by Milo Bravo
Client Onboarding Automation: Google Forms → GPT-4o → ClickUp & Gmail Who is this for? Consultants, agencies, freelancers, and SaaS teams handling client onboarding who want automated workspaces + AI task lists without manual setup. What problem is this workflow solving? Onboarding chaos wastes hours: Manual folder/task creation per client Inconsistent project scopes and timelines Forgotten welcome emails and links No standardized AI-scoped task lists This workflow auto-creates everything from intake form to production-ready ClickUp boards. What this workflow does: Trigger: Google Forms submission + proposal PDF AI Analysis: GPT-4o extracts scope → generates 20-30 tasks Google Drive: Client folder creation ClickUp: Folder + lists + detailed tasks with assignees/dues Gmail: Personalized welcome with all links Bonus: Audit trail in Sheets for tracking Setup (5 minutes) Google Forms: Intake + PDF upload OpenAI: API key (GPT-4o-mini) ClickUp: API + Team/Space IDs Google Drive: OAuth2 + parent folder Gmail: OAuth2 credentials Fully configurable via env vars—no hardcoded IDs. How to customize Tasks: Adjust AI prompt for your SOP/industry Tools: Swap ClickUp for Asana/Trello Email: Add Calendly/Zoom + branding Scale: Webhook for 100s clients/month ROI: 4-6 hours saved per client 100% consistent onboarding 30% faster project starts Zero manual workspace creation Need help customizing?: Contact me for consulting and support: LinkedIn / Message Keywords: client onboarding, ClickUp automation,
by Automate With Marc
🧠 RAG-Based Customer Support Agent (GPT-5 + Telegram) Description: This workflow builds a powerful Retrieval-Augmented Generation (RAG) Customer Support Agent that interacts with users directly through Telegram using the GPT-5 model. It combines real-time conversational capabilities with context-aware responses by leveraging vector search via Pinecone, making it ideal for automated, intelligent support systems. Watch Video Tutorial Build on Workflows Like These: https://www.youtube.com/@Automatewithmarc 💬 Key Features: Telegram Integration: Listens to customer queries via the Telegram Trigger node and sends back intelligent responses in the same chat. GPT-5 Agent (LangChain): A powerful AI agent node orchestrates the conversation using OpenAI's GPT-5 model. Contextual Memory: A Memory Buffer stores the last 15 interactions per user to provide more personalized and coherent multi-turn conversations. RAG with Pinecone: Integrates with Pinecone to fetch relevant answers from your “Customer FAQ” vector namespace, enabling grounded and accurate responses. Embeddings Generation: Uses OpenAI’s Embeddings node to process and vectorize documents for retrieval. End-to-End AI Pipeline: Connects all components from input to output, providing seamless and intelligent customer support. 🔧 Tech Stack: GPT-5 via OpenAI API Pinecone vector store (namespace: Customer FAQ) Telegram Bot API LangChain agent, memory, and embedding tools n8n self-hosted or cloud instance 📌 Ideal Use Cases: Automated customer support for e-commerce, SaaS, or community support FAQ bots with up-to-date product or policy documents Multilingual support agents (customizable via GPT-5) 🛠️ Setup Instructions: Set up your Telegram bot and insert credentials. Add your OpenAI and Pinecone API keys. Upload or index your support documents into the Customer FAQ namespace on Pinecone. Deploy and test your Telegram bot.
