Workflow Templates

This workflow automates the end-to-end analysis of WooCommerce product reviews, transforming raw customer feedback into actionable product and customer-care insights, and delivering them in a structured, visual, and shareable format. This workflow analyzes product review sentiment from WooCommerce using AI. It starts by retrieving reviews for a specified product via the WooCommerce. Each review then undergoes sentiment analysis using LangChain's Sentiment Analysis. The workflow aggregates sentiment data, creates a pie chart visualization via QuickChart, and compiles a comprehensive report using an AI Agent. The report includes executive summaries, quantitative data, qualitative analysis, product diagnostics, and operational recommendations. Finally, the AI-generated report is converted to HTML and emailed to a designated recipient for review by customer and product teams. Key Advantages 1. ✅ Full Automation of Review Analysis Eliminates manual work by automating data collection, sentiment analysis, reporting, visualization, and delivery in a single workflow. 2. ✅ Scalable and Reliable Batch processing ensures the workflow can handle dozens or hundreds of reviews without performance issues. 3. ✅ Action-Oriented Insights (Not Just Sentiment) Instead of stopping at sentiment scores, the workflow produces: Root-cause hypotheses Concrete improvement actions Prioritized recommendations (P0 / P1 / P2) Measurable KPIs 4. ✅ Combines Quantitative and Qualitative Analysis Merges hard metrics (averages, distributions, outliers) with qualitative insights (themes, risks, opportunities), giving a 360° view of customer feedback. 5. ✅ Visual + Narrative Output Stakeholders receive both: Visual sentiment charts** for quick understanding Structured written reports** for strategic decision-making 6. ✅ Ready for Product & Customer Care Teams The output format is tailored for non-technical teams: Clear language Masked personal data (GDPR-friendly) Immediate usability in meetings, emails, or documentation 7. ✅ Easily Extensible The workflow can be extended to: Run on a schedule Analyze multiple products Store results in a database or CRM Trigger alerts for negative sentiment spikes Ideal Use Cases Continuous monitoring of product sentiment Supporting product roadmap decisions Identifying customer pain points early Improving customer support response strategies Reporting customer voice to stakeholders automatically How it works Manual Trigger & Configuration The workflow starts manually and sets the target WooCommerce product ID and store URL. Data Retrieval from WooCommerce Fetches all reviews for the selected product via the WooCommerce REST API. Retrieves product details (name, description, categories) to enrich the analysis context. Batch Processing of Reviews Reviews are processed in batches to ensure scalability and reliability, even with a large number of reviews. AI-Powered Sentiment Analysis Each review is analyzed using an OpenAI-based sentiment analysis model. For every review, the workflow extracts: Sentiment category (Positive / Negative / Neutral) Strength (intensity) Confidence (reliability of the classification) Data Normalization & Aggregation Review text is cleaned and structured. Sentiment data is aggregated to compute overall distributions and metrics. Visual Sentiment Distribution A pie chart is dynamically generated via QuickChart to visually represent sentiment distribution. Advanced AI Insight Generation A specialized AI agent (“Product Insights Analyst”) transforms the raw and aggregated data into a professional, structured report, including: Executive summary Quantitative statistics Qualitative themes Product diagnosis Operational recommendations Product backlog ideas Next steps HTML Conversion & Delivery The report is converted into clean HTML. The final output is automatically sent via email to stakeholders (e.g. product or customer care teams). Set up steps Configure credentials: Set up WooCommerce API credentials in the HTTP Request node. Add OpenAI API credentials for both sentiment analysis and reporting. Configure Gmail OAuth2 credentials for sending the final email report. Set parameters: In the "Product ID" node, replace PRODUCT_ID and YOUR_WEBSITE with actual product ID and WooCommerce site URL. Update the recipient email address in the "Send a message" node. Optional adjustments: Modify the pie chart design in the "QuichChart" node if needed. Adjust the report structure or language in the "Product Insights Analyst" system prompt. Run the workflow: Click "Execute workflow" on the manual trigger to start the process. Monitor execution in n8n to ensure all nodes process correctly. Once configured, the workflow will automatically analyze product reviews, generate insights, and deliver a formatted report via email. 👉 Subscribe to my new YouTube channel. Here I’ll share videos and Shorts with practical tutorials and FREE templates for n8n. Need help customizing? Contact me for consulting and support or add me on Linkedin.

