Marketplace
3.557 fertige Workflow-Dateien zum Download, plus 10.661 quellenverknüpfte n8n-Referenzen.
Triage Gmail and draft replies with GPT-5 Mini and Google Sheets
Quick overview This workflow watches your Gmail inbox for new unread emails, uses OpenAI (GPT-5 Mini) to classify each message by priority and category, logs the triage results to Google Sheets, and creates a Gmail draft reply only when the email needs a personal response. How it works Triggers every minute when a new unread email arrives in Gmail. Applies your configured preferences (name, role, categories, and drafting style) to guide the triage. Sends the email content to OpenAI (GPT-5 Mini) to return a structured priority, category, one-line summary, whether a reply is needed, and an optional draft reply. Appends or updates a row in Google Sheets with the email details and triage results. If the email needs a reply, creates a draft reply in Gmail in the same thread addressed to the original sender. Setup Connect your Gmail account (Gmail Trigger and Gmail Draft) and ensure the trigger is set to monitor unread mail as desired. Add an OpenAI credential and select the GPT-5 Mini chat model in the OpenAI node. Connect Google Sheets OAuth credentials, then set the target spreadsheet document ID and sheet name for the triage dashboard. Create a Google Sheet with columns for Date, Fro
Run a Telegram voice assistant with OpenAI GPT-5 Mini and Google Calendar
Quick overview This workflow turns a Telegram bot into a personal assistant that accepts text or voice notes, transcribes audio with OpenAI, uses a memory-enabled AI agent for replies and calculations, and creates Google Calendar reminder events from natural-language requests. How it works Triggers whenever a new Telegram message is received by your bot. Routes the message based on type, sending text directly to the assistant, voice notes to transcription, and other message types to a fallback reply. For voice notes, downloads the audio from Telegram and transcribes it to text using OpenAI. Sends the user’s text (typed or transcribed) to an OpenAI chat model powered agent that remembers the last 15 messages per chat and can use a calculator tool. When the user asks for a reminder or event, the agent creates a Google Calendar event with AI-generated title and start/end times. Sends the agent’s final response back to the originating Telegram chat. Setup Create a Telegram bot with @BotFather, add a Telegram credential in n8n, and enable updates for the Telegram Trigger. Add an OpenAI credential with access to the chat model and audio transcription used in the workflow. Add a Google Ca
Check Japanese ad copy compliance with Google Gemini, Sheets, Slack and Gmail
Quick Overview This workflow runs daily to review Japanese ad copy in Google Sheets using Google Gemini, writes compliance risk results back to the sheet, and alerts the right team in Slack (and drafts a Gmail revision request) based on high/medium/low risk. How it works Runs every day at 9:00 on a schedule. Reads ad copy rows from Google Sheets to find items that still need a compliance check. Sends each copy item to Google Gemini with the configured product category, target laws, and extra rules to generate a risk level, violations, and a compliant rewrite. Parses and normalizes the Gemini output into fields like risk level, violation count, and safe rewrite, and posts a Slack alert if the AI check fails. Updates the corresponding Google Sheets row with the compliance results to keep a record of the review. Routes the item by risk level and posts to Slack for legal blocking (high), marketing review (medium), publish-ready notification (low), or manual review when the result is inconclusive. For high-risk copy, also creates a Gmail draft requesting the author to revise the copy using the suggested compliant rewrite. Setup Add credentials for Google Sheets, Google Gemini (PaLM) API
Verify Japanese invoice registration numbers from Gmail using Gemini, NTA API, Sheets and Slack
Quick Overview This workflow monitors Gmail for unread invoice emails with PDF attachments, extracts invoice details with Google Gemini, verifies Japanese qualified invoice registration numbers against the National Tax Agency (NTA) Invoice Web-API, logs results to Google Sheets, and sends Slack alerts for invalid, missing, or inconclusive checks. How it works Polls Gmail hourly for unread emails matching “has:attachment invoice” and downloads the first attachment. Extracts text from the attached invoice PDF. Uses Google Gemini to parse the invoice text into structured fields such as the T-registration number, issuer name, invoice date, and amounts. Normalizes and validates the registration number to ensure it matches the required “T + 13 digits” format. If the format is valid, calls the NTA Invoice Web-API to verify the registration number and interprets the response as valid, invalid, or not found. Appends the invoice details and verification status to a Google Sheets worksheet. Routes the outcome by sending the appropriate Slack alert for invalid/not found/inconclusive results or marking the invoice email as read when the number is valid. Setup Connect your Gmail OAuth2 credentia
