by Automate With Marc
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. 🧠 AI-Powered Blog Post Generator Category: Content Automation / AI Writing / Marketing Description: This automated workflow helps you generate fresh, SEO-optimized blog posts daily using AI tools—perfect for solo creators, marketers, and content teams looking to stay on top of the latest AI trends without manual research or writing. For more of such builds and step-by-step Tutorial Guides, check out: https://www.youtube.com/@Automatewithmarc Here’s how it works: Schedule Trigger kicks off the workflow daily (or at your preferred interval). Perplexity AI Node researches the most interesting recent AI news tailored for a non-technical audience. AI Agent (Claude via Anthropic) turns that news into a full-length blog post based on a structured prompt that includes title, intro, 3+ section headers, takeaway, and meta description—designed for clarity, engagement, and SEO. Optional Memory & Perplexity Tool Nodes enhance the agent's responses by allowing it to clarify facts or fetch more context. Google Docs Node automatically saves the final blog post to your selected document—ready for review, scheduling, or publishing. Key Features: Combines Perplexity AI + Claude AI (Anthropic) for research + writing Built-in memory and retrieval logic for deeper contextual accuracy Non-technical, friendly writing style ideal for general audiences Output saved directly to Google Docs Fully no-code, customizable, and extendable Use Cases: Automate weekly blog content for your newsletter or site Repurpose content into social posts or scripts Keep your brand relevant in the fast-moving AI landscape Setup Requirements: Perplexity API Key Anthropic API Key Google Docs (OAuth2 connected)
by Khairul Muhtadin
Who is this for? This workflow is perfect for Gmail users who want a tidy inbox without manual effort. It’s especially great for those overwhelmed by SPAM, social media updates, or promotional emails and want them automatically removed regularly. What problem is this workflow solving? Unwanted emails like SPAM, social notifications, and promotions can clutter your Gmail inbox, making it hard to focus on what matters. Manually deleting them is repetitive and time-consuming. This workflow automates the cleanup, keeping your inbox streamlined. What this workflow does Every 3 days, this workflow deletes emails from Gmail’s SPAM, Social, and Promotions categories. It uses n8n’s Gmail node to fetch these emails, merges them into a single list, splits out individual email IDs, and deletes each one. The scheduled process ensures consistent inbox maintenance. Setup Set up valid Gmail OAuth2 credentials in n8n. Import the "Clean My Mail" workflow into your n8n instance. Confirm the Gmail nodes target SPAM, CATEGORY_SOCIAL, and CATEGORY_PROMOTIONS labels. Adjust the "Run Every 3 Days (Trigger)" node’s schedule if needed. Activate the workflow to begin automated cleaning. How to customize this workflow to your needs Change the Gmail node labels to target other categories or custom labels. Adjust the schedule frequency in the trigger node. Add filters to spare specific emails from deletion. Extend functionality with nodes for archiving or notifications. made by:* khmuhtadin Need a custom? contact me on LinkedIn or Web
by Stephan Koning
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. **Alternatively, you can delete the community node and use the HTTP node instead. ** Most email agent templates are fundamentally broken. They're stateless—they have no long-term memory. An agent that can't remember past conversations is just a glorified auto-responder, not an intelligent system. This workflow is Part 1 of building a truly agentic system: creating the brain. Before you can have an agent that replies intelligently, you need a knowledge base for it to draw from. This system uses a sophisticated parser to automatically read, analyze, and structure every incoming email. It then logs that intelligence into a persistent, long-term memory powered by mem0. The Problem This Solves Your inbox is a goldmine of client data, but it's unstructured, and manually monitoring it is a full-time job. This constant, reactive work prevents you from scaling. This workflow solves that "system problem" by creating an "always-on" engine that automatically processes, analyzes, and structures every incoming email, turning raw communication into a single source of truth for growth. How It Works This is an autonomous, multi-stage intelligence engine. It runs in the background, turning every new email into a valuable data asset. Real-Time Ingest & Prep: The system is kicked off by the Gmail Trigger, which