Browse 12,955 Workflows

By WeblineIndia

Quick overview This workflow monitors cancellation records in Notion, checks related payment-failure (dunning) history in Google Sheets to classify churn as involuntary or voluntary, logs each result to a churn log sheet, and then runs a monthly rollup that summarizes churn with Google Gemini and emails the report via Gmail. How it works Triggers every minute when a new cancellation event is detected in a Notion database. Normalizes the cancellation payload into a customer ID, cancellation date, and plan revenue, then looks up matching dunning history for that customer in Google Sheets. Calculates whether the dunning start date occurred before the cancellation and within a 60-day window. Classifies the cancellation as Involuntary when a valid dunning record exists, otherwise as Voluntary, and appends the churn event (including plan, dates, revenue, and notes) to a Google Sheets churn log. Runs on a monthly schedule, fetches all rows from the churn log in Google Sheets, and aggregates the prior month’s involuntary/voluntary counts and lost revenue. Sends the aggregated metrics to Google Gemini to generate a short JSON-formatted executive summary and emails the formatted HTML report through Gmail. Setup Connect your Notion credentials and select the cancellation database used by the Notion trigger. Connect your Google Sheets credentials and update the document/sheet IDs for both the dunning history lookup sheet and the churn classification log sheet. Ensure your dunning history sheet includes at least “Customer ID” and “Dunning Start Date” columns and your churn log sheet includes the output columns used for appending. Add a Google Gemini (PaLM) API credential for the LLM node and adjust the prompt/schema if you want different report fields. Connect your Gmail credentials and set the email recipients and subject/body content for the executive report. Additional info How To Customize Nodes Adjust Dunning Time Window:** Open the Validate Dunning Window code node and update diffDays <= 60 to your preferred window size (e.g., 30 or 45 days). Modify AI Prompt:** Select the Generate AI Narrative node to adjust the tone, language, or specific analytical questions answered in the summary. Change Schedule Interval:** Update the Trigger: Monthly Rollup schedule settings if you prefer weekly or quarterly summaries. Customize Email Design:** Edit the HTML block in Email Executive Report to match your company's branding, color palette, or logos. Add‑ons Stripe / Chargebee Integration:** Replace the Notion trigger with direct webhook listeners from payment providers to eliminate manual data entry. Slack / Microsoft Teams Alerts:** Add a messaging node after Log Churn Event to broadcast high-value cancellation alerts immediately. Automated Dunning Win-Back Workflows:** Route involuntary churn events into automated email sequences via Customer.io or HubSpot to retry failed cards. Use Case Examples Payment Failure Recovery Audit: Identify exact revenue amounts lost to expired or declined credit cards versus voluntary cancellations. SaaS Executive Board Reporting: Generate monthly automated AI summaries for leadership without manual spreadsheet consolidation. Product vs. Billing Issue Segmentation: Isolate churn caused by product dissatisfaction from churn caused by payment gateway issues. Customer Success Priority Routing: Trigger outreach tasks for high-MRR customers who experienced voluntary cancellations. Billing Gateway Performance Monitoring: Track trends in involuntary churn across different payment processors or regional currencies. (Note: There can be many more such use cases of this workflow depending on your specific business, payment stack, and retention strategies.) Troubleshooting Guide | Issue | Possible Cause | Solution | | --- | --- | --- | | Notion Trigger Not Firing | Invalid database ID or missing integration permissions in Notion. | Ensure the Notion integration is shared with your cancellation database and has active read permissions. | | Dunning Check Fails | Customer ID mismatch between Notion and Google Sheets. | Verify that the Customer ID format in Notion matches the Customer ID column in your dunning sheet. | | Code Node Date Errors (NaN) | Missing, invalid, or non-ISO date strings in the incoming payload. | Ensure Cancellation Date and Dunning Start Date are passed as standard ISO (YYYY-MM-DD) date strings. | | Gemini JSON Schema Validation Error | AI response failed to produce strict JSON matching the requested schema. | Confirm your Google Gemini API key is active and that the schema properties (report_title, summary) are unmodified. | | Gmail Report Not Delivered | Missing recipient email address or expired Gmail OAuth2 credentials. | Open the Email Executive Report node, specify a valid Send To email address, and re-authenticate your Gmail connection. | Need Help? Setting up automated financial metric pipelines and configuring LLM chains requires precise field mapping and robust error handling. If you need assistance configuring this workflow, customizing integrations or developing custom automation solutions for your business, contact WeblineIndia. Our expert team can help you build and scale tailored n8n workflows for your operations. An n8n automation workflow template by WeblineIndia.