Automate Your Life: The Ultimate AI Assistant in Telegram (Powered by Google Gemini) Transform your Telegram messenger into a powerful, multi-modal personal or team assistant. This n8n workflow creates an intelligent agent that can understand text, voice, images, and documents, and take action by connecting to your favorite tools like Google Calendar, Gmail, Todoist, and more. At its core, a powerful Manager Agent, driven by Google Gemini, interprets your requests, orchestrates a team of specialized sub-agents, and delivers a coherent, final response, all while maintaining a persistent memory of your conversations. Key Features 🧠 Intelligent Automation: Uses Google Gemini as a central "Manager Agent" to understand complex requests and delegate tasks to the appropriate tool. 🗣️ Multi-Modal Input: Interact naturally by sending text, voice notes, photos, or documents directly into your Telegram chat. 🔌 Integrated Toolset: Comes pre-configured with agents to manage your memory, tasks, emails, calendar, research, and project sheets. 🗂️ Persistent Memory: Leverages Airtable as a knowledge base, allowing the assistant to save and recall personal details, company information, or past conversations for context-rich interactions. ⚙️ Smart Routing: Automatically detects the type of message you send and routes it through the correct processing pipeline (e.g., voice is transcribed, images are analyzed). 🔄 Conversational Context: Utilizes a window buffer to maintain short-term memory, ensuring follow-up questions and commands are understood within the current conversation. How It Works The Telegram Trigger node acts as the entry point, receiving all incoming messages (text, voice, photo, document). A Switch node intelligently routes the message based on its type: Voice**: The audio file is downloaded and transcribed into text using a voice-to-text service. Photo**: The image is downloaded, converted to a base64 string, and prepared for visual analysis. Document**: The file is routed to a document handler that extracts its text content for processing. Text**: The message is used as-is. A Merge node gathers the processed input into a unified prompt. The Manager Agent receives this prompt. It analyzes the user's intent and orchestrates one or more specialized agents/tools: memory_base (Airtable): For saving and retrieving information from your long-term knowledge base. todo_and_task_manager (Todoist): To create, assign, or check tasks. email_agent (Gmail): To compose, search, or send emails. calendar_agent (Google Calendar): To schedule events or check your agenda. research_agent (Wikipedia/Web Search): To look up information. project_management (Google Sheets): To provide updates on project trackers. After executing the required tasks, the Manager Agent formulates a final response and sends it back to you via the Telegram node. Setup Instructions Follow these steps to get your AI assistant up and running. Telegram Bot: Create a new bot using the BotFather in Telegram to get your Bot Token. In the n8n workflow, configure the Telegram Trigger node's webhook. Add your Bot Token to the credentials in all Telegram nodes. For proactive messages, replace the chatId placeholders with your personal Telegram Chat ID. Google Gemini AI: In the Google Gemini nodes, add your credentials by providing your Google Gemini API key. Airtable Knowledge Base: Set up an Airtable base to act as your assistant's long-term memory. In the memory_base nodes (Airtable nodes), configure the credentials and provide the Base ID and Table ID. Google Workspace APIs: Connect your Google account credentials for Gmail, Google Calendar, and Google Sheets. In the relevant nodes, specify the Document/Sheet IDs you want the assistant to manage. Connect Other Tools: Add your credentials for Todoist and any other integrated tool APIs. Configure Conversational Memory: This workflow is designed for multi-user support. Verify that the Session Key in the "Window Buffer Memory" nodes is correctly set to a unique user identifier from Telegram (e.g., {{ $json.chat.id }}). This ensures conversations from different users are kept separate. Review Schedule Triggers: Check any nodes designed to run on a schedule (e.g., "At a regular time"). Adjust their cron expressions, times, and timezone to fit your needs (e.g., for daily summaries). Test the Workflow: Activate the workflow. Send a text message to your bot (e.g., "Hello!"). Estimated Setup Time 30–60 minutes:** If you already have your API keys, account credentials, and service IDs (like Sheet IDs) ready. 2–3 hours:** For a complete, first-time setup, which includes creating API keys, setting up new spreadsheets or Airtable bases, and configuring detailed permissions.