constantly watches your inbox. The moment a new email arrives, the workflow fires. That email is immediately passed to the Set Target Email node, which strips it down to the essentials: the sender's address, the subject, and the core text of the message (I prefer using the plain text or HTML-as-text for reliability). While this step is optional, it's a good practice for keeping the data clean and orderly for the AI. AI Analysis (The Brain): The prepared text is fed to the core of the system: the AI Agent. This agent, powered by the LLM of your choice (e.g., GPT-4), reads and understands the email's content. It's not just reading; it's performing analysis to: Extract the core message. Determine the sentiment (Positive, Negative, Neutral). Identify potential red flags. Pull out key topics and keywords. The agent uses Window Buffer Memory to recall the last 10 messages within the same conversation thread, giving it the context to provide a much smarter analysis. Quality Control (The Parser): We don't trust the AI's first draft blindly. The analysis is sent to an Auto-fixing Output Parser. If the initial output isn't in a perfect JSON format, a second Parsing LLM (e.g., Mistral) automatically corrects it. This is our "twist" that guarantees your data is always perfectly structured and reliable. Create a Permanent Client Record: This is the most critical step. The clean, structured data is sent to mem0. The analysis is now logged against the sender's email address. This moves beyond just tracking conversations; it builds a complete, historical intelligence file on every person you communicate with, creating an invaluable, long-term asset. Optional Use: For back-filling historical data, you can disable the Gmail Trigger and temporarily connect a Gmail "Get Many" node to the Set Target Email node to process your backlog in batches. Setup Requirements To deploy this system, you'll need the following: An active n8n instance. Gmail** API credentials. An API key for your primary LLM (e.g., OpenAI). An API key for your parsing LLM (e.g., Mistral AI). An account with mem0.ai for the memory layer.
by Davi Saranszky Mesquita
Log errors and avoid sending too many emails Use case Most of the time, it’s necessary to log all errors that occur. However, in some cases, a scheduled task or service consuming excessive resources might trigger a surge of errors. To address this, we can log all errors but limit alerts to a maximum of one notification every 5 minutes. What this workflow does This workflow can be configured to receive error events, or you can integrate it before your own error-handling logic. If used as the primary error handler, note that this flow will only add a database log entry and take no further action. You’ll need to add your own alerts (e.g., email or push notifications). Below is an example of a notification setup I prefer to use. At the end, there’s an error cleanup option. This feature is particularly useful in development environments. If you already have an error-handling workflow, you can call this one as a sub-workflow. Its final steps include cleanup logic to reset the execution state and terminate the workflow. Setup Verify all Postgres nodes and credentials when using the 'Error Handling Sample' How to adjust it to your needs 1) You can set this workflow as a sub-workflow within your existing error-handling setup. 2) Alternatively, you can add the "Error Handling Sample" at the end of this workflow, which sends email and push notifications. Configuration Requirements: ⚠️ You must create a database table for this to work! DDL of this sample: create table p1gq6ljdsam3x1m."N8Err" ( id serial primary key, created_at timestamp, updated_at timestamp, created_by varchar, updated_by varchar, nc_order numeric, title text, "URL" text, "Stack" text, json json, "Message" text, "LastNode" text ); alter table p1gq6ljdsam3x1m."N8Err" owner to postgres; create index "N8Err_order_idx" on p1gq6ljdsam3x1m."N8Err" (nc_order); by Davi Saranszky Mesquita https://www.linkedin.com/in/mesquitadavi/
by Mutasem
Use Case Following up at the right time is one of the most important parts of sales. This workflow uses Gmail to send outreach emails to Hubspot contacts that have already been contacted only once more than a month ago, and records the engagement in Hubspot. Setup Setup HubSpot Oauth2 creds (Be careful with scopes. They have to be exact, not less or more. Yes, it’s not simple, but it’s well documented in the n8n docs. Be smarter than me, read the docs) Setup Gmail creds. Change the email variables in the Set keys node How to adjust this template There's plenty to do here because the approach here is really just a starting point. Most important here is to figure out what your rules are to follow up. After a month? More than once? Also, remember to update the follow-up email! Unless you want to sell n8n 😉
