Browse 159,125 AI agents

By Ashish Agarwal

Quick Overview This workflow checks SPF, DKIM, DMARC, and MX DNS records for a list of domains using Google Public DNS over HTTPS, compares the results to the previous run, and sends a Telegram message only when problems appear, get fixed, or records change. How it works Runs daily at 8:00 or on-demand via a manual test trigger. Reads a comma-separated list of domains (optionally with DKIM selectors) and builds DNS queries for MX, SPF (TXT), DMARC (TXT), and each DKIM selector (TXT). Calls Google Public DNS over HTTPS (dns.google/resolve) to resolve each requested record, retrying failed requests and treating unresolved lookups as unknown rather than missing. Evaluates each domain’s responses to flag issues such as missing/unsafe SPF, missing or weak DMARC settings, missing/revoked DKIM selectors, and missing MX. Compares current results with stored results from the last scheduled run to generate a change-only report (new issues, fixed issues, and edited record values), while manual runs produce a full report. Sends the compiled alert message to a Telegram chat. Setup Add your domains in the domain list field (comma-separated) and include any DKIM selectors after a colon, for example: example.com, mycompany.com:google|selector1. Create a Telegram bot, add the Telegram credential in n8n, and set the target chat ID in the Telegram send message step. Adjust the schedule time if needed, then run a manual test to verify the report before activating the workflow. An n8n automation workflow template by Ashish Agarwal.

By iamvaar

Quick overview Youtube Video :https://youtu.be/4S5f9Cc8zdQ?si=NT9Te6CLndH6f5S0 This workflow pulls webinar engagement and CRM context from Google Sheets, uses Google Gemini to classify each attendee’s buying intent, and writes qualified lead logs, sales tasks, and follow-up schedules back to Google Sheets, then posts a run summary to Slack. How it works Runs manually to start a webinar routing run. Reads webinar configuration, registrants, attendance, poll responses, questions, CRM contacts, routing rules, follow-up sequences, and an exclusion list from a Google Sheets spreadsheet. Merges these inputs into one normalized attendee profile per email, including engagement metrics, inferred buying signals, and exclusion flags. Sends each attendee profile plus the routing rules to Google Gemini and parses a structured classification (segment, intent score, recommended task type, sequence, and messaging hints). Applies guardrails and fallbacks (for competitors, customers, open deals, no-shows, or AI errors) and appends the final routing decision to the Qualified_Leads_Log sheet. Creates task records for routed leads that require human action and appends them to the Sales_Tasks sheet. Expands each lead’s assigned follow-up sequence into scheduled outreach steps and appends them to the Followup_Queue sheet. Builds a run summary with segment counts and top active buyers and posts it to a Slack channel. Setup Create a Google Sheets service-account credential in n8n, share the target spreadsheet with the service account email, and set the spreadsheet ID used by the workflow. Ensure the spreadsheet contains the expected tabs: Webinar_Config, Registrants, Attendance, Poll_Responses, Questions, CRM_Contacts, Routing_Rules, Followup_Sequences, Exclusion_List, Qualified_Leads_Log, Sales_Tasks, and Followup_Queue. Add a Google Gemini (PaLM) API credential for the intent-classification step. Add a Slack OAuth credential and select the channel where the run summary message is posted. An n8n automation workflow template by iamvaar.

By iamvaar

Quick overview This workflow receives Sentry issue alert webhooks, gathers related context from Sentry, GitHub, and a Postgres incident database, then uses Google Gemini to generate a structured incident investigation report, saves it back to Postgres, and posts a summary to Slack. How it works Receives a POST webhook from Sentry when an issue alert fires and normalizes the payload into a consistent incident context (issue ID, title, environment, and links). Checks Postgres to see if an investigation record already exists for the same Sentry issue ID and proceeds only if it is new. Fetches the latest issue details from Sentry and retrieves recent commits from the configured GitHub repository. Searches Postgres for up to 10 similar historical incidents based on the current issue title and recent incident reports. Bundles the Sentry issue data, GitHub commit context, and historical incidents and sends the evidence to Google Gemini to produce a JSON investigation report with severity, hypotheses, and recommended actions. Validates and scores the AI output, then upserts the full investigation (evidence and report) into Postgres. Posts an incident summary message to a Slack channel with severity, confidence, and a link back to the Sentry issue. Setup Configure your Sentry integration to send issue alert webhooks to this workflow’s webhook URL and ensure the payload includes a Sentry issue ID. Add Sentry API credentials in n8n so the workflow can fetch issue details. Add GitHub API credentials and update the repository URL/owner/name used to fetch recent commits. Set up a Postgres database with an incident_investigations table matching the fields used in the SELECT and INSERT/UPSERT queries, then add your Postgres credentials in n8n. Add a Google Gemini (PaLM) API credential for the chat model used by the AI agent. Add Slack OAuth credentials and set the target channel for posting the incident summary. An n8n automation workflow template by iamvaar.

By Hugo

Quick overview This workflow monitors a Google Sheets jobs tracker and, based on each row’s stage, generates quote, invoice, or receipt PDFs via Koutei and emails them with Gmail, while also sending overdue invoice reminders and writing any validation or delivery issues back to the sheet. How it works Runs on a manual trigger, every 30 minutes, and every morning at 9:00 to handle reminders. Reads all rows from a specified Google Sheets tab and evaluates each row’s stage and required fields to decide what action is needed. For rows requesting a document, marks the row as “Sending…” to prevent duplicate sends, then prepares the appropriate payload for Koutei (quote, deposit invoice, balance invoice, or receipt). Validates the document data with Koutei and, if valid, requests the final PDF from Koutei using an idempotency key to avoid duplicate document creation on retries. Emails the generated PDF via Gmail (to the owner in preview mode, or the client in final mode) and updates the Google Sheets row with the new stage, totals, due date, email ID, and other tracking fields. On the daily reminder run, finds overdue deposit or balance invoices, re-downloads the original sent invoice email attachment from Gmail, and emails a reminder with the same PDF while updating the row’s reminder tracking fields. When validation, PDF generation, emailing, or sheet updates fail, writes an actionable status note back to the relevant sheet row and emails the owner with any new non-waiting issues. Setup Create or copy a Google Sheets job sheet with the required columns (including job_id, stage, status, due_date, email_id, reminded_on, made_in, and doc_date) and set the sheet URL and tab name in the workflow settings. Add Google Sheets OAuth2 credentials and Gmail OAuth2 credentials for the account that reads/updates the sheet and sends emails. Create a Koutei account and API key, then configure an HTTP Header Auth credential with Authorization: Bearer and confirm the Koutei base URL in settings. Fill in workflow settings such as owner email, seller/business details, currency, deposit percent, payment terms, and reminder controls (on/off and interval). Start in mode = preview to send watermarked PDFs to the owner, then switch to mode = final before activating the workflow schedules for live client delivery. An n8n automation workflow template by Hugo.