Social Media Post & Caption Generator (Google Drive → AI Caption → Approval → Auto-Post) Automatically turn your existing content library into approved, AI-written social media posts. This workflow selects a random file from Google Drive, generates an Instagram caption using AI, sends it to you for approval, and—once approved—uploads and publishes the post via Blotato. 🎥 Watch Step-By-Step Guide: https://youtu.be/9XU9ECcj9dg What this template does On a scheduled basis (default: 10:00 AM), this workflow: Searches a specified Google Drive folder for content files Randomly selects one file to avoid repetitive posting Uses AI to generate an Instagram-ready caption based on the file name Sends the caption + file link to you via email for approval If approved: Downloads the file from Drive Uploads the media to Blotato Creates and publishes the social media post If rejected: Automatically loops back and selects a different random file Why it’s useful Keeps your social media consistent with minimal manual effort Adds a human-in-the-loop approval step for quality control Eliminates the need to manually write captions or pick content Ideal for creators, solo marketers, and small teams managing content at scale Requirements Before using this template, connect the following credentials in n8n: Google Drive OAuth (searching & downloading files) OpenAI API (caption generation) Gmail OAuth (approval email workflow) Blotato API (media upload & social posting) All credentials must be added manually after importing the template. No sensitive data is included in the template. How it works (Node overview) Schedule Trigger Runs the workflow at a fixed time each day. Google Drive – Search Files and Folders Fetches all files from a specified Drive folder. Randomizer (Code Node) Selects a random file from the available list to ensure content variety. Caption Generator AI Uses an AI model to generate a descriptive Instagram caption based on the file name. Gmail – Send for Approval and Wait Emails the generated caption and file link to you and pauses execution until approval or rejection. IF (Approved) Yes: proceeds to download, upload, and publish No: loops back to select another random file Google Drive – Download File Downloads the approved content file. Blotato – Upload Media & Create Post Uploads the media and publishes the post to the connected social account. Setup instructions Import the template into your n8n workspace Open the Google Drive nodes and connect your Drive OAuth credential Replace the Folder ID with your own content folder Connect your OpenAI credential in the Caption Generator node Connect Gmail OAuth and set your approval email address Connect your Blotato account and select the target social profile Run the workflow once to test the approval loop Activate the workflow to start automated posting Customization ideas Adjust the AI system prompt to change tone (funny, educational, sales-focused) Add hashtag rules (e.g. max 5 hashtags, niche-specific only) Replace random selection with “least recently posted” logic using a Data Table Duplicate the Blotato node to post to multiple platforms Add a fallback step to auto-edit captions that exceed character limits Troubleshooting No files found: confirm the Google Drive folder ID and permissions Approval email not received: check Gmail OAuth scopes and spam folder Caption quality not ideal: refine the AI system prompt Upload fails: confirm Blotato account permissions and social account connection

This template enriches a lead list by analyzing each contact’s LinkedIn activity and auto-generating a single personalized opening line for cold outreach. Drop a spreadsheet into a Google Drive folder → the workflow parses rows, fetches LinkedIn content (recent post or profile), uses an LLM to craft a one-liner, writes the result back to Google Sheets, and sends a Telegram summary. ⸻ Good to know • Works with two paths: • Recent post found → personalize from the latest LinkedIn post. • No recent post → personalize from profile fields (headline, about, current role). • Requires valid Apify credentials for LinkedIn scrapers and LLM keys (Anthropic and/or OpenAI). • Costs depend on the LLM(s) you choose and scraping usage. • Replace all placeholders like [put your token here] and [put your Telegram Bot Chat ID here] before running. • Respect the target platform’s terms of service when scraping LinkedIn data. What this workflow does Trigger (Google Drive) – Watches a specific folder for newly uploaded lead spreadsheets. Download & Parse – Downloads the file and converts it to structured items (first name, last name, company, LinkedIn URL, email, website). Batch Loop – Processes each row individually. Fetch Activity – Calls Apify LinkedIn Profile Posts (latest post) and records current date for recency checks. Recency Check (LLM) – An OpenAI node returns true/false for “post is from the current year.” Branching • If TRUE → AI Agent (Anthropic) crafts a single, natural reference line based on the recent post. • If FALSE → Apify LinkedIn Profile → AI Agent (Anthropic) crafts a one-liner from profile data (headline/about/current role). Write