WTrack competitor pricing changes with Google Sheets, OpenAI, and Gmail
Quick Overview This workflow runs daily, checks competitor webpages listed in Google Sheets, compares the latest page text to the previous snapshot using OpenAI, stores the updated snapshot in Google Sheets, and emails a consolidated HTML change report via Gmail. How it works Runs every day at 9:00 AM on a schedule. Reads the list of competitor sites (Site ID, Site Name, URL) from a Google Sheets tab. Fetches each competitor URL and extracts the visible page text from the HTML body. Looks up the previous saved snapshot for the same Site ID in a Google Sheets “Snapshots” tab. Uses OpenAI (gpt-4o-mini) to compare previous vs current text and summarize pricing, plan, and campaign changes or return “No changes detected”. Saves the current page text and fetch timestamp back to Google Sheets (append or update by Competitor Site ID) and formats each result into an HTML table row. Aggregates all rows into a single HTML table and sends the daily report email through Gmail. Setup Create a Google Sheets file with a “Monitored Sites” tab (Site ID, Site Name, URL) and a “Snapshots” tab (Competitor Site ID, Last Fetched At, Page Text). Add Google Sheets OAuth credentials and set your spreadsheet
W
Monitor weekly LLM share of voice with OpenRouter, Google Sheets, and email reports
Quick overview This workflow runs weekly to query multiple LLMs via OpenRouter with prompts from Google Sheets, analyzes brand mentions and domain citations, aggregates weekly Share of Voice metrics, and emails an HTML visibility report. How it works Runs every week on a schedule trigger. Reads active prompts from a Google Sheets “prompts” tab and expands them into multiple model runs (including repeated runs per model) to create OpenRouter chat completion requests. Sends each request to OpenRouter, normalizes the response into answer text and extracted citation URLs, and appends the results to the Google Sheets “runs” tab. Loads brand definitions from the Google Sheets “brands” tab, scans the latest successful runs for brand mentions and matching citation domains, and writes one mention/citation record per brand-run to the “mentions” tab. Aggregates the mention and citation results into weekly metrics per model (and an “all models” total), including mention rate, citation rate, Share of Voice, and average first-mention position, and appends them to the “weekly_agg” tab. Builds an HTML report that compares the current week to the previous week, flags alerts (SoV drop > 5pp or citat
Handle WhatsApp support text and voice messages with OpenAI GPT-5 Mini
Quick overview This workflow responds to incoming WhatsApp Business messages, handling both text and voice notes by transcribing audio with OpenAI and replying with an OpenAI chat agent that uses per-contact conversation memory and answers only from the business information you provide. How it works Triggers when a new WhatsApp message is received. Routes the incoming message by type, sending text messages directly to the support flow, audio messages to a voice-transcription flow, and other message types to a fallback reply. For voice notes, retrieves the WhatsApp media URL, downloads the audio file, and transcribes it to text with OpenAI. Sends the customer’s text (original or transcribed) to an OpenAI chat agent configured to answer only using your provided business information. Stores and reuses a per-contact conversation history keyed by the sender’s WhatsApp number to maintain context across messages. Sends the agent’s response back to the customer as a WhatsApp text message. Setup Connect WhatsApp Business Cloud credentials for both receiving messages (trigger) and sending replies, and ensure your WhatsApp webhook is configured to point to the trigger URL. Add OpenAI credenti
Answer customer questions on WhatsApp with OpenAI, Gmail, and Google Sheets
Quick overview This workflow answers incoming WhatsApp customer questions using an OpenAI-powered agent that reads your live website via HTTP requests, escalates unclear or sensitive cases to your support team via Gmail, and logs each conversation to Google Sheets. How it works Triggers when a new WhatsApp message is received. Loads configuration values (company name, website root URL, AI model, language rules, escalation email, and WhatsApp phone number ID) and extracts the customer phone number and message text. Ignores non-text WhatsApp updates (such as images, audio, and status messages). Uses OpenAI with conversation memory to navigate your website by listing links and fetching relevant pages, then generates a structured result containing an answer, escalation flag, sentiment, topic, and source URLs. If the agent marks the request as needing a human, sends an escalation email via Gmail to your support address with the customer details and the drafted reply. Sends the final plain-text reply back to the customer on WhatsApp. Appends the conversation details to a Google Sheets log. Setup Connect credentials for WhatsApp Trigger/WhatsApp Cloud API, OpenAI, Gmail, and Google Sheets