By Gaetano Castaldo

Quick overview This workflow reads Aruba “Hai ricevuto una nuova fattura elettronica” email notices via IMAP, extracts key invoice details into an n8n data table, and on a monthly schedule (or via webhook) generates an Excel report and uploads it to Dropbox, with email alerts for parsing failures or workflow errors. How it works Polls an IMAP mailbox for Aruba e-invoice notice emails matching the subject filter and keeps track of the last processed message. Parses each email’s raw content to extract supplier, invoice number, document date, document type, totals, and the receipt timestamp (Europe/Rome), and derives a monthly key (yyyy.MM). Upserts successfully parsed invoices into an n8n data table using a unique key to prevent duplicates. Sends a Gmail email notification if a notice can’t be parsed so you can review and update the parsing logic. On the 1st of each month at 07:10 (or when called via an authenticated webhook with a target month), selects the month to consolidate and prepares the Dropbox destination path. Reads all stored invoices from the data table, filters them to the selected month, calculates totals (treating credit notes as negative), converts the rows to an Excel file, and uploads it to Dropbox. If the workflow execution errors, sends a Gmail email with the last executed step and a link to the failed n8n execution. Setup Create an IMAP credential for the mailbox that receives Aruba notices and confirm the email filter (subject and SINCE date) matches your inbox history. Create an n8n data table with the expected columns (chiave, fornitore, numero, dataDocumento, tipo, totale, nettoAPagare, dataRicezione, meseRicezione) and select it in both data table steps. Add a Dropbox OAuth2 credential and set the base folder path used to store monthly Excel files. Add a Gmail credential and replace the recipient address (you@example.com) used for the parsing and error alert emails. If you use the on-demand rebuild endpoint, configure the webhook Header Auth credential and call the webhook URL with a JSON body like {"mese":"2026.10"}. Requirements Aruba's e-invoicing service with email notices enabled (usually delivered to your PEC), an n8n version with data tables, and Dropbox and Gmail accounts. Customization Swap Dropbox for Google Drive or OneDrive in the last two nodes, or change the SINCE date in the IMAP trigger options to import older notices. Additional info For an Aruba PEC mailbox use host imaps.pec.aruba.it, port 993, SSL; with two-step verification you need the app password for mail clients. The mailbox is never marked as read. Credit notes count as negative in the monthly total. Foreign invoices (TD17) don't go through Aruba and won't appear. Field names are in Italian on purpose: they mirror Aruba's notice and the columns an Italian accountant expects. An n8n automation workflow template by Gaetano Castaldo.

By Harpreet Singh

Quick overview This workflow let customers book, check, cancel and reschedule appointments in one WhatsApp chat, with no app and no booking page, syncing availability and changes to Google Calendar and logging every action to Google Sheets. How it works A customer messages your WhatsApp Business number and replies with a menu number: 1 Book, 2 My appointments, 3 Cancel, 4 Reschedule. The bot collects name, mobile, date and time, then checks opening hours and Google Calendar. A free slot becomes a calendar event. A taken slot gets alternative times. Each appointment includes a protected break (default 50 + 10 minutes). Customers only see and change appointments linked to their own WhatsApp number. Every booking, cancellation and reschedule is logged in Google Sheets. Setup Create a Meta WhatsApp Business Cloud app and add its credentials to the trigger and WhatsApp nodes. Connect Google Calendar and Google Sheets. In your sheet, create a tab named Appointments with this header row: S.NO, Timestamp, Booking ID, Status, Name, Mobile/Contact No., Start, End, Start ISO, End ISO, Calendar Event ID, WhatsApp Chat ID, Action. Open Configure Appointment Settings and enter your calendar ID, sheet ID, timezone and hours. Publish the workflow (it needs public HTTPS), then send /start to your number. Test with the published workflow, not manual runs, and use a separate test calendar first. Requirements WhatsApp Business Cloud API (Meta developer app) Google Calendar and Google Sheets accounts An n8n instance reachable over HTTPS (n8n Cloud or self-hosted) Customization How to customize the workflow Change opening hours, appointment length and break time in the settings node. Chat sessions live in workflow static data, so use a single-worker n8n. Two customers requesting the same slot at the same moment can still double-book, because there is no locking. Need help customizing? Built by Automexa. For custom setup or changes (other hours and timezones, reminders, CRM or payment integrations), email harryin09@gmail.com or message +91-98157-55575 on WhatsApp or Telegram. Additional info 4. Problem it solves Small businesses lose time and bookings to the "what time works for you?" back-and-forth. Customers already message on WhatsApp, but someone has to read each message, check the calendar, reply, and update a spreadsheet by hand. Slots get missed after hours, and cancellations and changes create more chat. This workflow turns that chat into a self-service booking flow. Customers get instant answers at any hour, your calendar stays the single source of truth, and Google Sheets keeps an audit log of every change. 5. Use cases Clinics and therapists:** patients book and move consultations by WhatsApp, with a protected break between sessions. Salons and barbers:** clients book a chair without calling, and cancellations free the slot right away. Coaches and consultants:** discovery calls and sessions land straight on your Google Calendar. Tutors and trainers:** students reschedule lessons themselves. Repair and service desks:** customers pick an inspection slot and see their upcoming visits. Any freelancer or agency:** put a WhatsApp booking number on a business card or Instagram bio, with nothing to host. 6. Why it stands out /USP No AI model and no AI costs.** Booking logic is deterministic, so behaviour is predictable. No third-party WhatsApp platform.** It uses Meta's WhatsApp Business Cloud API directly. Full lifecycle in one template:** book, view, cancel and reschedule, not just booking or reminders. Protected breaks* and *alternative slot suggestions** when a time is taken. Ownership checks:** a customer can only see and change appointments linked to their own WhatsApp number. Audit trail** in Google Sheets for every booking, cancellation and reschedule. whatsapp, whatsapp business, appointment scheduling, booking bot, google calendar, google sheets, reschedule, cancel booking, chatbot, small business, clinic, salon, no-code, meta cloud api Support, Sales , Personal Productivity. An n8n automation workflow template by Harpreet Singh.