by Trilox
> ⚠️ This template uses the Trilox community node (n8n-nodes-trilox) and requires self-hosted n8n. Who is this for n8n developers building Telegram chatbots who need to take over from the bot when it fails — without the customer getting double replies. How it works Customer sends a message on Telegram (text or voice) The message is recorded to Trilox and the handler status is checked If the bot is in control → the AI Agent responds with a structured escalation flag After the AI responds, the handler is checked again — catching the race condition where a human took over while the AI was thinking If the AI decides a human is needed → the conversation is escalated and the customer is notified A human takes over from the Trilox inbox → the bot goes completely silent The human replies from Trilox → the reply is forwarded to Telegram Human hands back → bot resumes automatically How to set up Install the Trilox community node (Settings → Community Nodes → Install n8n-nodes-trilox) Create a free account at trilox.io Create a Project → App (inbox) → API Key in Trilox Create a Telegram bot via @BotFather and get the API token Set up credentials for Trilox, Telegram, and OpenAI in n8n In all Trilox nodes, select your App from the dropdown Update the AI Agent system prompt with your business info and escalation rules Activate the workflow Requirements Self-hosted n8n (community nodes required) Trilox account (trilox.io) — free plan available Telegram Bot (via @BotFather) OpenAI API key (or any LLM provider) How to customize Escalation rules:** Edit the system prompt to define when is_human_required should be true (refunds, complaints, billing) Different LLM:** Replace OpenAI with OpenRouter, Anthropic, or any compatible model Add channels:** The Channel Router has placeholders for WhatsApp, Messenger, Instagram, Widget, and API Remove voice:** Delete the voice branch if you don't need it Add knowledge base:** Give the AI Agent tools (Google Docs, Notion, vector store)
by David Olusola
📧 Master Your First AI Email Agent with Smart Fallback! Welcome to your hands-on guide for building a resilient, intelligent email support system in n8n! This workflow is specifically designed as an educational tool to help you understand advanced AI automation concepts in a practical, easy-to-follow way. 🚀 What You'll Learn & Build: This powerful template enables you to create an automated email support agent that: Monitors Gmail** for new customer inquiries in real-time. Processes requests** using a primary AI model (Google Gemini) for efficiency. Intelligently falls back to a secondary AI model** (OpenAI GPT) if the primary model fails or for more complex queries, ensuring robust reliability. Generates personalized and helpful replies** automatically. Logs every interaction** meticulously to a Google Sheet for easy tracking and analysis. 💡 Why a Fallback Model is Game-Changing (and Why You Should Learn It): Unmatched Reliability (99.9% Uptime):** If one AI service experiences an outage or rate limits, your automation seamlessly switches to another, ensuring no customer email goes unanswered. Cost Optimization:** Leverage more affordable models (like Gemini) for standard queries, reserving premium models (like GPT) only when truly needed, significantly reducing your API costs. Superior Quality Assurance:** Get the best of both worlds – the speed of cost-effective models combined with the accuracy of more powerful ones for complex scenarios. Real-World Application:** This isn't just theory; it's a critical pattern for building resilient, production-ready AI systems. 🎓 Perfect for Beginners & Aspiring Automators: Simple Setup:** With drag-and-drop design and pre-built integrations, you can get this workflow running with minimal configuration. Just add your API keys! Clear Educational Value:** Learn core concepts like AI model orchestration strategies, customer service automation best practices, and multi-model AI implementation patterns. Immediate Results:** See your AI agent in action, responding to emails and logging data within minutes of setup. 🛠️ Getting Started Checklist: To use this workflow, you'll need: A Gmail account with API access enabled. A Google Sheets document created for logging. A Gemini API key (your primary AI model). An OpenAI API key (your fallback AI model). An n8n instance (cloud or desktop). Embark on your journey to building intelligent, resilient automation systems today!
by Automate With Marc
🔗 Slack + Bitly UTM Generator — Powered by OpenAI Description: This no-code n8n workflow transforms how marketing teams generate Bitly links with UTM parameters — directly from Slack. Powered by AI and fully automated, this system extracts relevant campaign data from a Slack message, creates a clean Bitly shortlink with UTM tags, and logs everything to a Google Sheet for tracking and reporting. Perfect for growth marketers, content teams, and anyone tired of manually building UTM-tagged links. If you like to follow step-by-step build of workflows like these, check out: https://www.youtube.com/@Automatewithmarc ⚙️ How It Works 🟢 Slack Trigger The workflow starts when a user mentions the bot in a Slack channel (e.g., @BitlyBot link this for IG campaign). 🧠 AI Agent (LangChain) Uses GPT-4o-mini to infer UTM values (e.g., utm_source, utm_medium, utm_campaign) Normalizes short forms like "IG" to "instagram" Follows UTM naming conventions (e.g., lowercase, underscore-separated) 🔍 Information Extractor Pulls cleanly structured UTM data from the AI response to prep for Bitly. 🔗 Bitly Tool Node Generates a short link using the inferred target URL + UTM values. 📋 Google Sheets Logger Automatically appends the full details (Bitly link, UTM parameters, campaign owner) to a Google Sheet for easy access. 📢 Slack Response Replies in-thread with the new Bitly link and campaign details, formatted clearly for the user. 🛑 Error Handling If Bitly link generation fails, the workflow gracefully stops with an error message. 🔧 Tools & Services Used Slack (Trigger + Response) LangChain AI Agent (with GPT-4o-mini) Bitly (via Bitly Tool Node) Google Sheets (auto-log generated links) OpenAI GPT-4o-mini (Language model for prompt understanding) 💡 Use Cases 🔗 Instantly create UTM-tagged links for campaigns 📊 Maintain a central Bitly + UTM link database in Google Sheets 🧠 Use AI to reduce manual tagging and formatting errors 🤝 Empower your team to request links via Slack, no forms needed ✅ Setup Instructions Slack: Set up a Slack bot and connect it using Slack Trigger and Slack response nodes. Bitly API: Generate a Bitly access token and set up credentials in the Bitly node. OpenAI / LangChain: Connect your GPT-4o or GPT-4 API key to the OpenAI Chat Model nodes. Google Sheets: Use OAuth2 credentials to connect to your Google Sheet. Make sure the sheet has matching columns for UTM parameters (sample headers included in the node schema).