By Faceless Channel OS

Quick overview This workflow lets you track expenses by sending messages or receipt photos to a Telegram bot, stores records in an n8n Data Table, and provides budget status, credit-card statement cycle summaries, due-date reminders, and monthly CSV exports back to Telegram. How it works Triggers when a new Telegram message arrives or every morning at 08:00 on a schedule. Parses the Telegram text or photo caption to detect amount, note, category, month, optional card tag (for payment method), and optional receipt photo file ID. If the message is an expense entry, saves it to the n8n Data Table and replies in Telegram with a confirmation plus current-month category budget progress and the relevant card statement total/close/due dates (if a card is used). If the message is a command, reads the sender’s expenses from the Data Table and returns either a month-by-category report with month-over-month comparison, a budget overview, or credit-card cycle/statement/due-date details in Telegram. If the command is /export, formats the selected month’s expenses as a CSV file and sends the CSV document to the Telegram chat. If the command is /undo, deletes the most recently created expense for that chat and confirms the removal in Telegram. On the daily schedule, scans all stored expenses to find chats with card statements due soon and sends Telegram reminders when the due date is within the configured reminder window. Setup Create a Telegram bot with @BotFather, add a Telegram API credential in n8n, and select it in each Telegram Trigger/Send node. Create an n8n Data Table named expenses with columns chat_id, category, note, month, spent_at, payment, receipt_file_id (string) and amount (number). Update the Config values for currency/locale/timezone, category keywords, monthly budgets, and your cards (tag, name, closingDay, dueDay) plus reminderDaysBefore. Activate the workflow and ensure your n8n instance is reachable via a public HTTPS URL so Telegram can deliver webhook updates to the Telegram trigger. Requirements n8n with Data Tables (n8n Cloud or self-hosted, tested on n8n 2.30) A Telegram bot token from @BotFather (free) A public HTTPS URL for the Telegram webhook (n8n Cloud, or self-hosted behind a tunnel or reverse proxy) No OpenAI or other paid API key needed Customization Add your own categories and keywords in Config (categoryKeywords); messages can also use #category tags Set a monthly budget per category in Config (budgets) Add as many credit cards as you like, each with its own closingDay and dueDay, and change reminderDaysBefore Change currency, locale and timezone (e.g. USD / en-US); turn off smallNumbersAreThousands if "50" should mean 50, not 50,000 Change the reminder time in the "Every morning 08:00" Schedule node Additional info Amounts like 50k, 1.2tr, 120.000 or 12.50 are parsed in code, so there is no AI cost per message. Each Telegram chat keeps its own data, so one bot can serve a family or a small team. Statement math handles short months (closing day 31 = last day of the month) and back-dated expenses ("@25/09"). Tested end-to-end on a real n8n server with 16 scenarios: adding expenses, budgets at 80% and over 100%, /cards, /budget, /report, /export to CSV, /undo and the morning due-date reminder. Only need simple tracking without cards and budgets? Use the free template "Track Telegram expenses with Data Tables and monthly reports". An n8n automation workflow template by Faceless Channel OS.