By Rahul Joshi

Quick overview This workflow collects back-in-stock waitlist signups for Shopify product variants, stores them in Google Sheets, and sends FIFO restock notifications in stock-based waves via WhatsApp Business Cloud or Gmail with time-limited Shopify discount codes, then posts wave summaries to Slack and marks conversions when Shopify orders. How it works Receives a POST webhook from your product page with a shopper’s variant ID, contact details, channel preference, and consent. Looks up the product variant in Shopify and checks Google Sheets to validate consent/contact info, detect duplicates, and decide whether to join the waitlist, return an “in stock” message, or reject the request. Appends valid signups to a Google Sheets waitlist and sends a confirmation message via WhatsApp Business Cloud or Gmail, then returns the shopper’s queue position in the webhook response. Triggers on Shopify inventory level increases and on an hourly schedule to find variants with waiting shoppers, expire previously notified entries whose offer window has ended, and fetch live inventory for those variants from Shopify. Plans a FIFO notification wave sized to available stock (including a configurable multiplier and cap), creates a time-limited variant-specific discount code in Shopify, and sends each recipient their back-in-stock message via WhatsApp Business Cloud or Gmail. Updates Google Sheets to mark recipients as notified (including code and expiry) and posts a wave summary message to a Slack channel. Triggers on Shopify order creation, matches orders back to notified waitlist entries by variant plus email/phone/discount code, and updates Google Sheets to mark matched entries as converted. Setup Add Shopify admin API access (custom app token or header auth) with permissions to read products/inventory and create discounts, and connect Shopify triggers for inventory_levels/update and orders/create. Connect Google Sheets, Gmail, Slack, and WhatsApp Business Cloud credentials, and set the WhatsApp Phone Number ID. Replace placeholders for your Shopify store domain, Google Sheet ID (with a “Waitlist” tab and required columns), Slack channel ID, and storefront URL in the workflow. Publish the signup webhook URL in your product page “notify me” form and send variant_id, email or phone, channel, and consent in the POST body. Review and adjust wave settings (multiplier, max wave size, discount percentage, and expiry window) to fit your restock strategy. An n8n automation workflow template by Rahul Joshi.

By Invoice Ledger

Quick overview This workflow lets you upload a single PDF invoice via an n8n Form, extracts the PDF text, parses common invoice fields (supplier, dates, totals, VAT, currency) using built-in code logic, and returns the detected fields and checks as a JSON response. How it works Receives an uploaded invoice PDF through an n8n Form trigger. Applies parsing settings like date order and a fallback default currency. Selects the uploaded file from the form submission and standardizes it into a binary field for processing. Extracts text from the PDF using n8n’s built-in PDF text extraction. Parses the text to identify invoice metadata (supplier, invoice number, invoice/due dates, currency, net/VAT/gross totals) and validates that net + VAT matches the total. Builds a human-readable summary plus a CSV-formatted ledger row and returns the full result as a JSON response to the form submission. Setup Run the workflow in n8n and open the generated form URL for the “read-one-invoice” path. Upload a PDF invoice that contains a readable text layer (scanned/image-only PDFs may not extract text). Optionally adjust dateOrder and defaultCurrency in the Set Default Parameters node to match your invoice formats. No credentials, API keys or AI models are needed, and the workflow saves no files. Requirements An n8n instance with the Form Trigger node (self-hosted or Cloud) PDF invoices with a text layer (no OCR for scans or photos) Customization Change dateOrder (auto, dmy or mdy) and defaultCurrency in the Set Default Parameters node Add or change extracted fields in the Parse Invoice Data code node. An n8n automation workflow template by Invoice Ledger.

By Oneclick AI Squad

Quick overview This workflow exposes a webhook that accepts an OpenAPI spec (inline or via URL), optionally fetches the spec, sends it to an external AI design endpoint, optionally validates and stores the generated design via HTTP APIs, then returns a packaged n8n workflow JSON and documentation. How it works Receives a POST request via an n8n webhook containing an OpenAPI specification or an OpenAPI URL plus generation preferences. Validates the incoming payload, extracts context like workflow name and auth preference, and prepares URLs used for downstream HTTP calls. Calls an external HTTP endpoint to fetch the OpenAPI document when a spec URL is provided (and continues even if the fetch fails). Sends the prepared context to an external AI design HTTP endpoint to generate a proposed n8n workflow structure. Calls external HTTP endpoints to validate the generated workflow design and to store/register the generated integration. Assembles a final response package with status flags, documentation, and a generated workflow JSON skeleton, then returns it to the webhook caller with an appropriate HTTP status code. Setup Configure where the workflow should send requests by replacing the placeholder httpbin.org URLs in the validation code with your real OpenAPI fetcher, AI workflow designer, validator, and storage endpoints. If your external endpoints require authentication, add the required credentials/headers to the HTTP Request steps. Activate the workflow and copy the production webhook URL, then configure your client to POST openApiSpec or openApiUrl along with optional fields like workflowName and preferredAuth. An n8n automation workflow template by Oneclick AI Squad.