by Ali Khosravani
This workflow enriches your WordPress articles by automatically adding an AI-generated heading and a short concluding paragraph. It ensures each post ends with valuable, engaging content to improve user satisfaction, branding, and SEO. How It Works Fetches published articles from your WordPress site via the REST API. Cleans and formats the article text for processing. Sends the content to OpenAI with a structured prompt. AI generates a new heading + 3-line conclusion tailored to the article. Appends the generated text to the original content. Updates the article back in WordPress automatically. Requirements n8n version: 1.49.0 or later (recommended). Active OpenAI API key. WordPress REST API enabled. WordPress API credentials (username + application password). Setup Instructions Import this workflow into n8n. Go to Credentials and configure: OpenAI API (API key). WordPress API (username + application password). Replace https://example.com with your site’s URL. Run manually or schedule it to enhance content automatically. Categories AI & Machine Learning WordPress Content Marketing SEO Tags ai, openai, wordpress, seo, content enhancement, automation, n8n
by Ranjan Dailata
This workflow automates the discovery and structuring of FAQs from real AI search behavior using SE Ranking and OpenAI. It fetches domain-specific AI search prompts and answers, then extracts relevant questions, responses, and source links. Each question is enriched with AI-based intent classification and confidence scoring, and the final output is aggregated into a structured JSON format ready for SEO analysis, content planning, documentation, or knowledge base generation. Who this is for This workflow is designed for: SEO professionals and content strategists building FAQ-driven content Growth and digital marketing teams optimizing for AI Search and SERP intent Content writers and editors looking for data-backed FAQ ideas SEO automation engineers using n8n for research workflows Agencies producing scalable FAQ and topical authority content What problem this workflow is solving Modern SEO increasingly depends on AI search prompts, user intent, and FAQ coverage, but manually: Discovering real AI search questions Grouping questions by intent Identifying content gaps Structuring FAQs for SEO is slow, repetitive, and inconsistent. This workflow solves that by automatically extracting, classifying, and structuring AI-driven FAQ intelligence directly from SE Ranking’s AI Search data. What this workflow does This workflow automates end-to-end FAQ intelligence generation: Fetches real AI search prompts for a target domain using SE Ranking Extracts: Questions Answers Reference links Applies zero-shot AI classification using OpenAI GPT-4.1-mini Assigns: Intent category (HOW_TO, DEFINITION, PRICING, etc.) Confidence score Aggregates all data into a structured FAQ dataset Exports the final result as structured JSON for SEO, publishing, or automation Setup If you are new to SE Ranking, please signup on seranking.com Prerequisites n8n (Self-Hosted or Cloud)** SE Ranking API access** OpenAI API key (GPT-4.1-mini)** Configuration Steps Configure Credentials SE Ranking using HTTP Header Authentication. Please make sure to set the header authentication as below. The value should contain a Token followed by a space with the SE Ranking API Key. Add OpenAI API credentials Update Input Parameters In the Set the Input Fields node: Target domain Search engine type (AI mode) Region/source Include / exclude keyword filters Result limits and sorting Verify Output Destination Confirm the file path in the Write File to Disk node Or replace it with DB, CMS, or webhook output Execute Workflow Click Execute Workflow Structured FAQ intelligence is generated automatically How to customize this workflow You can easily adapt this workflow to your needs: Change Intent Taxonomy** Update categories in the AI zero-shot classifier schema Refine SEO Focus** Modify keyword include/exclude rules for niche targeting Adjust Confidence Thresholds** Filter low-confidence questions before export Swap Output Destination** Replace file export with: CMS publishing Notion Google Sheets Vector DB for RAG Automate Execution** Add a Cron node for weekly or monthly FAQ updates Summary This n8n workflow transforms AI search prompts into structured, intent-classified FAQ intelligence using SE Ranking and OpenAI GPT-4.1-mini. It enables teams to build high-impact SEO FAQs, content hubs, and AI-ready knowledge bases automatically, consistently, and at scale.