By Rahul Joshi

Quick overview This workflow runs daily and pulls Meta Ads account and ad insights from the Meta Graph API, detects spend/performance anomalies and creative fatigue, uses OpenAI (gpt-4o-mini) to propose fixes for flagged accounts, and posts either an alert or an all-clear message to Slack. How it works Runs every day at 9:00 AM (cron schedule). Loads your configured Meta ad accounts and generates the “yesterday” and 7-day lookback date window for each account. Queries the Meta Graph API for account-level daily metrics, active ad-level daily metrics, and 7-day ad totals for baseline comparison. Compares yesterday’s performance to the 7-day baseline to flag issues like spend spikes/drops, CPA spikes, CTR drops, CPM spikes, missing results, or missing data, and identifies ads with creative fatigue based on frequency and CTR trend. If issues are found, sends the findings to OpenAI (gpt-4o-mini) to generate a short diagnosis and prioritized fix recommendations (plus creative ideas when fatigue is present). Formats the results into a Slack message (including an Ads Manager link) and posts either the alert or an optional all-clear message to the configured Slack channel. If the workflow fails, triggers an error handler that posts a workflow error alert to Slack. Setup Add a Meta access token as an HTTP Header Auth credential and connect it to the three Meta Graph API HTTP Request nodes. Add an OpenAI API credential for the OpenAI node using the gpt-4o-mini model. Add a Slack OAuth2 credential and update the Slack channel IDs used for posting alerts and workflow error notifications. Update the account list and defaults in the configuration step (ad account IDs, client name, goal, target CPA, default Slack channel, currency symbol, and action types). Adjust the detection thresholds and limits in the configuration (lookback days, minimum spend, spend/CPA/CTR/CPM thresholds, frequency threshold, and max fatigued ads) to match your reporting needs. An n8n automation workflow template by Rahul Joshi.

By UnoPim

Quick overview A chat window for your UnoPim catalog. An OpenAI GPT-4o agent answers questions about your products and writes catalog data back through six UnoPim tools. Every reply is then routed by the workflow itself: a write is read back from UnoPim to confirm it landed, logged to a Google Sheet and announced in Slack, while anything the agent could not resolve opens a Linear issue. How it works The Chat Trigger opens a chat window that anyone on your team can use, with no n8n knowledge needed. A Settings node holds the locale, the channel and a read-only switch, so the rules live in one place rather than buried in the prompt. An OpenAI GPT-4o model drives a tool-calling agent whose system message teaches it how UnoPim stores data. Six UnoPim tools are attached to the agent. List products browses the catalog, Look up a product reads one SKU in full, and Update a product writes back with PATCH. List attributes and List families are what stop the agent inventing an attribute code or missing a field the family requires. It checks both before any write. Look up a configurable product covers products with variants, which UnoPim keeps on a separate endpoint keyed by code rather than SKU. A window buffer memory keeps the last fifteen messages, so a follow-up such as "now do the same for the other three" still makes sense. The agent ends every reply with a STATUS block naming the SKU, the field, the old value, the new value and the reason. A Code node parses that block into real fields, so the rest of the workflow is deterministic rather than trusting the model to call the right tool. A Switch routes on that status. On changed, the SKU is fetched back from UnoPim, because a write is only believed once it reads back. The before and after values are appended to a Google Sheet with a confirmed flag, and the change is posted to Slack. On unresolved, the gap becomes a Linear issue instead of an invented value. On answered, the reply goes straight back to the chat. Setup Install the community node n8n-nodes-unopim from Settings, Community nodes. This template is self-hosted only, because n8n Cloud cannot install community nodes. In UnoPim open Configuration, Integrations, API Keys and create a key. All four values the credential needs come from the same row. Add the UnoPim API credential. The URL is the application root, for example https://demo.unopim.com, not the admin address. Add an OpenAI credential and confirm it can reach gpt-4o. Pick the Google Sheet and worksheet for the change log, choose your Linear team, and select the Slack channel for announcements. Read the system message before you share the chat. It is what keeps the agent from writing something you did not approve. Requirements Self-hosted n8n. Community nodes cannot be installed on n8n Cloud. UnoPim 3.0 or newer with the n8n connector package installed. An OpenAI API key with access to gpt-4o. Google Sheets, Linear and Slack accounts for the change log, the issues and the notifications. Customization Swap gpt-4o for any chat model n8n supports. Remove Update a product and the agent becomes read only, and the changed branch simply never fires. Edit the system message to change the safety rules, or the locale and channel the agent reads values from. Change the memory window from fifteen messages to suit shorter or longer sessions. Add a tool for any other catalog resource the node supports, such as categories, channels or currencies. Replace Slack, Google Sheets or Linear on the branches with whatever your team already uses. They are ordinary nodes, not agent tools, so swapping one does not change how the agent behaves. Additional info Point the agent at a staging UnoPim first, because the credential it uses can reach a live catalog. The system message requires the agent to confirm before writing, and the workflow re-reads every SKU it wrote, so a claimed change that did not actually land shows up in the change log as not found. Update a product sends PATCH rather than PUT, so it can never replace a whole record. A video walkthrough is embedded as a sticky note on the canvas. An n8n automation workflow template by UnoPim.