By DataDrifter

Quick overview This workflow runs on schedules to invoice and chase unpaid WooCommerce on-hold orders in WordPress using Invoice Ninja, tracking each order in an n8n Data Table to avoid duplicates, sending reminders and optional Telegram alerts, and delivering a daily email report via SMTP. How it works Runs every hour and every day at 08:00 using scheduled triggers. Validates your chase settings, then uses the Invoice Ninja API and WooCommerce REST API to confirm connectivity and determine whether to run the hourly invoicing path or the daily chasing path. On the hourly run, fetches WooCommerce orders with status on-hold, filters to selected payment methods, skips orders already logged in the n8n Data Table, and records newly claimed orders for tracking. Creates or matches the customer in Invoice Ninja, builds an invoice from WooCommerce line items (including shipping, fees, and taxes), verifies the Invoice Ninja total matches the WooCommerce order total, and emails the invoice via Invoice Ninja. Adds an order note in WooCommerce with the Invoice Ninja invoice number and updates the tracking row to mark the order as invoiced, or records a failure reason if any invoicing step fails. On the daily run, loads all tracked invoiced orders, checks each Invoice Ninja invoice and its WooCommerce order status, then releases fully paid orders to processing or stops chasing if the invoice/order was changed externally. For overdue invoices, sends an Invoice Ninja reminder email, optionally sends a Telegram owner alert, and optionally voids the invoice and cancels the WooCommerce order when the configured cancel day is reached. Sends a daily SMTP email report summarizing newly invoiced orders, payments, overdue status, cancellations, and any errors that require attention. Setup Create an n8n Data Table named dd_in_chase with the columns used by the workflow (for example order_id, order_number, state, currency, order_total, due_date, invoice_id, invoice_number, amount_paid, step_a_at, step_b_at, step_c_at, last_error, invoiced_at, closed_at). Add credentials for WooCommerce (read/write), Invoice Ninja v5, SMTP (for the run failure and daily report emails), and Telegram (optional, for owner alerts). Update the Chase settings values, including your WordPress store URL, Invoice Ninja base URL, payment method IDs to chase, due/reminder/alert/cancel day thresholds, report email addresses, and optional telegram_chat_id. If you enable cancellation, set cancel_unpaid_orders to true and confirm your reminder and cancel day settings reflect your policy, since cancelled orders and voided invoices are not automatically restored. Requirements WordPress with WooCommerce and a REST API key with Read/Write permission (tested on WooCommerce 11.2.1, WordPress 7.1.3) Invoice Ninja v5 with an API token and its email set up to send invoices (tested on 5.13.22, self-hosted) Self-hosted n8n with data tables (tested on 2.33.7) An SMTP credential for the report and failure emails A Telegram bot, if you want the owner alerts Customization payment_methods takes any WooCommerce payment method id that leaves orders on hold due_days, reminder_day, owner_alert_day and cancel_day set the timetable, counted in whole days Leave telegram_chat_id empty to switch the owner alerts off Cancelling on day C stays off until you set cancel_unpaid_orders to true Additional info Full guide, free to read: https://datadrifter.io/chase-unpaid-woocommerce-orders-wordpress-invoice-ninja/ After purchase you download the workflow from your DataDrifter account. That copy carries the full setup notes on the canvas: the credentials, the data table columns and every setting. Email support and updates to this version are included. It does not take payments: your customer pays through Invoice Ninja's invoice page or however you have set it up there. Invoices and reminders go out through Invoice Ninja, with Invoice Ninja's own mail settings. An n8n automation workflow template by DataDrifter.

By Mohamed Zaghloul

Quick overview Checks competitor product pages daily, reads price and stock from structured data (Gemini only when needed, with a text fallback), logs every check to Google Sheets and pings Slack only on real price moves or stock changes. Includes dedupe, configurable thresholds, an Errors tab and a run summary. How it works A daily schedule reads your Watchlist and History tabs, drops duplicate or inactive rows and skips URLs checked in the last few hours. Each page is checked one at a time with a polite pause: a keyless demo extractor API first, then a direct page fetch that reads JSON-LD, meta tags and microdata. Pages without structured data go to Gemini with a strict schema; if Gemini fails, the price is read from the page text instead. Each result is compared with the last known price. Slack is alerted only when the price moves by at least your threshold or stock changes; low-confidence reads are logged, not alerted. Every check is appended to History. Failed checks and Sheets/Slack errors go to an Errors tab, and a short run summary is posted to Slack. Setup Create a Google Sheet with Watchlist, History and Errors tabs (headers are listed in the yellow note). In the Config node set sheetId and slackChannelId; optionally adjust minChangePct, minConfidence, minHoursBetweenChecks and runSummary. Add Google Sheets, Slack and Google Gemini credentials. Execute once to record a baseline, then activate. Save the workflow and verify the Config node holds your own sheetId and slackChannelId before activating the trigger. Additional info Built with built-in nodes only, tested on n8n 2.43. No credentials or real IDs included. The demo extractor endpoint needs no key (10 pages a day). The Pro version adds undercut alerts with suggested reprices, room-to-raise and market rank, Apify for JavaScript-heavy shops, a Latest dashboard tab and a weekly summary: https://mohabaha0.gumroad.com/l/price-monitor-pro. An n8n automation workflow template by Mohamed Zaghloul.