Run a personal assistant for calendar, Gmail and utilities with OpenAI and MCP
Quick overview This workflow runs a chat-based OpenAI assistant in n8n that calls three MCP servers for Google Calendar management, Gmail search and draft replies, and utility tools for weather, currency conversion, and calculations. How it works Receives a chat message in n8n to start or continue a conversation. Loads the assistant configuration (model, memory window, and system prompt) and sends the user message to an OpenAI chat model with short-term conversation memory. When the assistant needs calendar actions, it calls an MCP server that searches, creates, updates, or deletes Google Calendar events. When the assistant needs email actions, it calls an MCP server that searches Gmail messages and creates draft replies for user review. When the assistant needs quick utilities, it calls an MCP server that fetches weather from wttr.in, converts currency using frankfurter.app, or runs calculations. Returns the assistant’s response back to the chat, including any results from the MCP tool calls. Setup Add credentials for OpenAI, Google Calendar (OAuth2), and Gmail (OAuth2) in n8n. Activate the workflow, then copy each MCP Server Trigger Production URL for the Calendar, Gmail, and Uti
Send daily AI news digests from RSS feeds with OpenAI, Telegram and Gmail
Quick overview This workflow runs every morning at 8 AM, pulls articles from multiple RSS feeds, deduplicates and trims the list, uses OpenAI (GPT-5 Mini) to write a short plain-text news digest, and delivers the same digest to a Telegram chat and a Gmail inbox. How it works Runs daily at 8:00 AM on a schedule. Splits your configured RSS feed URL list into individual feeds and fetches the latest articles from each one, continuing even if a feed fails. Removes duplicate articles by link, keeps only the newest items up to your maxArticles limit, and trims each item to title, link, publish date, and a short snippet. Combines all cleaned articles into a single JSON list and sends it to OpenAI (GPT-5 Mini) to select 5–8 top stories and generate a single plain-text digest under 3,500 characters. Sends the generated digest to your specified Telegram chat. Emails the same digest as a plain-text message through Gmail. Setup Add an OpenAI credential and ensure the GPT-5 Mini model is available in your account. Create a Telegram bot with @BotFather, add the Telegram credential in n8n, and set your target telegramChatId (for example by using @get_id_bot). Connect a Gmail account in n8n and set
Run a multimodal WhatsApp AI assistant with OpenAI for text, voice and images
Quick overview This workflow turns WhatsApp into a multimodal assistant that answers text, voice notes, images, and PDF documents using OpenAI, and can generate images with DALL·E on demand, replying back in WhatsApp with either text, audio, or an image. How it works Triggers when a new WhatsApp message is received. Detects whether the incoming message is text, a voice note, an image, a PDF document, or an unsupported type. For text messages, generates an image with OpenAI DALL·E when the message starts with the configured /image command, and sends the generated image back to the sender. For voice notes, fetches the WhatsApp media URL, downloads the audio, transcribes it with OpenAI, and forwards the transcript to the assistant. For images, fetches the WhatsApp media URL, downloads the image, describes it with OpenAI vision using the configured analysis prompt, and forwards the description (plus any caption) to the assistant. For PDF documents, downloads the file from WhatsApp, extracts the PDF text, and forwards the extracted content (plus any caption) to the assistant, while non-PDF files receive an error message. Uses an OpenAI chat model with per-contact short-term memory to ge
Screen LinkedIn jobs and send tailored applications with Apify and OpenAI
Quick overview This workflow collects your job preferences via an n8n form, uses Apify to scrape LinkedIn job listings, and has OpenAI screen and rank them. After you approve a shortlist by Gmail, it generates tailored resume and cover-letter PDFs with DocRaptor, emails them to you, and logs matches to Sheets How it works Receives your job preferences and resume text through an n8n form submission. Sends the preferences to Apify to scrape recent LinkedIn jobs, then removes duplicates and obvious mismatches (seniority, years of experience, and location). Uses OpenAI to score each job’s relevance and eligibility and returns a JSON verdict with a fit score and short reason. Keeps the top matches above the configured threshold and emails you a shortlist in Gmail with approve/decline buttons. If you approve, uses OpenAI to draft a job-specific resume and cover letter from only the provided profile text and generates HTML interview prep questions. Converts the resume and cover letter HTML into PDFs via DocRaptor, emails the tailored application package to you in Gmail, and appends the match details to a Google Sheets tracker. Setup Add credentials for OpenAI, Gmail OAuth2, Google Sheets