Back (Google Sheets) – Updates the original sheet by matching on email and writing the personalization field. Notify (Telegram) – Sends a brief completion summary with sheet name and link. Requirements • Google Drive & Google Sheets connections • Apify account + token for LinkedIn scrapers • LLM keys: Anthropic (Claude) and/or OpenAI (you can use one or both) • Telegram bot for notifications (bot token + chat ID) How to use Connect credentials for Google, Apify, OpenAI/Anthropic, and Telegram. Set your folder in the Google Drive Trigger to the one where you’ll drop lead sheets. Map sheet columns to the expected headers (e.g., First Name, Last Name, Company Name for Emails, Person Linkedin Url, Email, Website). Replace placeholders ([put your token here], [put your Telegram Bot Chat ID here]) in the respective nodes. Upload a test spreadsheet to the watched folder and run once to validate the flow. Review results in your sheet (new personalization column) and check Telegram for the completion message. Setup Connect credentials - Google Drive/Sheets, Apify, OpenAI and/or Anthropic, Telegram. Configure the Drive trigger - Select the folder where you’ll upload your lead sheets. Map columns - Ensure your sheet has: First Name, Last Name, Company Name for Emails, Person Linkedin Url, Email, Website. Replace placeholders - In HTTP nodes: Bearer [put your token here]. In Telegram node: [put your Telegram Bot Chat ID here] (Optional) Adjust the recency rule - Current logic checks for current-year posts; change the prompt if you prefer 30-day windows. How to use Upload a test spreadsheet to the watched Drive folder. Execute the workflow once to validate. Open your Google Sheet to see the new personalization column populated. Check Telegram for the completion summary. Customizing this template • Data sources: Add company news, website content, or X/Twitter as fallback signals. • LLM choices: Use only Anthropic or only OpenAI; tweak temperature for tone. • Destinations: Write to a CRM (HubSpot/Salesforce/Airtable) instead of Sheets. • Notifications: Swap Telegram for Slack/Email/Discord. Who it’s for • Sales & SDR teams needing authentic, scalable personalization for cold outreach. • Lead gen agencies enriching spreadsheets with ready-to-use openers. • Marketing & growth teams improving reply rates by referencing real prospect activity. Limitations & compliance • LinkedIn scraping may be rate-limited or blocked; follow platform ToS and local laws. • Costs vary with scraping volume and LLM usage. Need help customizing? Contact me for consulting and support: LinkedIn

Employee Directory Sync – Microsoft Teams & Coda ⚠️ COMMUNITY TEMPLATE DISCLAIMER: This is a community-contributed template that uses ScrapeGraphAI (a community node). Please ensure you have the ScrapeGraphAI community node installed in your n8n instance before using this template. This workflow keeps your employee directory perfectly synchronized across your HRIS (or any REST-compatible HR database), Microsoft Teams, Coda docs, and Slack channels. It automatically polls the HR system on a schedule, detects additions or updates, and propagates those changes to downstream tools so everyone always has the latest employee information. Pre-conditions/Requirements Prerequisites An active n8n instance (self-hosted or n8n cloud) ScrapeGraphAI community node installed A reachable HRIS API (BambooHR, Workday, Personio, or any custom REST endpoint) Existing Microsoft Teams workspace and a team/channel for announcements A Coda account with an employee directory table A Slack workspace and channel where directory updates will be posted Required Credentials Microsoft Teams OAuth2** – To post adaptive cards or messages Coda API Token** – To insert/update rows in your Coda doc Slack OAuth2** – To push notifications into a Slack channel HTTP Basic / Bearer Token** – For your HRIS REST endpoint ScrapeGraphAI API Key** – (Only required if you scrape public profile data) HRIS Field Mapping | HRIS Field | Coda Column | Teams/Slack Field | |------------|-------------|-------------------| | firstName| First Name| First Name | | lastName | Last Name | Last Name | | email | Email | Email | | title | Job Title | Job Title | | department| Department| Department | (Adjust the mapping in the Set and Code nodes as needed.) How it works This workflow keeps your employee directory perfectly synchronized across your HRIS (or any REST-compatible HR database), Microsoft Teams, Coda docs, and Slack channels. It automatically polls the HR system on a schedule, detects additions or updates, and propagates those changes to downstream tools so everyone always has the latest employee information. Key Steps: Schedule Trigger**: Fires daily (or at your chosen interval) to start the sync routine. HTTP Request**: Fetches the full list of employees from your HRIS API. Code (Delta Detector)**: Compares fetched data with a cached snapshot to identify new hires, departures, or updates. IF Node**: Branches based on whether changes were detected. Split In Batches**: Processes employees in manageable sets to respect API rate limits. Set Node**: Maps HRIS fields to