By Zvid

Quick overview For gyms and coaches: turn today’s workout from Google Sheets into a branded vertical video using Zvid. Validate the design, render the MP4, then download completed media for review and sharing. How it works Triggers every day at 6am or runs on demand via a manual trigger. Loads branding and render settings (colors, fonts, hero video, music, timezone, and dry-run options) and reads workout rows from a Google Sheets tab. Selects today’s row using the configured timezone. Date, WorkoutName and Ex1 are required. If fallbackToLatest=true, use the latest past row, preserve its original workout date and never select a future row. Parse Ex1–Ex5 into exercise and reps fields. Builds a Zvid project JSON for a three-scene vertical video (hook footage, workout board, and coach’s note) and generates a ready-to-post caption. Validates the Zvid project payload using Zvid’s validation endpoint and stops with a detailed error if the payload is invalid. Optional dryRun=true saves an editor draft only with Zvid Project → Create support; published npm v0.1.8 does not expose this operation. Keep dryRun=false with that version. dryRun=false is the default: submit a Zvid render job, poll until completion or timeout and output a summary. The gated Watch video step downloads completed media for review in Binary → data → View. Setup Use self-hosted n8n. Install @zvid/n8n-nodes-zvid from Settings → Community nodes before configuring credentials; a workspace owner/admin may need to install it. Create a Zvid API credential with a key from https://app.zvid.io/api-keys and Base URL https://api.zvid.io, then select it on every Zvid node. Add Google Sheets credentials and set the spreadsheet document ID and sheet name in the Google Sheets read step. Use headers Date, WorkoutName, Focus, Ex1, Ex2, Ex3, Ex4, Ex5, CoachNote. Date must use YYYY-MM-DD; WorkoutName and Ex1 must be filled. Format exercises as “Exercise x Reps”; the last separator is used. Add a row for today, or optionally set fallbackToLatest=true to reuse the latest past workout. Update gymName, handle, branding, heroVideo, musicUrl, timezone and polling settings in Config. Align the workflow and Config timezones. dryRun defaults to false and spends Zvid credits after successful validation. Test manually and review the result before activating daily runs. Editor drafts require Project → Create support, unavailable in published v0.1.8. An n8n automation workflow template by Zvid.

By Zvid

Quick overview This workflow runs weekly and reads menu items from Google Sheets, then builds and validates a Zvid video project to render a branded vertical “weekly specials” reel, returning a shareable video URL and suggested caption. How it works Runs every Monday at 9am (or on-demand with a manual test trigger). Loads configuration values (restaurant details, branding, timing, media, and dry-run settings) and reads rows from a Google Sheets menu tab. Filters the sheet to rows marked ThisWeek = TRUE and normalizes up to five dishes (name, description, price, and photo URL). Builds a Zvid project with a sizzle hook, one scene per dish and a booking end card. Supported photo sources are bounded to 1920×1920 without distortion; supply custom image URLs already within those limits. Sends the project to Zvid’s validate endpoint to check schema and estimate credits, and stops with a detailed error if validation fails. dryRun=false is the default: submit a Zvid render job and poll until completion or timeout. Optional dryRun=true saves an editor draft only with Zvid Project → Create support; published npm v0.1.8 does not expose this operation. Keep false with that version. Outputs the completed video URL and a suggested caption. The gated Watch video step downloads completed media for review in Binary → data → View. Review the reel and share it manually. Setup Use self-hosted n8n. Install @zvid/n8n-nodes-zvid from Settings → Community nodes before configuring credentials; a workspace owner/admin may need to install it. Create a Zvid API credential with a key from https://app.zvid.io/api-keys and Base URL https://api.zvid.io, then select it on every Zvid node. Add a Google Sheets credential and select the target spreadsheet and sheet in the Google Sheets read step. Ensure your sheet has headers Dish, Description, Price, PhotoUrl, and ThisWeek, and mark 1–5 rows with ThisWeek = TRUE each week. Update restaurantName, handle, address, branding, timings, musicUrl and sizzleVideo in Config. dryRun defaults to false and spends Zvid credits after successful validation. Test manually, review the result and check the workflow timezone before activating the schedule. The editor-draft branch requires Project → Create support, unavailable in published v0.1.8. An n8n automation workflow template by Zvid.