Govern enterprise marketplace support actions with OSuite approvals
Quick overview This workflow runs on demand to preflight a high-value marketplace support action and send it to OSuite for governance review, then blocks, waits for approval, or proceeds to draft a safe internal refund-risk recommendation and records the final outcome in OSuite. How it works Starts manually to create a structured enterprise support action request with risk, data classification, systems touched, and expected side effects. Runs a local preflight that validates required fields, normalizes the risk score, and computes exposure level, blast radius, and a recommended control. Stops with an intake-fix status if the request is incomplete, including the blockers and warnings to address. Retrieves an OSuite runtime exposure snapshot and submits the planned work to OSuite for policy review with the preflight and decision context. Builds an operator approval packet from OSuite’s response and stops immediately if OSuite blocks the action. Checks OSuite to confirm whether the specific action ID has been approved, and stops in a waiting state until approval is granted. After approval, drafts an internal-only refund-risk recommendation (no refunds or external messages) and records
WCreate human-reviewed personalized PDFs from Stripe payments using OpenAI
Quick overview This workflow receives Stripe payment webhooks, looks up the customer’s order in Google Sheets, generates personalized HTML content with OpenAI, converts it to a PDF using PDFShift, then queues the request for human approval and delivers the final document via Gmail with Slack notifications. How it works Receives a Stripe payment notification via a webhook endpoint. Extracts payment details (event type, payment ID, customer email, amount, currency) and stops the main flow if the email is missing. Pulls order rows from Google Sheets and matches the order to the payer’s email. Sends the combined payment and order data to the OpenAI Chat Completions API to generate structured personalized content, then renders it into an HTML document. Converts the HTML to a PDF with PDFShift and sends the customer an acknowledgement email via Gmail. Appends the request to a Google Sheets “ReviewQueue” and notifies staff in Slack with instructions to approve via a separate webhook. When an approval webhook is received and marked approved, emails the final message to the customer via Gmail and updates the “ReviewQueue” status in Google Sheets. Setup Create and configure two webhook URLs
Route urgent Gmail support emails and WhatsApp digests with Groq and Supabase
Quick overview This workflow monitors a Gmail inbox, uses Groq LLM classification to label each support email as urgent, routine, or spam, logs the result to Supabase, sends immediate WhatsApp alerts for urgent messages, and delivers a daily WhatsApp digest summarizing routine emails. How it works Triggers every minute when a new email arrives in Gmail. Uses Groq (via an LLM prompt) to classify the email as urgent, routine, or spam and generate a one-sentence summary and reason. Inserts the email metadata, category, and summary into a Supabase table for tracking. Sends an immediate WhatsApp message to the support owner when the email is classified as urgent and updates the Supabase record to reflect it was notified. Runs on a daily schedule to fetch all routine emails in Supabase that have not yet been included in a digest. Aggregates those routine emails into a single WhatsApp digest message, sends it to the support owner, and marks the included Supabase records as digested. Setup Connect Gmail OAuth2 credentials and ensure the trigger watches the support inbox/labels you want monitored. Add Groq API credentials for the chat model used to classify and summarize emails. Add Supabas
Generate weekly student progress reports with Gemini, Supabase, and WhatsApp
Quick overview This workflow runs weekly to pull student attendance and score data from Supabase, uses Google Gemini to generate per-student performance summaries and attention flags, sends immediate WhatsApp alerts for flagged students, then compiles all summaries into a PDF report, uploads it, and shares it with the coach via WhatsApp. How it works Runs weekly on a schedule. Fetches all student weekly metrics (attendance and scores) from Supabase. Uses Google Gemini to write a short performance summary per student and determine whether the student should be flagged for attention based on attendance and score-drop rules. If a student is flagged, sends a WhatsApp message to the coach and inserts a flag record into Supabase. Aggregates all students’ summaries into a single HTML weekly report. Converts the HTML report to a PDF via an HTTP-based HTML-to-PDF API, uploads the PDF to a file-hosting API, and sends the PDF link/document to the coach via WhatsApp. Logs the report URL to Supabase for recordkeeping. Setup Add Supabase credentials and create the required tables/columns (weekly_student_data, attention_flags, and weekly_reports) referenced by the workflow. Add a Google Gemini (P
