model. Email service (Gmail/SMTP) set in n8n Credentials. Parser schema aligned to your People Analytics fields (risk_score, drivers, actions).

AI-Powered Invoice Extraction & Automation System Workflow Aim The aim of the Invoice Data Automation workflow is to streamline invoice processing by extracting, validating, and storing invoice details automatically. It uses AI to read invoices (from images/PDFs), structures the data in JSON, checks for missing or duplicate entries, and records the information in a Google Sheet while also uploading the original invoice to Google Drive. Additionally, it sends email notifications for successful entries, duplicates, or missing fields. Goal The goal is to: Allow users to upload invoice images/files via chat. Extract invoice data using AI and format it into a structured JSON. Validate mandatory fields like invoice_id, shop_name, date, Total, and items. Check if the invoice already exists in the Google Sheet. Append new invoices to Google Sheets and upload the original file to Google Drive. Notify the user via email about success, duplicates, or errors. This ensures that invoices are processed accurately, efficiently, and securely with minimal manual effort. Requirements The workflow relies on specific components and configurations: n8n Platform The automation is built and hosted on n8n, which orchestrates the entire workflow. Node Requirements When chat message received – Triggers the workflow when a user submits an invoice. Analyze image1 – Uses Google Gemini Vision AI to extract invoice data from the uploaded file. AI Agent1 + Google Gemini Chat Model1 – Restructures the extracted data into strict JSON format. Make data in JSON structure format – Prepares and organizes the structured output. Get data – Looks up the Google Sheet to check if the invoice already exists. check if Data exist or not in table – Decides whether to process as new data or duplicate. New data add using payload / Check Mandatory fields – Ensures invoice JSON is valid and complete. If – check missing field – Branches based on whether mandatory fields are present. no missing field – new data add using payload 2 – Passes only verified invoices forward. Append data to sheet – Saves invoice data in Google Sheets. Upload invoice to drive – Uploads the original invoice file to Google Drive. Send successful email – Notifies the user of successful entry. Duplicate entry send mail – Alerts the user if the invoice already exists. Send missing field error on mail – Sends an error email if mandatory fields are missing. Credentials Google Gemini (PaLM) API** – For AI-based invoice data extraction and formatting. Google Sheets API** – For storing structured invoice records. Google Drive API** – For uploading original invoices. Gmail API** – For sending success, duplicate, and error notifications. Input Requirements Invoice file (Image or PDF). Output Structured invoice data in Google Sheets. Original invoice stored in Google Drive. Notifications sent via Gmail (success, duplicate, or error). API Usage Google Gemini (PaLM API):** Used in Analyze image1 and AI Agent1 to extract and structure invoice data. It ensures fields like invoice_id, shop_name, date, and items are clearly formatted. Google Sheets API:** Used in Get data and Append data to sheet nodes to validate duplicates and store new invoices. Google Drive API:** Used in Upload invoice to drive to securely store the original uploaded invoice file. Gmail API:** Used in Send successful email, Duplicate entry send mail, Send missing field error on mail to notify users about the status of invoice processing. Workflow Summary The Invoice Data Automation workflow automates the entire process of invoice handling by: Receiving invoice uploads via chat. Extracting invoice details with AI (Google Gemini). Structuring and validating the data in JSON format. Checking Google Sheets for duplicates. Appending new invoices to the sheet and uploading originals to Google Drive. Sending email notifications to keep the user updated on the process outcome. This end-to-end automation ensures invoices are handled with speed, accuracy, and transparency, reducing manual work and eliminating common errors in invoice management.