By Muhammad Bilal

Quick overview This workflow uses WhatsApp Business Cloud, OpenAI, Supabase, and PostgreSQL to let patients check lab report status or receive a ready report PDF in English, Urdu, or Roman Urdu, while enforcing access control by matching the sender’s WhatsApp number to an authorized number stored with each report. How it works Triggers when a new WhatsApp text message is received and ignores non-text or invalid messages. Loads the sender’s recent session state from Supabase and uses OpenAI to classify intent (status check, send PDF, or general query), extract any Report ID or full patient name, and detect the reply language. Validates and normalizes the identifier (Report ID or full patient name), optionally reusing a recently verified report context for short follow-ups, then looks up matching report records in Supabase. Applies access control by verifying the incoming WhatsApp number matches the report’s stored authorized_whatsapp value, and routes denied or ambiguous/missing-identifier cases to a clarification reply. For authorized status checks, replies on WhatsApp with “ready” or “pending” messaging based on the report_status field. For authorized PDF requests with a ready report and a PDF URL, validates the PDF host, downloads the PDF over HTTPS, and sends it back to the same WhatsApp number as a document. For general questions, uses OpenAI with PostgreSQL chat memory to draft a short WhatsApp reply in the user’s language. Setup Connect credentials for WhatsApp Trigger/WhatsApp Business Cloud, OpenAI, Supabase, and PostgreSQL (and ensure Supabase and PostgreSQL point to the same database/schema used by the workflow). Create the required tables in your database (lab_reports, patient_session_state, and the PostgreSQL chat memory tables) and ensure lab staff populate authorized_whatsapp for each report in international digits-only format. Replace REPLACE_WITH_WHATSAPP_PHONE_NUMBER_ID in both WhatsApp send steps with your WhatsApp Phone Number ID. Set REPLACE_WITH_REPORT_STORAGE_HOST in the PDF validation step to your exact HTTPS storage hostname and ensure report_pdf_url values are short-lived direct HTTPS links with no redirects. Requirements n8n, WhatsApp Business Cloud, OpenAI, Supabase and PostgreSQL credentials, configured report/session tables, registered patient WhatsApp numbers and private HTTPS report PDFs. Customization Customize lab branding, AI models, reply languages, message wording, report-ID format, database mappings, session expiry and trusted PDF storage host. Additional info Help patients check report status and receive ready PDFs directly on WhatsApp, reducing repetitive reception queries. Supports English, Urdu and Roman Urdu, with a registered-number check before releasing report details. Adapt the workflow to your laboratory’s database and test with sample records before handling real patient information. An n8n automation workflow template by Muhammad Bilal.

By Shuo Yuan

Quick overview This workflow runs daily to pull YouTube trending videos and keyword-based search results via the YouTube Data API, deduplicates them in an n8n Data Table, scores breakout potential with DeepSeek, and sends threshold-based breakout alerts and a ranked digest to Telegram. How it works Runs every day at 08:00 on a schedule. Fetches the current YouTube “most popular” chart for the configured region and searches YouTube for videos matching your niche keywords from the last 24 hours, then hydrates those search results with video statistics. Merges and deduplicates both result sets by video ID and calculates momentum metrics like views per hour, engagement rate, and a deterministic base score. Skips any video already recorded in an n8n Data Table, then upserts newly found videos into the Data Table as “seen” for future deduplication. Sends the new videos to DeepSeek to generate an LLM breakout score and reason (falling back to the deterministic score if the DeepSeek request fails) and calculates a blended final score. Sends an immediate Telegram message for videos at or above the alert threshold, and aggregates mid-range videos into a ranked daily Telegram digest while ignoring anything below the digest threshold. Setup Create a Google Cloud API key with YouTube Data API v3 enabled and add it to n8n as an HTTP Query Auth credential (parameter name key) used by the YouTube HTTP Request nodes. Create a DeepSeek API key and add it to n8n as an HTTP Header Auth credential (for example, Authorization: Bearer YOUR_DEEPSEEK_KEY). Create a Telegram bot, add Telegram credentials in n8n, and replace YOUR_TELEGRAM_CHAT_ID in both Telegram send steps. Create an n8n Data Table with columns for video_id, title, channel, url, source, first_views, and first_seen, then replace YOUR_DATA_TABLE_ID in both Data Table steps. Update the monitoring values (region code, niche keywords, digest size, and score thresholds) in the workflow’s configuration step before activating. An n8n automation workflow template by Shuo Yuan.

By Olly McBride

Quick Overview This workflow listens for meal photos sent to a Telegram bot, uses Google Gemini Vision to estimate the dish and nutrition, logs each entry to a Google Sheets food diary, and replies in Telegram with the estimate plus the sender’s running totals for the day. How it works Triggers when a new Telegram message is received by your bot. Checks whether the message includes a photo and replies asking for a meal photo if none is provided. Downloads the largest available version of the Telegram photo and sends it (plus any caption) to Google Gemini Vision to return structured nutrition estimates. Stops and replies in Telegram if Gemini indicates the image is not food. Appends the meal details (date/time, user info, dish, calories, macros, confidence, notes) to a Meals sheet in Google Sheets and then reads back today’s rows for that date. Totals today’s calories and macros for the same Telegram user and replies with the per-meal estimate and daily totals. Setup Create a Telegram bot with @BotFather and add its token as a Telegram credential in n8n. Add a Google Gemini (PaLM) API credential with an API key that can access the Gemini vision model. Connect a Google Sheets OAuth2 credential and replace YOUR_SHEET_ID with your spreadsheet ID in both Google Sheets steps. Create a Google Sheet tab named Meals with columns matching the workflow fields (date, time, user_id, user_name, dish, portion, calories_kcal, protein_g, carbs_g, fat_g, confidence, notes). Set the workflow timezone in n8n so the “today” totals match your local day, then activate the workflow. An n8n automation workflow template by Olly McBride.