by Daniel Shashko
This workflow automates daily or manual keyword rank tracking on Google Search for your target domain. Results are logged in Google Sheets and sent via email using Bright Data's SERP API. Requirements: n8n (local or cloud) with Google Sheets and Gmail nodes enabled Bright Data API credentials Main Use Cases Track Google search rankings for multiple keywords and domains automatically Maintain historical rank logs in Google Sheets for SEO analysis Receive scheduled or on-demand HTML email reports with ranking summaries Customize or extend for advanced SEO monitoring and reporting How it works The workflow is divided into several logical steps: 1. Workflow Triggers Manual:** Start by clicking 'Test workflow' in n8n. Scheduled:** Automatically triggers every 24 hours via Schedule Trigger. 2. Read Keywords and Target Domains Fetches keywords and domains from a specified Google Sheets document. The sheet must have columns: Keyword and Domain. 3. Transform Keywords Formats each keyword for URL querying (spaces become +, e.g., seo expert → seo+expert). 4. Batch Processing Processes keywords in batches so each is checked individually. 5. Get Google Search Results via Bright Data Sends a request to Bright Data's SERP API for each keyword with location (default: US). Receives the raw HTML of the search results. 6. Parse and Find Ranking Extracts all non-Google links from HTML. Searches for the target domain among the results. Captures the rank (position), URL, and total number of results checked. Saves timestamp. 7. Save Results to Google Sheets Appends the findings (keyword, domain, rank, found URL, check time) to a “Results” sheet for history. 8. Generate HTML Report and Send Email Builds an HTML table with current rankings. Emails the formatted table to the specified recipient(s) with Gmail. Setup Steps Google Sheets: Create a sheet named “Results”, and another with Keyword and Domain columns. Update document ID and sheet names in the workflow’s config. Bright Data API: Acquire your Bright Data API token. Enter it in the Authorization header of the 'Getting Ranks' HTTP Request node. Gmail: Connect your Gmail account via OAuth2 in n8n. Set your destination email in the 'Sending Email Message' node. Location Customization: Modify the gl= parameter in the SERP API URL to change country/location (e.g., gl=GB for the UK). Notes This workflow is designed for n8n local or cloud environments with suitable connector credentials. Customize batch size, recipient list, or ranking extraction logic per your needs. Use sticky notes in n8n for further setup guidance and workflow tips. With this workflow, you have an automated, repeatable process to monitor, log, and report Google search rankings for your domains—ideal for SEO, digital marketing, and reporting to clients or stakeholders.
by Marketing Canopy
Automate Pinterest Analysis & AI-Powered Content Suggestions With Pinterest API This workflow automates the collection, analysis, and summarization of Pinterest Pin data to help marketers optimize content strategy. It gathers Pinterest Pin performance data, analyzes trends using an AI agent, and delivers actionable insights to the Marketing Manager via email. This setup is ideal for content creators and marketing teams who need weekly insights on Pinterest trends to refine their content calendar and audience engagement strategy. Prerequisites Before setting up this workflow, ensure you have the following: Pinterest API Access & Developer Account Sign up at Pinterest Developers and obtain API credentials. Ensure you have access to both Organic and Paid Pin data. Airtable Account & API Key Create an account at Airtable and set up a database. Obtain an API key from Account Settings. AI Agent for Trend Analysis An AI-powered agent (such as OpenAI's GPT or a custom ML model) is required to analyze Pinterest trends. Ensure integration with your workflow automation tool (e.g., Zapier, Make, or a custom Python script). Email Automation Setup Configure an SMTP email service (e.g., Gmail, Outlook, SendGrid) to send the summarized results to the Marketing Manager. Step-by-Step Guide to Automating Pinterest Pin Analysis 1. Scheduled Trigger for Data Collection At 8:00 AM (or your preferred time), an automated trigger starts the workflow. Adjust the timing based on your marketing schedule to optimize trend tracking. 2. Fetch Data from Pinterest API Retrieve recent Pinterest Pin performance data, including impressions, clicks, saves, and engagement rate. Ensure both Organic and Paid Ads data are labeled correctly for clarity. 