By Zvid

Quick overview This workflow runs daily (or manually) to read job openings from Google Sheets, generate a branded vertical “we’re hiring” video project for each opening, render it with Zvid, and write the resulting VideoUrl back to the matching spreadsheet row. How it works Runs every day at 9am (or starts manually) and loads your company branding and rendering settings. Checks the optional soundtrack once per run. An unreachable or oversized track is omitted so the hiring video can render without music. Reads job openings from Google Sheets and selects rows where Role and ApplyUrl are filled and VideoUrl is empty, capped by maxPerRun. For each selected row, builds a Zvid project JSON (role, perks, salary, branding, and media) and validates it with Zvid to get warnings and a credit estimate. The default dryRun=false branch renders. Optional dryRun=true saves an editor draft only with a Zvid node exposing Project → Create; published npm v0.1.8 does not expose this operation. Keep false with that version. If dryRun is disabled, submits a Zvid render job, polls until it completes (or fails/timeouts), and gets the final video URL. Updates the source Google Sheets row with the rendered VideoUrl and outputs a run summary (and optionally downloads the finished video file for review). Setup Use self-hosted n8n. Install @zvid/n8n-nodes-zvid from Settings → Community nodes before configuring credentials; a workspace owner/admin may need to install it. Create a Zvid API credential with a key from https://app.zvid.io/api-keys and Base URL https://api.zvid.io, then select it on every Zvid node. Add a Google Sheets OAuth credential and set the spreadsheet document ID and sheet/tab name in both the read and update steps. Create a sheet with headers Role, Team, Location, SalaryRange, Perk1, Perk2, Perk3, ApplyUrl, VideoUrl, and leave VideoUrl empty for rows that should be rendered. Update companyName, companyLogoUrl, heroVideoUrl, optional musicUrl, colors, maxPerRun and polling settings in Company Config. dryRun defaults to false and spends Zvid credits after successful validation. The optional editor-draft branch requires Project → Create support, unavailable in published v0.1.8. If using the schedule trigger, confirm the workflow timezone and the 9am schedule settings match your preferred run time. An n8n automation workflow template by Zvid.