Coda columns and Teams/Slack message fields. Coda Node**: Upserts rows in the employee directory table. Microsoft Teams Node**: Posts an adaptive card summarizing changes to a selected channel. Slack Node**: Sends a formatted message with the same update. Sticky Note**: Provides inline documentation within the workflow for maintainers. Set up steps Setup Time: 10-15 minutes Import the workflow into your n8n instance. Open Credentials tab and create: Microsoft Teams OAuth2 credential. Coda API credential. Slack OAuth2 credential. HRIS HTTP credential (Basic or Bearer). Configure the HRIS HTTP Request node Replace the placeholder URL with your HRIS endpoint (e.g., https://api.yourhr.com/v1/employees). Add query parameters or headers as required by your HRIS. Map Coda Doc & Table IDs in the Coda node. Select Teams & Slack channels in their respective nodes. Adjust the Schedule Trigger to your desired frequency. Optional: Edit the Code node to tweak field mapping or add custom delta-comparison logic. Execute the workflow manually once to verify proper end-to-end operation. Activate the workflow. Node Descriptions Core Workflow Nodes: Schedule Trigger** – Initiates the sync routine at set intervals. HTTP Request (Get Employees)** – Pulls the latest employee list from the HRIS. Code (Delta Detector)** – Stores the previous run’s data in workflow static data and identifies changes. IF (Has Changes?)** – Skips downstream steps when no changes were detected, saving resources. Split In Batches** – Iterates through employees in chunks (default 50) to avoid API throttling. Set (Field Mapper)** – Renames and restructures data for Coda, Teams, and Slack. Coda (Upsert Rows)** – Inserts new rows or updates existing ones based on email match. Microsoft Teams (Post Message)** – Sends a rich adaptive card with the update summary. Slack (Post Message)** – Delivers a concise change log to a Slack channel. Sticky Note** – Embedded documentation for quick reference. Data Flow: Schedule Trigger → HTTP Request → Code (Delta Detector) Code → IF (Has Changes?) If No → End If Yes → Split In Batches → Set → Coda → Teams → Slack Customization Examples Change Sync Frequency // Inside Schedule Trigger { "mode": "everyDay", "hour": 6, "minute": 0 } Extend Field Mapping // Inside Set node items[0].json.phone = item.phoneNumber ?? ''; items[0].json.location = item.officeLocation ?? ''; return items; Data Output Format The workflow outputs structured JSON data: { "employee": { "id": "123", "firstName": "Jane", "lastName": "Doe", "email": "jane.doe@example.com", "title": "Senior Engineer", "department": "R&D", "status": "New Hire", "syncedAt": "2024-05-08T10:15:23.000Z" }, "destination": { "codaRowId": "row_abc123", "teamsMessageId": "msg_987654", "slackTs": "1715158523.000200" } } Troubleshooting Common Issues HTTP 401 from HRIS API – Verify token validity and that the credential is attached to the HTTP Request node. Coda duplicates rows – Ensure the key column in Coda is set to “Email” and the Upsert option is enabled. Performance Tips Cache HRIS responses in static data to minimize API calls. Increase the Split In Batches size only if your API rate limits allow. Pro Tips: Use n8n’s built-in Version Control to track mapping changes over time. Add a second IF node to differentiate between “new hires” and “updates” for tailored announcements. Enable Slack’s “threaded replies” to keep your #hr-updates channel tidy.

How it works This workflow automatically detects completed orders in PostgreSQL and prepares them for AI-based post-purchase communication. It enriches each order with customer, product, and payment data, then generates a personalized message using an AI agent. The message is delivered via email and WhatsApp and finally logged in Google Sheets for tracking and auditing. Step-by-step Step 1: Fetch and prepare completed orders for AI processing** Postgres Trigger – Watches the orders table for updates and initiates the workflow. Postgres (Execute query) – Fetches only orders marked as completed. Split In Batches – Loops through completed orders safely and sequentially. Postgres (Execute query) – Retrieves full customer, product, and payment details using joins. AI Agent – Generates a personalized post-purchase message using order data. Groq Chat Model – Supplies the language model used by the AI agent. Merge – Combines AI-generated text with database results for downstream use. Step 2: Deliver messages and log post-purchase communication** Code – Formats AI output into clean email and WhatsApp message templates. Gmail – Sends the post-purchase email to the customer. WhatsApp – Sends the same message via WhatsApp. Set – Flags email and WhatsApp messages as successfully sent. Google Sheets – Appends customer, order, and communication details. Wait – Pauses before continuing to process the next completed order. Why use this? Automates post-purchase communication with zero manual effort. Ensures consistent, personalized messaging across email and WhatsApp. Adapts message tone automatically based on payment status. Creates a centralized audit log in Google Sheets. Scales easily as order volume grows.