3. Store Data in Airtable Pins are logged and categorized in an Airtable database for further analysis. Sample Airtable Template for Pinterest Pins | Column Name | Description | |---------------|---------------------------------------| | pin_id | Unique identifier for each Pin | | created_at | Timestamp of when the Pin was created | | title | Title of the Pin | | description| Short description of the Pin | | link | URL linking to the Pin | | type | Type of Pin (e.g., organic, ad) | 4. AI Agent Analyzes Pinterest Trends The AI model reviews the latest Pinterest data and identifies: Trending Topics & Keywords** Engagement Patterns** Audience Interests & Behavior Changes** Optimal Posting Times & Formats** 5. Generate Content Suggestions with AI The AI Agent recommends new Pin ideas and content calendar updates to maximize engagement. Suggestions include creative formats, hashtags, and timing adjustments for better performance. 6. Summary & Insights Generated by AI A concise report is created, summarizing Pinterest trends and actionable insights for content strategy. 7. Email Report Sent to the Marketing Manager The summary is emailed to the Marketing Manager to assist with content planning and execution. The report includes: Performance Overview of Recent Pins Trending Content Ideas Best Performing Pin Formats AI-Generated Recommendations This workflow enables marketing teams to automate Pinterest analysis and optimize their content strategy through AI-driven insights. 🚀
by Marth
🧠 How It Works This AI Agent automatically qualifies property buyer leads from form submissions. Form Submission Trigger When a user submits their details via a property inquiry form, the workflow is triggered. AI Lead Classification The buyer's input (budget, location, timeline, etc.) is analyzed by OpenAI to extract structured data and generate a lead score (0–100). Lead Qualification Logic Leads with a score of 70 or above are marked as qualified, the rest are ignored or stored separately. Follow-Up Action Qualified leads trigger: Email notification to the agent Record creation in Airtable as CRM ⚙️ How to Set Up Form Setup Replace the form trigger with your preferred source (Typeform, Google Form, etc.) Make sure the form includes: Name, Email, Budget, Location, Timeline, Property Type Connect Your Credentials Add your OpenAI API key for the LLM node Connect your Gmail account for notifications Link your Airtable base and table to store qualified leads Customize Scoring Logic (Optional) You can tweak the prompt in the Information Extractor node to change how scoring works Test the Workflow Submit a test entry via the form Check if you receive an email and see the lead in Airtable Activate & Go Live Turn on the workflow and start qualifying real buyer leads in real time Connect with my linkedin: https://www.linkedin.com/in/bheta-dwiki-maranatha-15654b227/
by Corentin Ribeyre
This template can be used to verify an email address with Icypeas. Be sure to have an active account to use this template. How it works This workflow can be divided into three steps : The workflow initiates with a manual trigger (On clicking 'execute'). It connects to your Icypeas account. It performs an HTTP request to verify an email address. Set up steps You will need a working icypeas account to run the workflow and get your API Key, API Secret and User ID. You will need an email address to perform the verification.
by isaWOW
Description Activate this workflow once and every weekday morning at 8AM your phone receives a complete day briefing on Telegram — automatically. It fetches your unread emails and today's and tomorrow's calendar events in parallel, sends everything to GPT-4o-mini which filters out promotions and noise, and delivers one clean structured message with your urgent emails, today's schedule, tomorrow's preparation, and one focus recommendation. Built for founders, executives, and busy professionals who want full day context before they open a single app. What This Workflow Does Fetches emails and calendar simultaneously** — Pulls unread inbox emails from the last 24 hours and calendar events for today and tomorrow at the same time to save processing time Filters out email noise automatically** — GPT-4o-mini identifies only emails that need a reply or action — newsletters, promotions, automated notifications, and receipts are silently excluded Separates today and tomorrow events** — Calendar events are split into two lists so your schedule and your preparation are clearly distinct in the brief Generates one focus recommendation** — Based on the combined context of your