By Ali Amin

Quick overview This workflow polls a Gmail inbox for new property enquiries, uses OpenAI (GPT-4o) to extract applicant details and draft a personalised reply, matches the enquiry to a property list in Google Sheets, logs each enquiry, and either creates a Gmail draft for approval or auto-sends a safe reply. How it works Runs every minute (or manually with a test message) and lists unread messages in Gmail. Deduplicates message IDs, fetches each full email via the Gmail API, and parses headers and body text. Classifies the enquiry source (Rightmove, Zoopla, OnTheMarket, SpareRoom, or website) and drops non-enquiry portal/admin emails. Uses OpenAI to extract structured contact, property, and qualification details, then normalises the data and detects which qualification fields are missing. Reads the Properties tab in Google Sheets to match the enquiry to a property by reference or address, determines availability, and builds a pre-qualification form link or similar-property suggestions. Uses OpenAI to generate a reply body that acknowledges any details already provided and follows the correct call-to-action, then wraps it in a branded HTML email. Appends the enquiry and outcome to the Enquiry Log tab in Google Sheets and either creates a threaded Gmail draft for staff approval or auto-sends the reply and marks the original email as read. Setup Add a Gmail OAuth2 credential with access to the mailbox you want to monitor and use it for the Gmail API request nodes (list, fetch, create draft, send, and modify/mark read). Add an OpenAI API credential and ensure the workflow can use the GPT-4o and gpt-4o-mini models. Connect a Google Sheets credential and select your spreadsheet and sheet names for both the Properties reader and Enquiry Log appender. Create a Google Sheet with a Properties tab (including at least ref, address, rent, bedrooms, available_from, status, area, notes) and an Enquiry Log tab with columns for the logged fields used by this workflow. Update the configuration values in the code steps for agency name, application/pre-qualification form base URL, branding/signature details, and whether auto-send is enabled. Optional: Configure Meta WhatsApp Cloud API (phone number ID, approved template, and header auth credentials) if you want the WhatsApp follow-up, or remove the WhatsApp steps. Requirements A Gmail account (OAuth2) that receives your Rightmove, Zoopla, OnTheMarket, SpareRoom or website enquiry emails An OpenAI API key — gpt-4o-mini handles extraction, gpt-4o writes the replies A Google Sheet with two tabs: Properties (ref, address, rent, bedrooms, available_from, status, area, notes) and Enquiry Log A pre-qualification or application form URL to send applicants to (Google Form, Typeform or your own) Optional: Meta WhatsApp Cloud API access with an approved message template for the WhatsApp follow-up Customization Set your agency name, form URL and the auto-send switch in the Link Properties to Enquiries node Edit brand colour, sign-off, contact details and legal footer in the Construct Branded Email node Tune the reply tone, structure and house rules in the draft system prompt — it already enforces "never re-ask what the applicant told you" Add or adjust enquiry sources in Identify Enquiry Source to match whatever lands in your inbox Extend the extraction schema with any extra qualification fields your referencing process needs Keep auto-send off for full staff approval via Gmail drafts, or enable it for instant replies to safe, fresh enquiries Delete the WhatsApp branch if you're email-only Additional info About the creator: Built and maintained by Ali Amin, founder of IhsanOps (https://ihsanops.ai) — a UK-based AI automation consultancy helping letting agents and property businesses respond to enquiries in seconds instead of hours. This template is based on a production system running for a UK letting agency managing 800+ properties. Ali is an AWS-certified DevOps Engineer building n8n automations and AI systems for UK SMEs — see https://linkedin.com/in/ali-tm-amin. Want it adapted to your agency — CRM integration, voice/phone enquiries, auto-send rules, or your own application form? Email ali@ihsanops.ai or visit https://ihsanops.ai. An n8n automation workflow template by Ali Amin.

By Tangma Craftsman

Quick Overview This manual workflow reads pending editorial prospects from Google Sheets, matches each one to a published WooCommerce product from an EU or NA store, fetches the prospect page metadata, scores editorial relevance with OpenAI, and upserts a prioritized review record back into Google Sheets. How it works Runs when started manually. Fetches all published products from two WooCommerce stores (EU and NA) and reads pending prospects from a Google Sheets tab. Validates each prospect (region, permission status, and safe public URL) and text-matches it to the best-fit regional WooCommerce product. For valid prospects, requests the target URL and extracts the page title and meta description from the HTML response. Sends the page metadata and matched product context to the OpenAI Chat Completions API to get a JSON relevance score, rationale, pitch angle, and suggested anchors. Combines the OpenAI relevance score with sheet-provided domain rating and traffic inputs to set a review status and append-or-update the opportunity in the Google Sheets Opportunities tab. For invalid, unapproved, or unsafe prospects (or fetch/metadata failures), skips the AI step and writes a flagged record to the Opportunities tab for manual follow-up. Setup Add WooCommerce credentials for both regional stores and ensure product permalinks use the expected EU/NA hostnames. Add a Google Sheets OAuth credential, replace REPLACE_WITH_SPREADSHEET_ID, and ensure the Pending_Leads and Opportunities sheet tabs exist. Add an OpenAI API key as an HTTP Bearer Auth credential for the OpenAI Chat Completions request and change the model name if your account requires it. Ensure Pending_Leads includes the required columns (prospect_id, target_url, target_region, brand, model, part_category, permission_status) and Opportunities has opportunity_key set as the match column for upserts. An n8n automation workflow template by Tangma Craftsman.