By Kishan Makani

Quick overview This workflow receives signup, activation, and upgrade events via a webhook, then uses Brevo (Sendinblue) to manage contact attributes/lists and send a 7-email onboarding sequence for free users, stopping the sequence and moving contacts to a Pro list when they upgrade. How it works Receives a POST webhook event (Clerk user.created or a backend { event, email, firstname, contactId } payload) on the your-product-onboarding path. Normalizes the incoming payload into a consistent event, email, and firstname structure and routes processing based on signup, activated, or upgrade_pro. On signup, upserts the contact in Brevo with onboarding attributes (for example PLAN=FREE and IS_ACTIVATED=false), adds the contact to Brevo list 6, and sends the Welcome email. After each wait period, re-fetches the contact from Brevo and exits the sequence if PLAN=PRO by removing them from list 6 and adding them to list 3. If the contact remains on the free plan, continues sending the remaining onboarding emails with delays between them, choosing different branches depending on the Brevo IS_ACTIVATED flag. On activated, updates the Brevo contact attribute IS_ACTIVATED=true so subsequent checks can fast-forward to the later part of the sequence. On upgrade_pro, updates the Brevo contact attribute PLAN=PRO and immediately moves the contact from list 6 to list 3 so any waiting executions stop at the next plan check. After the final email, removes the contact from list 6 and adds them to Brevo list 5 (Inactive) to mark the free onboarding sequence complete. Setup Add a Brevo (Sendinblue) API credential and select it in all Brevo and HTTP Request nodes that call the Brevo v3 API. In Brevo, create or confirm the list IDs used by the workflow (6 = New Signup, 3 = Pro Users, 5 = Inactive) or update the list IDs in the Brevo API URLs. In Brevo, ensure your contact attributes exist (at least PLAN, IS_ACTIVATED, FIRSTNAME, PRODUCT_NAME, and CLERK_ID). Update the transactional email sender address/name and any links or branding in the HTML templates to match your product. Copy the production webhook URL for your-product-onboarding and configure it in Clerk (for user.created) and/or your backend event sender to POST the supported payload shape. An n8n automation workflow template by Kishan Makani.

By Ali Abdullah

Quick overview This workflow scans a Google Drive folder of contract PDFs on a weekly schedule, extracts key renewal terms from new documents using the Gemini API, stores and updates a contract registry in Google Sheets, and sends renewal alerts via Gmail and Slack plus a weekly digest email. How it works Runs weekly (or manually for testing) and loads configuration values like Drive folder ID, Google Sheet ID, alert email, and Slack channel. Searches Google Drive for PDFs in the target folder and reads the current contract registry from Google Sheets. Compares Drive files to the registry to identify new contracts, then downloads each new PDF, extracts its text, and calls the Gemini API to extract structured contract terms. Appends extracted contract records to the Google Sheets Registry and combines new and existing contracts into a single list. Calculates days-to-renewal and assigns urgency tiers (90/60/30/notice_passed) with risk flags for short-notice auto-renewals, then filters contracts that have entered a new alert tier since the last run. For each alert due, builds a one-page renewal briefing, emails it via Gmail, posts a Slack notification, and updates the registry to record the last alerted tier. Builds a portfolio summary of tracked contracts, new contracts, alerts sent, and items needing review, emails the weekly digest via Gmail, and logs the run to a RunLog sheet in Google Sheets. Setup Create a Google Sheet with a Registry tab containing columns: file_id, vendor_name, contract_title, start_date, end_date, auto_renewal, notice_period_days, annual_value, currency, termination_penalty, key_contact, last_alert_tier, status, added_date, and a RunLog tab with date, contracts_scanned, new_contracts, alerts_sent. Add Google Drive, Google Sheets, Gmail, and Slack credentials in n8n, and set a Slack channel to receive renewal notifications. Get a Gemini API key (Google AI Studio) and fill in the Workflow Configuration values for geminiApiKey, driveFolderId, registrySheetId, alertEmail, slackChannelId, and maxCharsPerContract. Put your contract PDFs into the configured Google Drive folder and run the workflow once manually to populate the registry and validate alerts and digest emails. An n8n automation workflow template by Ali Abdullah.

By EcomOpsKits

Quick overview Compare price and availability changes for variants of one known public Shopify product. Save the latest complete report in an n8n Data Table and use it on the next manual run. This free workflow uses a paid, publisher-owned RapidAPI service. How it works A manual execution validates the product, currency, date and explicit spending consent. It reads the latest complete report from a Data Table, reserves one attempt and the request's recovery key, and verifies that reservation before calling the API once. It validates the full response, saves it together with the updated pilot state and reads it back before returning success. The first success establishes a baseline; later successes include variant-level changes. Errors preserve the prior report. No scheduled monitoring or alerts are included. Only one execution and one workflow copy may use the history row. Setup Use n8n2.40.7 or a compatible release supporting Data Table create/get/upsert. Enter a known public product URL, its expected currency and a stop date within 14 days. Add your RapidAPI key as an HTTP Header Auth credential named x-rapidapi-key and select it on the HTTP node. Review current pricing and the complete setup note before enabling spending consent. Run one execution at a time, one workflow copy, without manual history edits. Stop at 14 reserved attempts or the saved date; follow the note's exact recovery procedure. Additional info EcomOpsKits publishes the linked paid API: https://rapidapi.com/ecomclosekit/api/shopify-variant-price-and-availability-diff The USD0.01/request tariff is the October4 publication snapshot, not a current buyer quote; bandwidth/other charges and n8n hosting are separate. Replays/errors may bill. The workflow counter is not a billing cap or concurrency lock. Full product URL/previous report data is transmitted to RapidAPI/Cloudflare/Apify; no retention period is promised. Only one public product/source/currency and 1–249variants are supported. This is a latest-report comparison pilot, without sales/inventory inference, currency conversion, schedules or alerts. Free direct Shopify JSON/code solutions are possible; this API is a convenience choice. On interruption/error before commit, inspect the saved row and prior execution. If recovery is appropriate, enable recoverPendingRequest and run the full workflow with the same credential/consumer. It reuses the exact saved body/key, consumes another slot and may bill. A cached provider error remains an error; recovery does not promise a fresh observation. An uncertain backend start may need provider reconciliation. Never use native Retry execution, partial Execute step on HTTP/save nodes, a fresh key or reset history to recover: these can bypass the reservation or create another billable request. After a successful commit, pending is already cleared; explicit recovery then refuses another call. Disable recovery only when deliberately starting a new observation. An n8n automation workflow template by EcomOpsKits.