emails and calendar, GPT surfaces the single most important thing to concentrate on today Adds a preparation tip for busy meetings** — If tomorrow has meetings with more than two attendees, the brief automatically includes a preparation suggestion Delivers with Markdown formatting** — The Telegram message uses bold headings and clean layout so the brief is easy to scan on a phone screen Includes a timezone-aware timestamp** — A footer shows the exact local time the brief was generated so you always know when the data was pulled Setup Requirements Tools Needed n8n instance (self-hosted or cloud) Gmail account (the inbox you want monitored) Google Calendar (your primary calendar) OpenAI account with GPT-4o-mini API access Telegram bot (created via @BotFather) Credentials Required Gmail OAuth2 Google Calendar OAuth2 OpenAI API key Telegram Bot credential Estimated Setup Time: 15–20 minutes Step-by-Step Setup Import the workflow — Open n8n → Workflows → Import from JSON → paste the workflow JSON → click Import Get your Telegram Chat ID — Open Telegram → search for @userinfobot → send /start → it replies with your numeric chat ID Fill in Config Values — Open node 2. Set — Config Values → replace all four placeholders: | Field | What to enter | |---|---| | PASTE_YOUR_TELEGRAM_CHAT_ID_HERE | Your Telegram chat ID from step 2 | | PASTE_YOUR_GMAIL_ADDRESS_HERE | Your Gmail address (e.g. you@gmail.com) | | PASTE_YOUR_NAME_OR_COMPANY_HERE | Your name or company name (used in the GPT prompt greeting) | | timezone | Your timezone string — default is Asia/Kolkata. Change to your timezone e.g. America/New_York, Europe/London, Asia/Singapore | Connect Gmail — Open node 3. Gmail — Fetch Unread Emails → click the credential dropdown → add Gmail OAuth2 → sign in with the Gmail account you want monitored → authorize access Connect Google Calendar — Open node 4. Google Calendar — Fetch Today and Tomorrow → click the credential dropdown → add Google Calendar OAuth2 → sign in with the same Google account → authorize access Connect OpenAI — Open node 7. OpenAI — GPT-4o-mini Model → click the credential dropdown → add your OpenAI API key → test the connection Connect Telegram — Open node 9. Telegram — Send Morning Brief → click the credential dropdown → add your Telegram Bot API credential (paste the bot token from @BotFather) → save Activate your Telegram bot — Open Telegram → find your bot → send /start — this is required before the bot can message you for the first time Activate the workflow — Toggle the workflow to Active — it will run automatically every weekday at 8AM > ⚠️ Test before 8AM — To test immediately, click on node 1. Schedule — Every Weekday 8AM and use the manual Execute option to trigger a test run. How It Works (Step by Step) Step 1 — Schedule: Every Weekday 8AM This step fires the workflow automatically every Monday through Friday at 8AM. The cron expression 0 8 * * 1-5 ensures it never runs on weekends. No manual trigger is needed once activated. Step 2 — Set: Config Values Your Telegram chat ID, Gmail address, name, timezone, and all date variables used throughout the workflow are stored here. Today's date, today's ISO timestamp, yesterday's timestamp (for the 24-hour email window), tomorrow's timestamp, and the day-after-tomorrow's timestamp are all calculated automatically from the current date — you never need to update these. Step 3 — Gmail: Fetch Unread Emails (parallel) All unread inbox emails received in the last 24 hours are fetched from your Gmail account. This step runs at the same time as the calendar fetch to save time. Up to 20 emails are processed — the sender, subject line, and a short preview of each message are captured. Step 4 — Google Calendar: Fetch Today and Tomorrow (parallel) All events from your primary Google Calendar for today and tomorrow are fetched simultaneously alongside the Gmail step. For each event, the title, start and end time, location, and attendee count are captured. If the event has a specific time it is formatted as HH:MM to HH:MM — all-day events are labelled accordingly. Step 5 — Code: Merge Emails and Calendar Both the email and calendar data are read together here and formatted into clean text for GPT. Emails are listed with sender, subject, and preview. Calendar events are separated into a today list and a tomorrow list, each with time and attendee count. If either source returns no data, a clean fallback message is used (e.g. "No unread emails in the last 24 hours"). The formatted text, event counts, and email count are all packaged for the AI step. Step 6 — AI Agent: Write Morning Brief GPT-4o-mini receives your name, today's date, the full email list, and both