By WeblineIndia

Quick overview This workflow runs daily to compare procurement transactions in Google Sheets against active contract terms stored in Notion, flags pricing/SLA/volume violations with calculated leakage, and uses Groq LLM analysis to generate corrective recommendations that are logged back to Google Sheets. How it works Runs every day at 6:00 AM on a schedule. Retrieves all active contract records from a Notion database. Pulls recent procurement transactions from Google Sheets and compares each transaction to the matching contract SKU to detect pricing overcharges, SLA breaches, volume threshold issues, or missing contracts, calculating per-transaction leakage. Appends compliant transactions to a dedicated Google Sheets tab for audit tracking. For violations, loads historical violation logs from Google Sheets and calculates vendor/SKU recurrence counts and cumulative leakage to estimate total impact. Processes each current violation through Groq Chat to produce a structured impact assessment, urgency, and corrective recommendation. Appends the violation details, calculated leakage, and AI recommendation to the Google Sheets “Violation Logs” audit sheet. Setup Add Notion credentials and select the Notion database that contains your contract records, including fields for SKU, agreed price, SLA days, volume threshold, contract ID, and an “Active” status. Add Google Sheets credentials and set the spreadsheet and sheet tabs used for input transactions, compliant transaction logging, and violation logging. Add a Groq API credential for the LangChain Groq Chat model used to generate structured recommendations. Ensure your Google Sheets transaction columns match the workflow’s expected headers (for example: Transaction ID, Date, Vendor, Item SKU, Quantity Purchased, Unit Price Paid, and Actual Delivery Days). Additional info How To Customize Nodes Adjusting Violation Thresholds:** Open the Compare Terms vs Actuals node. You can modify the JavaScript to include a tolerance buffer (e.g., only flagging price overcharges if they exceed the contracted rate by more than 2%). Customizing AI Output:** The Enforce JSON Schema node strictly structures the AI's response (Impact Analysis, Action Category, Urgency, Recommendation). You can add new schema fields here, such as a drafted email response to the vendor. Visual Canvas Organization:** You can improve workspace readability for your team by styling the sticky notes with low-saturation, sensory-friendly color palettes and utilizing dark charcoal text to clearly map out compliance routing paths without overwhelming the reader. Add‑ons To expand the functionality of this workflow, consider adding: Vendor Email Automation:** Add a Gmail or Outlook node after the AI Analysis to automatically email the vendor a "Notice of Contract Violation" based on the AI's recommendation. ERP Integration:** Replace Google Sheets with HTTP Request nodes to pull daily transactions and log compliance statuses directly into ERP systems like NetSuite or SAP Ariba. Ticketing System Sync:** Connect Jira or ServiceNow to automatically open a resolution ticket for any violation flagged with a "High" urgency by the AI. Use Case Examples This workflow handles multiple procurement scenarios simultaneously. Primary use cases include: Price Overcharge Detection:** A supplier invoices $12 per unit instead of the contracted $10. The workflow catches the discrepancy, calculates total leakage based on volume, and alerts the buyer to request a credit memo. SLA/Late Delivery Breach:** A critical shipment arrives in 14 days, but the contract mandates a maximum of 10 days. The workflow flags the SLA breach so procurement can enforce late-delivery penalties. Volume Threshold Exceeded:** A buyer accidentally orders 5,000 units on a contract capped at 2,000 units per month. The workflow detects the overage and advises management to renegotiate terms or hold the excess inventory. Repeat Offender Identification:** A vendor continually overcharges by small amounts over several months. The AI analyzes the historical logs, identifies the recurring pattern, calculates cumulative impact, and recommends a systemic supplier review. (There can be many more variations of this workflow by simply adjusting the JavaScript variance rules or adding additional AI evaluation criteria!) Troubleshooting Guide | Issue | Possible Cause | Solution | | --- | --- | --- | | Workflow misses contract matches | Naming discrepancies between Notion and Google Sheets. | Check for trailing spaces or case-sensitivity issues. The Compare Terms vs Actuals node requires an exact text match on the SKU fields. | | Code node returns NaN for leakage | Quantity or Price fields in Google Sheets are formatted as text. | Ensure numeric columns in Google Sheets are strictly formatted as numbers, or update the JS code to parse strings into floats. | | AI Node times out or throws schema errors | Groq API rate limits reached or unexpected LLM output. | Verify your Groq API credentials. If the model fails to parse JSON, consider switching to a different supported model like Llama 3 within the Groq node. | | Slack alerts are not sending | Incorrect Channel ID or missing app permissions. | Re-authenticate the Slack node and ensure the n8n bot is invited to the target channel. | Need Help? Building reliable, automated compliance engines requires a deep understanding of data validation, API integration and custom business logic. If you need assistance configuring your Notion databases, customizing the JavaScript leakage formulas, integrating this workflow into your native ERP system or building similar supply chain automations, please contact WeblineIndia. Our team of technical integration experts can help you design, scale and maintain tailored automation workflows for your entire business. An n8n automation workflow template by WeblineIndia.