Send CRM lead outreach emails with Notion, Gmail, Google Drive and OpenAI
Quick Overview This workflow watches a Notion CRM for leads ready to contact, checks Gmail to avoid duplicate outreach, then sends or drafts an email with Google Drive PDF attachments and updates the lead status in Notion, with bounce detection that marks invalid emails (using OpenAI to extract addresses). How it works Triggers when a lead page is updated in a selected Notion CRM database. Validates that the lead’s Email field looks like an email address and searches Gmail Sent for recent messages to that recipient to detect prior outreach. If the lead was already emailed and the current status is safe to overwrite, it updates the Notion lead status to “Emailed.” If the lead was not previously emailed, it downloads two PDF attachments from Google Drive, converts them to Gmail attachments, and either creates a Gmail draft for specific domains (optionally sending a Twilio SMS to a rep) or sends a generic vs personalized Gmail email based on whether a contact name exists. After sending, it waits briefly, searches Gmail for bounce messages mentioning “Address not found,” and updates the Notion record to “INVALID EMAIL” (or sets “Emailed” when the status indicates the lead is in an acti
WAnalyze compliant documents with PromptLock Guard, Claude, and Google Sheets
Quick overview Screen contracts, intake forms, and reports for HIPAA, GDPR, and PCI data — plus always-on prompt-injection detection — before Claude summarizes them. Clean documents pass through, risky ones get flagged for review or blocked, and every document gets an audit row in a Google Sheet. How it works Receives a POST request to a webhook containing either a PDF upload or a JSON body with a text field. Extracts text from PDFs or uses the provided JSON text as-is. Sends the document text to PromptLock Guard to screen for regulated-data and prompt-injection risk, failing closed on screening errors. If the document is allowed or redacted, sends the cleaned text to Anthropic Claude and returns a structured JSON analysis in the webhook response. If the document is flagged, sends a Gmail notification email for human review instead of sending the content to the AI model. If the document is blocked (or screening is unavailable), returns a JSON webhook response indicating the block/unverified reason. Appends a per-document audit row (timestamp, action taken, risk score, and compliance status) to a DocAuditLog tab in Google Sheets. Setup Install the n8n-nodes-promptlock-guard communit
Sync SAP sales project fields between Microsoft SQL and Asana
Quick overview This workflow runs hourly to sync project records from a Microsoft SQL Server staging table into matching Asana projects, updating Asana custom fields and writing back sync status, errors, and the Asana project ID to the database. How it works Runs every hour and queries Microsoft SQL Server for up to 100 project records that are not yet synced (or previously failed) and have fewer than three sync attempts. Marks each selected record as “Processing” in SQL Server to prevent duplicate handling during the sync. Calls the Asana API to list projects in a specific portfolio and matches the SQL ProjectName to an Asana project name. If no Asana project matches, updates the SQL record to a “Waiting for Project ID” state with a message for manual project creation. If a match is found, retrieves the Asana project’s custom fields and builds an update payload mapping SQL values (manager, margin, revenue, costs, and dates) to Asana custom fields. Updates the Asana project via the Asana API and then marks the SQL record as “Completed” with the Asana project ID, or logs the error and marks the record as “Failed” while incrementing the attempt counter. Setup Create Microsoft SQL Ser
Save starred Gmail emails as Markdown notes to an Obsidian Google Drive folder
Quick overview This workflow runs daily, finds starred Gmail emails that are not yet labeled as saved, converts each email into a Markdown note with YAML frontmatter, uploads the note to a Google Drive folder synced with your Obsidian vault, and then labels the email to prevent duplicates. How it works Runs every day at 7am on a schedule trigger. Searches Gmail for emails matching your query (default: starred) while excluding messages already labeled obsidian-saved. Converts each matching email into a Markdown file with YAML frontmatter (title, from, date, tags) and the email body, using a date-prefixed, filesystem-safe filename. Processes emails one at a time to avoid rate limits and ensure reliable saves. Creates a .md file in the selected Google Drive folder using the generated filename and Markdown content. Adds the obsidian-saved label to the original Gmail message so it is skipped in future runs. Setup Add Gmail OAuth credentials and ensure your account has access to read messages and apply labels. Add Google Drive OAuth credentials and select the destination Drive and folder ID where your Obsidian vault syncs (for example, a folder inside your vault). Create a Gmail label na