calendar lists. It writes a structured 4-section brief in plain text with basic Telegram Markdown bold headings. Section 1 lists only urgent emails that need a reply or action — all promotional and automated emails are excluded. Section 2 lists all today's events with their times. Section 3 lists tomorrow's events and adds a preparation tip for any meeting with more than two attendees. Section 4 gives one single focus recommendation for the day based on the combined context. The brief is kept under 300 words. Step 7 — OpenAI: GPT-4o-mini Model This is the language model powering the brief. It runs at temperature 0.4 for a natural, warm tone that is not robotic but also not overly creative. It is capped at 600 tokens to keep the brief concise and costs extremely low — well under $0.001 per morning brief. Step 8 — Code: Prepare Telegram Message The GPT brief text is read and a timestamp footer is added in your local timezone (e.g. Brief generated at 08:02). If GPT failed to generate any output, a fallback message is used instead so Telegram always receives something. The complete message and your Telegram chat ID are packaged for delivery. Step 9 — Telegram: Send Morning Brief The full brief is sent to your Telegram chat with Markdown rendering enabled. Bold headings render correctly in Telegram so the four sections are clearly separated. A Telegram attribution footer is suppressed so the message looks clean. Key Features ✅ Fully automated weekday delivery — Runs Monday to Friday at 8AM with zero manual input after the one-time setup ✅ Parallel Gmail and Calendar fetch — Both data sources are pulled at the same time rather than one after the other, keeping the workflow fast ✅ Noise-filtered email list — GPT actively excludes newsletters, promotions, and automated notifications so only actionable emails appear in your brief ✅ Two-day calendar view — Today's schedule and tomorrow's events are always both included so you can plan ahead from the morning brief alone ✅ Preparation tips for group meetings — If tomorrow has a meeting with more than two attendees, the brief automatically suggests how to prepare ✅ Fallback protection — If GPT fails or returns empty output, a fallback message is sent to Telegram so you always receive something at 8AM ✅ Timezone-correct timestamp — The footer shows your local time based on the timezone value in Config Values — not UTC ✅ Under $0.001 per brief — GPT-4o-mini at 600 tokens with temperature 0.4 costs fractions of a cent per run — 260 working days a year costs less than $0.25 total Customisation Options Change the delivery time — In node 1. Schedule — Every Weekday 8AM, edit the cron expression 0 8 * * 1-5 to fire at a different hour — for example 0 7 * * 1-5 for 7AM or 30 7 * * 1-5 for 7:30AM. Include weekends — In node 1. Schedule — Every Weekday 8AM, change the cron expression from 0 8 * * 1-5 to 0 8 * * * to receive a brief every day of the week including Saturday and Sunday. Add a specific Gmail label filter — In node 3. Gmail — Fetch Unread Emails, add a label filter to only pull emails tagged with a specific Gmail label (e.g. your client label) so the brief focuses only on the emails that matter most to you. Include a second Google Calendar — After node 4. Google Calendar — Fetch Today and Tomorrow, duplicate the step and connect it to a second calendar ID — then update node 5. Code — Merge Emails and Calendar to also read from that second calendar result and merge the events together. Add a Slack summary for your team — After node 8. Code — Prepare Telegram Message, add a Slack node that posts a shorter 2-line version (just today's meeting count and your one focus) to a #team-standup channel so your team gets daily context too. Troubleshooting Workflow not triggering at 8AM: Confirm the workflow is Active — inactive workflows do not run on a schedule Check that the cron expression in node 1. Schedule — Every Weekday 8AM is exactly 0 8 * * 1-5 — any accidental edit breaks the schedule Confirm your n8n instance is running at 8AM — self-hosted instances that are turned off will not fire scheduled workflows To test immediately, click on node 1 and use the manual Execute option Gmail returning no emails even when you have unread messages: Confirm the Gmail OAuth2 credential in node 3. Gmail — Fetch Unread Emails is connected and not expired — re-authorize if needed The filter fetches emails received after yesterdayISO — if your n8n instance timezone is set incorrectly, this window may shift unexpectedly Check that PASTE_YOUR_GMAIL_ADDRESS_HERE in node 2. Set — Config Values is replaced with your actual Gmail address Google Calendar returning no events: Confirm the Google Calendar