By CleanScrape

Quick overview This workflow runs every Monday, scrapes the last 7 days of 1–2 star reviews from the App Store and Google Play via Apify, summarizes the main complaint themes with OpenAI, and posts a weekly digest to a Slack channel only when complaints exist. How it works Runs every Monday at 9:00 on a schedule trigger. Sends your App Store and Google Play app identifiers, country, rating filter (1–2 stars), and a 7-day lookback window to the Apify “App Store & Google Play Reviews Scraper” actor and retrieves the resulting review dataset. Aggregates the reviews into a single weekly payload, counting items per store and formatting up to 150 review lines with store, rating, version, and text for summarization. Stops if there are no matching reviews for the week. Uses OpenAI (gpt-5-mini) to produce a short Slack-ready digest listing 3–5 top complaint themes with estimated counts, a representative quote, and version callouts where relevant. Posts the digest to the selected Slack channel with a header showing total review count and the App Store vs Google Play breakdown. Setup Add an Apify credential (API token) and ensure the workflow can run the “cleanscrape/app-store-reviews-scraper” actor. Add an OpenAI API credential for the chat model used to summarize the reviews. Add a Slack credential with permission to post messages and make sure the target channel exists. Update the Settings values for your Google Play and App Store app links/IDs, store country, how many reviews to check, and the Slack channel name. Requirements Apify account. The Actor charges per review saved (about $0.20 per 1,000 reviews plus a small start fee); Apify's free plan includes monthly credit. OpenAI API key. Slack workspace and a channel for the digest. Customization Change the star ratings or the 7-day window in the Apify node's input. Check more reviews per run with reviewsToCheck in Settings. Send the digest to email, Microsoft Teams or Notion instead of Slack. Additional info The example Settings use the Strava app; replace them with your own app's links. Schedule times use the workflow's time zone. Made by CleanScrape, the developer of the Apify Actor used here. An n8n automation workflow template by CleanScrape.

By Andy

Quick overview Create a quotation draft from a request CSV and an approved price list, with unmatched or conflicting items held for review. Built for parts distributors and sales teams using exact SKUs. How it works Receives an n8n Form submission with two uploaded CSV files (request and price list) and a chosen delimiter. Validates that both uploads are UTF-8 .csv files within size limits and reads their contents as text. Parses both CSVs, enforces required headers, and builds a catalogue from the price list while flagging invalid rows and blocking duplicate SKUs. Validates each request line (line_id, quantity, unit) and matches it to exactly one case-sensitive SKU in the catalogue, holding unknown, blocked, duplicate, or unit-mismatched lines for review. Calculates unit prices and line totals for accepted lines, keeps separate totals per currency, and generates report.json plus quotation-draft.csv and review.csv. Packages the three files into a single ZIP and returns it as the form completion download with a status summary. Setup Import the workflow and run it from the editor to open the n8n Form trigger. Prepare two UTF-8 CSV files matching the required schemas (request: line_id, sku, quantity, unit; price list: sku, description, unit, unit_price, currency). Upload both CSVs in the form and select the delimiter that both files share (comma, semicolon, or tab). Submit the form and download quotation-review.zip. Inspect report.json and review.csv, resolve all reported issues, and check the accepted line totals before using the draft. A partial draft is not a complete offer. Requirements Tested on n8n 2.28.6. Built-in nodes only; no API credentials or paid services. Existing hosting costs apply. Both files must be UTF-8 CSVs using the same delimiter. Limits: 4,000,000 bytes per file, 1,000 request rows, 10,000 catalogue rows. Supported currencies: USD, EUR, GBP, THB, JPY, KWD. Customization Change the input files and delimiter in the form. Rename source headers to the documented schema. Validation changes require code edits and retesting. Additional info CSV-only: no Google Sheets connection, PDF extraction, tax calculation, or customer delivery. Unknown, duplicate, conflicting, and invalid items remain unpriced for human review. A partial draft is not a complete offer. Enable form authentication before publishing a production form. An n8n automation workflow template by Andy.

By James Mundy

Quick Overview This workflow takes a lead URL, uses Gaffa to extract contact details from the web page, and then creates or updates a HubSpot contact based on the extracted email. How it works Runs when you manually execute the workflow. Sets the lead URL and the CSS selector that defines which part of the page to parse. Builds a Gaffa request that defines a JSON schema for first name, last name, company, role, and email. Sends the request to Gaffa to parse the target web page and return the extracted contact fields. Upserts the contact in HubSpot using the extracted email and maps the other extracted fields to HubSpot contact properties. Setup Install the community node package @gaffa-dev/n8n-nodes-gaffa in your self-hosted n8n instance. Create and add a Gaffa API credential with your API key from gaffa.dev. Create a HubSpot private app with crm.objects.contacts read/write scopes and add its app token as HubSpot credentials. Update the lead URL (and optionally the selector) in the workflow settings before running it. An n8n automation workflow template by James Mundy.

By Jason Bullen

Quick overview This workflow runs a sample support-ticket triage in n8n and uses FirstHelm’s control plane APIs to log activity, evaluate communication constraints, and route high-urgency tickets for human approval while logging completion. How it works Starts when you manually execute the workflow in n8n. Creates a sample support ticket payload with customer, subject, urgency, and ticket ID. Sends a log event to FirstHelm (logActivity) to record that triage has started. Calls FirstHelm (evaluateConstraint) to check whether sending a resolution email to the customer is allowed under the configured constraints. If the ticket urgency is high, requests human approval via FirstHelm (requestApproval) and logs that the workflow is waiting for an operator decision. If the ticket urgency is not high, logs an auto-response email action to FirstHelm. Logs a final completion event to FirstHelm (logActivity) to mark the triage as finished. Setup Create a FirstHelm account and obtain a FirstHelm API key, then replace YOUR_FIRSTHELM_API_KEY in all HTTP requests. Set your FirstHelm agent_id by replacing YOUR_AGENT_ID in the request bodies. (Optional) Replace the sample ticket fields (customer, subject, urgency, ticket_id) with values from your real support system or upstream trigger. Requirements Free FirstHelm account (firsthelm.dev) + API key Customization Swap the sample ticket trigger for your own Gmail/Outlook/helpdesk node. An n8n automation workflow template by Jason Bullen.