by Marko
📌 Short Overview Automatically sync files from Google Drive into a searchable AI knowledge base with Pinecone, and answer user queries using GPT-4o with conversational memory. ⸻ 🛠️ Workflow Usage Steps 1. Watch Google Drive for file changes Trigger the workflow when a new file is uploaded or an existing file is updated in a specific Google Drive folder. 2. Download and process the file Retrieve the file, split it into smaller text chunks with a Recursive Character Text Splitter, and generate vector embeddings using OpenAI. 3. Store embeddings in Pinecone Save the embeddings in a Pinecone vector database to keep your knowledge base continuously updated and searchable. 4. Search context for chat queries When a user asks a question, query Pinecone for relevant context, combine results with conversational memory, and process them with GPT-4o. 5. Respond with AI-powered answers Provide a concise response (100–200 words) that blends knowledge from your documents with the conversation history. ⸻ ✅ Use Cases • Keep a live, AI-ready knowledge base from your Google Drive files. • Enable team members to query company documents instantly. • Build a personal assistant that stays up to date with your latest uploads. ⚙️ Setup Steps Google Drive • Create a Google Cloud project. • Enable the Google Drive API. • Generate OAuth credentials and connect them in n8n. OpenAI • Sign up at OpenAI. • Copy your API key from the dashboard. • Add it to n8n under Credentials → OpenAI API. Pinecone • Create an account at Pinecone. • Create a new index (e.g., docs-embeddings). • Copy your API key and environment, then add them to n8n under Credentials → Pinecone API. Workflow Configuration • Import this workflow into your n8n instance. • Select the Google Drive folder you want to monitor. • Set the Pinecone index name in the workflow. • Adjust chunk size / overlap in the text splitter if needed. Test the Workflow • Upload a new document to your Google Drive folder. • Run the workflow to confirm embeddings are created and stored in Pinecone. • Ask a sample query and verify the AI returns a context-aware answer.
by Rajeet Nair
Overview This workflow helps sales teams automatically monitor deal health and detect risks early. It pulls deal data from your CRM and combines it with recent email activity. Using AI, it analyzes engagement, identifies objections, and assigns a risk score. High-risk deals are flagged and alerts are sent so your team can take action quickly. How It Works Scheduled Trigger The workflow runs daily to monitor active deals. Configuration Defines key settings like deal stages, email lookback period, and risk threshold. Data Collection Fetches deals from your CRM Retrieves recent email conversations Context Combination Merges deal data and email activity into a single dataset for analysis. AI Analysis AI reviews the combined data to: Identify objections Suggest next steps Detect risk signals Assign a risk score (0–100) CRM Update The workflow updates each deal with: Objections Next steps Risk score Risk summary Risk Evaluation Compares the risk score against a defined threshold. Alerting If the deal is high-risk, a Slack alert is sent to notify the sales team. Setup Instructions Connect HubSpot credentials (for deals) Connect Gmail credentials (for email data) Connect OpenAI credentials (for analysis) Connect Slack credentials (for alerts) Configure the Workflow Configuration node: Set deal stage filters Define email lookback days Set risk score threshold Ensure CRM fields exist for: objections next_steps risk_score risk_summary Test with sample deals Activate the workflow Use Cases Identifying deals at risk before they are lost Tracking customer objections automatically Improving sales follow-up with clear next steps Monitoring engagement across deals Alerting managers about critical deals in real time Requirements HubSpot account (or replace with your CRM) Gmail account (for email data) OpenAI API access Slack workspace (for alerts) n8n instance with proper credentials configured Notes You can adjust the risk threshold based on your sales process. AI prompts can be customized to match your sales methodology. This workflow can be extended to include CRM filters for specific pipelines or teams.