OAuth2 credential in node 4. Google Calendar — Fetch Today and Tomorrow is connected with the same Google account that owns the calendar The step fetches from the primary calendar — if your events are on a different calendar (e.g. a work calendar with a different email), you need to change the calendar ID in the step Check that your calendar events have dates that fall within today or tomorrow relative to your n8n server's timezone OpenAI not generating the brief: Confirm the API key is connected in node 7. OpenAI — GPT-4o-mini Model and your account has available credits If the brief arrives as the fallback message ("Your brief could not be generated"), check the execution log of node 6. AI Agent — Write Morning Brief for the raw error Temperature 0.4 and 600 max tokens are set by design — do not reduce max tokens below 400 or the brief may be cut off mid-section Telegram message not arriving: Confirm the Telegram Bot credential in node 9. Telegram — Send Morning Brief is connected with a valid bot token from @BotFather Confirm PASTE_YOUR_TELEGRAM_CHAT_ID_HERE in node 2. Set — Config Values is replaced with your numeric chat ID from @userinfobot You must send /start to your bot in Telegram before the first message can be delivered — bots cannot initiate conversations without this activation step Support Need help setting this up or want a custom version built for your team or agency? 📧 Email: info@isawow.com 🌐 Website: https://isawow.com/
by Avkash Kakdiya
Quick overview This workflow runs every weekday morning to find HubSpot deals with no recent activity, uses OpenAI to generate a personalized re-engagement email, sends it via Gmail, logs the outcome to Google Sheets, and notifies your team in Slack with per-deal alerts and a daily digest. How it works Runs on a weekday schedule at 08:00 and retrieves all open deals from HubSpot. Calculates days since the last deal activity and keeps only deals stalled for 7 days or more. Checks whether each stalled deal has an associated HubSpot contact and logs deals without a contact to Google Sheets as skipped. Fetches the associated contact from HubSpot, verifies an email address exists, and logs deals without an email to Google Sheets as skipped. Sends the deal and contact context to OpenAI to generate a JSON email subject and body, then parses the result into fields. Sends the re-engagement email to the contact via Gmail, adds a note to the HubSpot deal, posts a Slack alert to the sales channel, and appends the action to Google Sheets. Builds a run summary (re-engaged vs skipped) and posts a single daily digest message to Slack. Setup Add credentials for HubSpot, OpenAI, Gmail, Slack, and Google Sheets in n8n. Replace REPLACE_WITH_YOUR_SHEET_ID with your Google Sheet document ID and ensure the target sheet name (for example, Sheet1) exists. Create the Google Sheet columns used for logging (Date, Deal Name, Contact Email, Stage, Days Stalled, Email Sent, Slack Notified, Status). Update the Slack channel names/IDs for the sales notifications (for example, sales-team) and the error channel (for example, n8n-errors).
by Akshay Chug
Quick overview This workflow monitors a Google Sheets patient intake log, uses Anthropic Claude to decide the right follow-up action and draft an email, sends the message via Gmail, optionally notifies a clinic manager in Slack for re-bookings, and appends each communication to a Google Sheets log. How it works Triggers when a new patient row appears in a Google Sheets intake spreadsheet. Loads clinic settings (sheet IDs, clinic name, booking link, sender email, and Slack channel) and formats the patient record into a prompt. Sends the prompt to Anthropic Claude (Sonnet) to return a JSON plan with an action, urgency, email subject/body, and a short reason. Parses Claude’s JSON response and falls back to a default follow-up message if parsing fails. Routes the patient to the correct branch and sends a plain-text email via Gmail (welcome, re-booking, or follow-up). For re-booking emails, posts a Slack notification to the clinic manager with patient details for manual confirmation. Appends a row to a Google Sheets communications log with the action, status, urgency, timestamp, and email details. Setup Connect credentials for Google Sheets, Gmail, Slack, and Anthropic (Claude) in n8n. Update the configuration values for INTAKE_SHEET_ID, LOG_SHEET_ID, LOG_SHEET_NAME, SLACK_CHANNEL_ID, CLINIC_NAME, BOOKING_LINK, and SENDER_EMAIL. Ensure your intake sheet contains the expected fields (for example Patient Name, Email, Contact Reason, Appointment Status, Last Visit, and Notes) and create a communications log sheet with matching columns for the appended data.