By Siddharth Gupta

Quick Overview This workflow scrapes job listings from multiple company career sites, stores and updates them in Google Sheets, cleans and extracts job text from each job page, then uses Google Gemini and Groq (via LangChain) to generate LinkedIn-ready job posts that can be published through LinkedIn and reported via Telegram. How it works Triggers from a Telegram bot command or on a scheduled cron timetable. Scrapes job listings from multiple career sites (including TruGreen, SavATree, Perennial Services Group, Senske/UKG, Paylocity job boards, Breezy HR, and SilkRoad) and appends or updates new jobs in Google Sheets using Req ID as the key. Loads unprocessed jobs from Google Sheets, validates each record has an Original URL, and routes it to the correct brand-specific scraper based on the URL pattern. Fetches each job detail page, sanitizes the HTML into clean plain text, and writes the result back to Google Sheets with “Text created” and “Date Text Created” fields. For ad-hoc or scheduled posting, loads a job with cleaned text, validates the “Job Text” field is present, and prompts a LangChain agent using Google Gemini and Groq to draft a compliance-focused LinkedIn post. Publishes approved posts to a LinkedIn organization and logs the LinkedIn post URL, published status, post text, and publish date back into Google Sheets. Sends Telegram updates for process status and generates total, daily, and weekly posting reports from Google Sheets metrics. Setup Connect credentials for Google Sheets OAuth2, LinkedIn OAuth2 (with permission to post as your target organization), Telegram bot API, Groq API, and Google Gemini (PaLM) API. Create or select the Google Sheets spreadsheet and worksheet with the expected columns (for example: Req ID, Job title, Brand Name, City, State, Zip code, Address, Original URL, Job Text, Text created, Date Text Created, Published?, Post Link, Post text, Publish Date). Update the Google Sheets document ID, sheet/tab name, and any matching columns (Req ID and/or Original URL) to align with your spreadsheet. Set your Telegram chat IDs and configure the Telegram bot in BotFather, then start the bot and use the inline menu options to run scraping, cleaning, posting, or reporting. Confirm the LinkedIn organization ID used for posting matches your organization and that the workflow’s schedule times match your desired timezone and cadence. An n8n automation workflow template by Siddharth Gupta.

By starkAhmed43

An AI-powered application hosted on Hugging Face Spaces by starkAhmed43. Built with docker.

By cetiennec

Slides, exercise sheets and interactive spaces of my courses Hosted on Hugging Face Spaces by cetiennec. SDK: static.

By vllm-sr

Point at it, extract it, check it. A 0.25B encoder on CPU. Hosted on Hugging Face Spaces by vllm-sr. SDK: docker.

By mrfakename

Chat with Recursive's Flint coding model Hosted on Hugging Face Spaces by mrfakename. SDK: gradio.

By hugging-apps

Discover closed-form laws of nature from ≤10 data pairs Hosted on Hugging Face Spaces by hugging-apps. SDK: gradio.

By smirki

Expressive voice cloning that sighs, gasps and breaks Hosted on Hugging Face Spaces by smirki. SDK: gradio.

By samliumay

Inspect LLM-generated SQL before it reaches the database Hosted on Hugging Face Spaces by samliumay. SDK: docker.

By samliumay

A deliberately imperfect LLM bank assistant to pentest Hosted on Hugging Face Spaces by samliumay. SDK: docker.

By AlekseyCalvin

Run & Train Small LMs for Free w/ GGUF, PEFT & more! Hosted on Hugging Face Spaces by AlekseyCalvin. SDK: gradio.

By jbhati305

An AI-powered application hosted on Hugging Face Spaces by jbhati305. Built with static.

By Roman81

An AI-powered application hosted on Hugging Face Spaces by Roman81. Built with static.

By SabaPivot

An AI-powered application hosted on Hugging Face Spaces by SabaPivot. Built with static.

By hugging-apps

Small cognition models predict your choices, trial by trial Hosted on Hugging Face Spaces by hugging-apps. SDK: gradio.

By xal2077

Video generation with a synchronized soundtrack Hosted on Hugging Face Spaces by xal2077. SDK: static.

By sotinhoss

Compare three reference-guided manga colorizers Hosted on Hugging Face Spaces by sotinhoss. SDK: gradio.

By mirrash7

An AI-powered application hosted on Hugging Face Spaces by mirrash7. Built with docker.

By mioulin

Adversarial evaluation toolkit for frontier language models Hosted on Hugging Face Spaces by mioulin. SDK: gradio.

By spark-nlp

An AI-powered application hosted on Hugging Face Spaces by spark-nlp. Built with docker.

By wb-droid

An AI-powered application hosted on Hugging Face Spaces by wb-droid. Built with gradio.

By GeorgyVlasov

An AI-powered application hosted on Hugging Face Spaces by GeorgyVlasov. Built with gradio.

By sms07

An AI-powered application hosted on Hugging Face Spaces by sms07. Built with streamlit.

By joelniklaus

Which coding-agent harness should you use for your model? Hosted on Hugging Face Spaces by joelniklaus. SDK: docker.

By cyun9286

An AI-powered application hosted on Hugging Face Spaces by cyun9286. Built with gradio.

By CharlesW

Confucius4-TTS with optional reference transcription Hosted on Hugging Face Spaces by CharlesW. SDK: gradio.

By hugging-apps

Step into a live, steerable generated world Hosted on Hugging Face Spaces by hugging-apps. SDK: gradio.

By vllm-sr

Towards Open Multimodal Foundation Decision Models Hosted on Hugging Face Spaces by vllm-sr. SDK: static.