By Buğra Şıkel

Quick Overview This workflow collects an Instagram post request via an authenticated n8n form, uses Google Gemini to draft a caption from a submitted image and verified facts, sends the draft to Telegram for human approval, and publishes to Instagram via the Facebook Graph API only after approval. How it works Receives a post request through an authenticated n8n form with a public HTTPS image URL, product name, verified facts, and an optional call to action. Validates the submission and downloads the image file from the provided URL. Sends the image and a guarded prompt to Google Gemini to generate a JSON draft containing a caption, five hashtags, a confidence score, and any risks. Applies deterministic checks (caption length, product-name inclusion, minimum confidence, banned phrases, risk flags, and exactly five unique hashtags) to decide whether the draft is eligible for review. If the draft passes, sends it to Telegram with a private approval link and pauses until a reviewer approves or rejects it. If approved, creates an Instagram media container and polls the Instagram Graph API until processing finishes. Publishes the post to Instagram, fetches the permalink, and confirms publication in Telegram, or reports rejection/processing delays back to Telegram without publishing. Setup Configure Basic Auth for the request form and publish the workflow so requesters can access the production form URL. Add credentials for Google Gemini, Telegram, and Facebook Graph API (Meta) to the corresponding nodes. Update the brand settings, Telegram chat ID, Instagram user ID, Graph API version, model name, and moderation rules in the "Configure Brand and Channels" step. Use an Instagram professional account connected to a Facebook Page and ensure the submitted image URL is a publicly reachable HTTPS JPG/PNG/WebP that stays accessible while Meta processes the media container. An n8n automation workflow template by Buğra Şıkel.

By coinsentry

Quick Overview This workflow receives signed coinsentry webhook alerts for crypto exchange listings and delistings, verifies the HMAC signature, then logs each valid event to Google Sheets and posts a formatted notification to Telegram. How it works Receives a POST webhook from coinsentry containing a listing or delisting event. Recomputes an HMAC-SHA256 signature from the raw request body and compares it to the x-coinsentry-signature header to reject unsigned or tampered requests. Filters the payload to only allow listing_announced, listing_live, or delisting events. Extracts key fields (timestamp, event, exchange, symbol, pairs, trading start time, and source URL) and formats a headline for notifications. Appends the event as a new row in a selected Google Sheets worksheet. Sends a message to a configured Telegram chat with the headline and any available pair, start time, and source link details. Setup In coinsentry, create a webhook channel pointing to this workflow’s production webhook URL and set a signing secret. Add an n8n Crypto credential containing the same HMAC secret used in coinsentry. Connect a Google Sheets account and select the target spreadsheet and sheet in the Google Sheets append step. Create the sheet columns to match the workflow mapping (at least detected_at, event, exchange, symbol, pairs, trading_starts_at, and source). Add Telegram credentials and set the target chatId for where the alerts should be posted. An n8n automation workflow template by coinsentry.