by Vadim Mubi
Meet your automated Lead Gen Specialist. This workflow streamlines cold outreach by scraping local businesses, qualifying them with AI, and delivering them to your sales team instantly via an interactive Telegram bot. It solves the "empty pipeline" problem by fetching fresh leads from Google Maps, checking for duplicates in your Notion CRM, and letting agents "claim" leads with a single click. 💡 Why use this? Automated Sourcing:** Stop manual copy-pasting. It fetches verified business data (Phone, Reviews, Website) directly from Google Maps via Outscraper. Smart Deduplication:** It checks your Notion database first to ensure you never accidentally pitch the same business twice. AI "Icebreakers":** GPT-4 analyzes the reviews to find specific pain points (e.g., "Slow service" -> "Pitch QR Menu"), giving your agents a warm opening line. One-Click Assignment:* Leads are sent to a Telegram group. Agents simply click *"⚡️ Take Lead"**, and the system automatically assigns the deal to them in Notion and updates the chat. ⚙️ How it works Fetch: Takes your query (e.g., "Sushi in London") and gets data via Outscraper. Filter: Checks if the phone number already exists in your Active Deals database. Analyze: AI reads the reviews and writes a personalized sales argument. Notify: Sends a formatted card to the Telegram group. Assign (Loop): Listens for the button click, identifies the agent via their Telegram ID, updates the CRM, and locks the lead. 🛠 Setup Steps This workflow works best with the "AI Sales Coach" Notion system. Get the Notion System: Click here to duplicate the Notion Template Add your team to the "Agents Configuration" database (map Telegram IDs to Notion Users). Connect Databases: In the Notion nodes (Search Duplicate, Create New Lead, Assign Lead), select your duplicated Active Deals database. In the Find Agent node, select your Agents Configuration database. Configure Settings: Open the 📝 CONFIGURATION node. Add your Outscraper API Key. Set your Telegram Chat ID (where leads should be posted). Customize the AI_TONE and MY_SERVICES to fit your product. Connect Accounts: Add credentials for Notion, OpenAI, Telegram, and Outscraper.
by Ivan Maksiuta
What this template does Collects the latest crypto news from multiple RSS feeds, filters and deduplicates them, uses OpenAI GPT-4 to analyze and select the top stories, translates and formats them into Russian, and posts a digest to a Telegram channel or group. The workflow runs automatically on a schedule and ensures all messages fit Telegram’s 4096-character limit. How it works (high level) RSS Sources: Reads fresh items from CoinDesk, Cointelegraph, Decrypt, Cryptobriefing, and Nulltx. Filter & Deduplicate: Keeps only unique items from the last 24 hours. AI Analysis (Crypto Analyst): An OpenAI agent identifies the most important events and selects the best article for each. AI Formatting (SMM Editor): Another OpenAI agent writes a styled digest in Russian with Telegram-compatible HTML formatting. Message Preparation: Long texts are split into safe chunks ≤ 4096 characters. Telegram Post: The digest is posted automatically to your configured Telegram channel or group. Prerequisites n8n Cloud or n8n >= 1.107.4 Credentials: OpenAI (gpt-4o-mini or gpt-4.1-mini) Telegram Bot with rights to post in your target chat Setup (5 minutes) Import this workflow into n8n. Open the Telegram node “Post to Group” and set your chatId (e.g., @your_channel or numeric ID). Connect your OpenAI and Telegram credentials. (Optional) Adjust the Scheduler interval (default: every 3 hours). Run once manually to test, then activate. Customization Add or replace RSS sources. Modify the prompts in Crypto Analyst and SMM Editor to adapt tone, style, or language. Swap out the Telegram node to publish on other platforms (Slack, Discord, etc.).
by Vladimir
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Automated Meeting Bot: Google Meet → AI Summary → Slack How it works Automatically joins Google Meet calls, transcribes conversations, and posts AI-generated summaries to Slack - completely hands-free meeting notes for busy teams. The workflow triggers when a Google Meet starts in your calendar, joins the meeting with a bot, waits for completion, then generates and posts a structured summary to your Slack channel. Set up steps Connect Google Calendar API for meeting detection Set up Vexa.ai account and obtain API key for meeting bot functionality Configure OpenAI API credentials for AI-powered summarization Create Slack bot token and add to desired channel Update calendar ID and Slack channel in workflow settings Test with a sample meeting to verify end-to-end functionality Keep detailed descriptions in sticky notes inside your workflow for easy configuration and troubleshooting.