What Problem Does It Solve? Staying up-to-date with AI and LLM developments requires reading dozens of articles every week. Manual research is time-consuming and often leads to “information overload” or reading low-quality clickbait. Important technical breakthroughs often get buried under marketing fluff. This workflow solves these by: Leveraging Decodo to instantly find and scrape high-quality organic articles (automatically filtering out YouTube/video noise). Using AI to read and summarize every article individually. Using an "Analyst Agent" to score news by relevance and write a single, high-quality intelligence report. How to Configure It Decodo & API Setup Decodo:** Connect your Decodo credentials. This is the core engine that handles the high-precision Google Search and content scraping. OpenAI:** Connect your OpenAI API key (GPT-4o or 4.1-mini recommended for best analysis). Gmail:** Connect a Google Service Account or Gmail OAuth to send the emails. Search Configuration Open the Set Search Config node. Edit the search_query value to match your niche (e.g., "Latest Large Language Model benchmarks" or "Generative AI in Healthcare"). How It Works Trigger:** The workflow wakes up once a week (customizable). Search (Powered by Decodo):** It searches Google using Decodo's organic results filter to ensure only high-quality reading material is selected. Scraping:** It visits every URL found and extracts the raw text, cleaning up HTML tags. Summarization:** An LLM reads each article individually to extract key technical points. Analyst Agent:** Reviews all summaries, assigns a "Relevance Score", and compiles the final newsletter. Delivery:** The final report is emailed to you immediately. Customization Ideas Change the topic to any industry (Crypto, Finance, Sports). Swap the AI model for Claude or DeepSeek. Log the summaries into a Notion database. If you need any help Get In Touch

How It Works Automates revenue data validation and intelligent anomaly detection with scheduled weekly processing. Fetches revenue data, applies dual OpenAI models for categorization and anomaly detection, identifies outliers or suspicious patterns, and synchronizes clean data with accounting software. Includes correction workflow through Connection Agent for data quality remediation. System generates compliance summaries and automatically sends reports to tax agents via Gmail. Designed for accounting firms, tax professionals, and finance teams requiring enterprise-grade data validation, fraud detection, and regulatory compliance without manual review bottlenecks. Setup Steps Configure OpenAI API keys for categorization and anomaly detection models Connect revenue data source and accounting software via Connection Agent Define anomaly detection thresholds and categorization Set email templates for tax agent communication Configure weekly schedule trigger timing Prerequisites OpenAI API key, accounting software credentials, revenue data source connectivity, Gmail account Use Cases Accounting firm multi-client processing, monthly/quarterly tax compliance Customization Adjust anomaly thresholds per business rules, customize categorization rules for industry standards Benefits Reduces data validation time by 85%, eliminates manual categorization errors, detects fraud patterns

Description This workflow automates the first line of customer support by intelligently drafting email replies. It bridges the gap between your CRM (Supabase), your technical documentation (Vector Store), and your inbox (Outlook). By analyzing the sender's identity and the technical content of the query, it ensures that every draft reply is personalized, accurate, and follows strict business rules. How It Works Trigger: Monitors a Microsoft Outlook inbox for new incoming messages. Contact Enrichment: Queries a Supabase contacts table using the sender's email to retrieve their name, organization, and department. Context Construction: A Code node prepares a "Chat Input" that includes the email body, sender metadata, and specific brand "Business Rules." AI Intelligence (RAG): An AI Agent (GPT-4o) analyzes the request. If technical details are required, the Agent uses a Supabase Vector Store tool to retrieve semantic matches from your product manuals. Draft Creation: The AI generates an HTML-formatted reply which is saved as a Draft in Outlook for manual review. Audit Trail: Logs the intent, urgency, and outcome into a Google Sheet for performance tracking. Requirements Microsoft Outlook:** Business/Office 365 account. Supabase:** * A table for contact lookups. A vector-enabled database containing document embeddings. OpenAI API:** For the GPT-4o model and embeddings. Google Sheets:** To maintain an execution summary log. Setup Instructions Import: Paste the workflow JSON into your n8n canvas. Credentials: Set up and select credentials for Outlook, OpenAI, Supabase, and Google Sheets. Placeholder Updates: Fetch Contact Info: Set the table name to your specific CRM table. Vector Store: Update the table name and query function to match your Supabase Vector Store setup. Log to Google Sheets: Replace the Document ID and Sheet Name with your specific spreadsheet details. Persona Tuning: Open the AI Support Agent node and the Build AI Prompt code node to replace the [YOUR_COMPANY] and [YOUR_NAME] placeholders with your actual brand identity. Customization Ideas Urgency Routing:** Add an If node after the Agent to send a Slack or Teams notification if the AI detects the urgency is "high." Attachments:** Modify the Outlook node to include specific PDF brochures based on the primary_product_codes identified by the AI. Human-in-the-loop:** Use n8n "Wait for Webhook" or "Manual Approval" nodes if you want to approve the draft within the n8n UI before it hits the Outlook drafts folder.