Track weekly Google keyword rankings with SearchApi and Slack
Quick Overview This workflow runs weekly to track your Google rankings for multiple keywords using SearchApi, compares current positions to the previous run stored in an n8n Data table, and posts a formatted movement report to Slack. How it works Runs every week on a schedule. Loads your target domain, comma-separated keyword list, and Google location, then fetches previously saved ranks from an n8n Data table. Splits the keyword list into individual keywords and queries Google via SearchApi for the first 5 pages of results per keyword. Scans the organic results to find your domain’s best position per keyword and calculates week-over-week movement (up, down, new, dropped out, or not ranking in the top 50). Formats the results into a Slack Block Kit message with a plain-text fallback. Posts the report to a Slack channel and upserts currently ranking keywords back into the Data table for the next comparison. Setup Add a SearchApi.io credential in the SearchApi node. Create or select an n8n Data table (for example, “Rank History”) with columns for keyword, position, url, and last_checked, and select it in both the read and upsert Data table nodes. Add a Slack OAuth2 credential, choose
Draft personalized cold emails from Google Sheets using Gemini and HubSpot
Quick overview This workflow batch-processes leads from Google Sheets, researches each person and company using Tavily plus Google Gemini, drafts a personalized cold email, then creates/updates the contact in HubSpot with a research note and a saved email draft before marking the lead as Done in the sheet. How it works Runs manually and sets a batch size that controls how many leads to process per run. Reads leads from Google Sheets, skips rows already marked as Done, and normalizes the selected batch into clean lead fields. Processes the batch one lead at a time and uses Tavily search (last 60 days) with Google Gemini to extract the most recent public activity, pain points, and a personalization hook. Cleans and parses the research JSON so it can be reused reliably downstream. Uses Google Gemini to draft a 90–120 word cold outreach email (subject and body) that incorporates the research and offers a free “Automated LinkedIn Post Creator” n8n workflow. Creates or reuses the HubSpot contact, logs a HubSpot note with the research and drafted email, and saves the email as a HubSpot engagement in DRAFT status. Updates the matching row in Google Sheets (by Email) to set Status to “Done
Create Zoho Books invoices from email attachments using OpenAI OCR
Quick overview This workflow monitors an IMAP inbox for emails with invoice attachments, uses OpenAI to OCR and extract structured invoice data, looks up customers and tax/currency settings in Zoho Books, and then creates a new Zoho Books invoice with the original attachment included. How it works Triggers when a new email arrives via IMAP. Filters for emails that contain attachments, then splits each attachment into its own item for processing. Normalizes each attachment’s binary data and routes it to OpenAI for OCR based on whether it is a PDF or an image. Fetches taxes, currencies, and active customer contacts from Zoho Books and prepares the data for matching and invoice creation. Sends the OCR text plus Zoho Books tax metadata to OpenAI to validate that the document is a sales invoice and to return invoice and customer details as JSON. Filters out non-invoice attachments, matches the extracted customer to an existing Zoho Books contact (with a configurable fallback), and posts a new invoice to Zoho Books using multipart upload to attach the original file. Setup Add IMAP credentials for the mailbox that receives invoice emails. Add Zoho Books OAuth2 credentials and ensure the c
WRecover Shopify abandoned carts and send weekly reports via Gmail and Sheets
Quick overview This template automates Shopify abandoned cart recovery with a 3-email Gmail sequence, tracks recoveries in Google Sheets via Shopify “order paid” webhooks, and sends a weekly HTML performance report every Monday using data aggregated from the same spreadsheet. How it works Receives a Shopify “checkout created” webhook, verifies the checkout includes an email address, and skips customers who already have an active recovery sequence logged in Google Sheets. Logs the abandoned checkout details to Google Sheets and waits one hour before checking Shopify Orders for a paid purchase by the same email. If no paid order exists, sends the first recovery email via Gmail and updates the Google Sheets row to mark Email 1 as sent. After another 23 hours, checks Shopify Orders again and, if still unpaid, sends the second recovery email via Gmail and updates Google Sheets. After another 48 hours, checks Shopify Orders again and, if still unpaid, creates a unique one-time Shopify discount (price rule + discount code) and sends the third email via Gmail, then stores the discount code and Email 3 status in Google Sheets. Receives a Shopify “order paid” webhook, looks up the customer i