Who’s it for Perfect for marketing agencies that manage multiple Facebook ad accounts and want to automate their weekly reporting. It eliminates manual data collection, analysis, and client updates by delivering a ready-to-share PDF report. How it works Every Monday, the workflow: Fetches the previous week’s campaign metrics from the Facebook Graph API. Formats and summarizes each campaign’s performance using OpenAI. Merges all summaries into one comprehensive report with insights and next-week suggestions. Converts the report into a polished PDF using any PDF generation API. Sends the final PDF report automatically to the client via Gmail. How to set up Connect your Facebook, OpenAI, and Gmail accounts in n8n. Add credentials for your preferred PDF generator (e.g., PDFCrowd, Placid, etc.). Open the “Set Node” to customize recipient email, date range, or report text. Requirements Facebook Graph API access token OpenAI API key Gmail credentials API key for your PDF generation service How to customize You can modify the trigger day, personalize the report design, or include additional analytics such as ROAS, CPC, or conversion data for deeper insights.

How it works This workflow automatically generates a new haiku poem every morning using AI, formats it in 5-7-5 structure, saves it to Google Docs, and sends it to your email inbox. Workflow steps: Schedule Trigger – Runs daily at 7:00 AM. AI Agent – Asks AI to output four words (kigo, noun, verb1, verb2) in JSON format. Code in JavaScript – Builds a 5-7-5 haiku using the AI-generated words and sets today’s title. Edit Fields – Prepares document fields (title and body) for Google Docs. Create a document – Creates a new Google Document for the haiku. Prepare Append – Collects the document ID and haiku text for appending. Update a document – Inserts the haiku into the existing Google Doc. Send a message – Sends the haiku of the day to your Gmail inbox. OpenRouter Chat Model – Connects the OpenRouter model used by the AI Agent. Setup steps Connect your OpenRouter API key as a credential (used in the AI Agent node). Update your Google Docs folder ID and Gmail account credentials. Change the email recipient address in the “Send a message” node. Adjust the Schedule Trigger time as you like. Run the workflow once to test and verify document creation and email delivery. Ideal for Writers and poets who want daily creative inspiration. Individuals seeking a fun morning ritual. Educators demonstrating AI text generation in a practical example. ⚙️ Note: Each node includes an English Sticky Note above it for clarity and documentation.

How it works: This n8n workflow automates communication with meeting invitees to decrease no-show rates by sending timely email and WhatsApp reminders, and a clarification request if more information is needed to prepare the meeting. Step-by-step: The workflow is triggered by an incoming email notification from Calendly about a newly scheduled meeting. It uses AI to extract key meeting data from the email content. It checks if the invitee didn't provide sufficient information, and, if there is a need for more information, sends a clarification request email. It calculates the waiting time required for the 24-hour and 1-hour reminders. It uses an If node to determine the correct waiting path based on the meeting time. It uses Wait nodes for timing the reminders correctly. Finally, it sends a reminder email and a WhatsApp reminder before the meeting. Customization Options: Replace Google Gemini with your preferred LLM model (though Gemini works on the free tier). Tailor email and WhatsApp messages to speak your brand's language. Replace Twillio node to WhatsApp node to be a completly free usage flow.