itemMatching() usage example
This workflow provides a simple example of how to use itemMatching(itemIndex: Number) in the Code node to retrieve linked items from earlier in the workflow.
By n8n TeamBuild a RAG system with automatic citations using Qdrant, Gemini & OpenAI
This workflow implements a Retrieval-Augmented Generation (RAG) system that: Stores vectorized documents in Qdrant, Retrieves relevant content based on user input, Generates AI answers using Google Gemini, Automatically cites the document sources (from Google Drive). --- Workflow Steps Create Qdrant Collection A REST API node creates a new collection in Qdrant with specified vector size (1536) and cosine similarity. Load Files from Google Drive The workflow lists all files in a Google Drive folder, downloads them as plain text, and loops through each. Text Preprocessing & Embedding Documents are split into chunks (500 characters, with 50-character overlap). Embeddings are created using OpenAI embeddings (text-embedding-3-small assumed). Metadata (file name and ID) is attached to each chunk. Store in Qdrant All vectors, along with metadata, are inserted into the Qdrant collection. Chat Input & Retrieval When a chat message is received, the question is embedded and matched against Qdrant. Top 5 relevant document chunks are retrieved. A Gemini model is used to generate the answer based on those sources. Source Aggregation & Response File IDs and names are deduplicated. The AI response is combined with a list of cited documents (filenames). Final output: AI Response Sources: ["Document1", "Document2"] --- Main Advantages End-to-end Automation: From document ingestion to chat response generation, fully automated with no manual steps. Scalable Knowledge Base: Easy to expand by simply adding files to the Google Drive folder. Traceable Responses: Each answer includes its source files, increasing transparency and trustworthiness. Modular Design: Each step (embedding, storage, retrieval, response) is isolated and reusable. Multi-provider AI: Combines OpenAI (for embeddings) and Google Gemini (for chat), optimizing performance and flexibility. Secure & Customizable: Uses API credentials and configurable chunk size, collection name, etc. --- How It Works Document Processing & Vectorization The workflow retrieves documents from a specified Google Drive folder. Each file is downloaded, split into chunks (using a recursive text splitter), and converted into embeddings via OpenAI. The embeddings, along with metadata (file ID and name), are stored in a Qdrant vector database under the collection negozio-emporio-verde. Query Handling & Response Generation When a user submits a chat message, the workflow: Embeds the query using OpenAI. Retrieves the top 5 relevant document chunks from Qdrant. Uses Google Gemini to generate a response based on the retrieved context. Aggregates and deduplicates the source file names from the retrieved chunks. The final output includes both the AI-generated response and a list of source documents (e.g., Sources: ["FAQ.pdf", "Policy.txt"]). --- Set Up Steps Configure Qdrant Collection Replace QDRANTURL and COLLECTION in the "Create collection" HTTP node to initialize the Qdrant collection with: Vector size: 1536 (OpenAI embedding dimension). Distance metric: Cosine. Ensure the "Clear collection" node is configured to reset the collection if needed. Google Drive & OpenAI Integration Link the Google Drive node to the target folder (Test Negozio in this example). Verify OpenAI and Google Gemini API credentials are correctly set in their respective nodes. Metadata & Output Customization Adjust the "Aggregate" and "Response" nodes if additional metadata fields are needed. Modify the "Output" node to format the response (e.g., changing Sources: {{...}} to match your preferred style). Testing Trigger the workflow manually to test document ingestion. Use the chat interface to verify responses include accurate source attribution. Note: Replace placeholder values (e.g., QDRANTURL) with actual endpoints before deployment. --- Need help customizing? Contact me for consulting and support or add me on Linkedin.
By DavideMulti platform content generator from YouTube using AI & RSS
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Multi Platform Content Generator from YouTube using AI & RSS This workflow automates content generation by monitoring YouTube channels, extracting transcripts via AI, and creating platform-optimized content for LinkedIn, X/Twitter, Threads, and Instagram. Ideal for creators, marketers, and social media managers aiming to scale content production with minimal effort. ✨ Key Features 🔔 Automated YouTube Monitoring via RSS feed 🧠 AI-Powered Transcript Extraction using Supadata API ✍️ Multi-Platform Content Generation with OpenRouter AI 🎯 Platform Optimization based on tone and character limits 📬 Telegram Notification for easy preview 📊 Centralized Data Management via Google Sheets > 🗂️ All video data, summaries, and generated content are tracked and stored in a single, centralized Google Sheets template > This ensures full visibility, easy access, and smooth collaboration across your team. --- ⚙️ Workflow Components 🧭 Channel Monitoring Schedule Trigger: Initiates workflow periodically Google Sheets (Read): Pulls YouTube channel URLs HTTP Request + HTML Parser: Extracts channel IDs from URLs RSS Reader: Fetches latest video metadata 🧾 Content Processing Supadata API: Extracts transcript from YouTube video OpenRouter AI: Summarizes transcript + generates content per platform Conditional Check: Prevents duplicate content by checking existing records 📤 Multi-Platform Output LinkedIn: Story-driven format (≤ 1300 characters) X/Twitter: Short, punchy copy (≤ 280 characters) Threads: Friendly, conversational Instagram: Short captions for visual posts 🗃️ Data Management Google Sheets (Write): Stores video metadata + generated posts Telegram Bot: Sends content preview ID Tracking: Avoids reprocessing using video ID --- 🔐 Required Credentials Google Sheets OAuth2 Supadata API OpenRouter API Telegram Bot Token & Chat ID --- 🎁 Benefits ⌛ Save Time: Automates transcript + content generation 🔊 Consistent Tone: Adjust AI prompts for brand voice 📡 Multi-Platform Ready: One video → multiple formats 📂 Centralized Logs via Google Sheets: Easily track, audit, and collaborate 🚀 Scalable: Handle many channels with ease
By Budi SJScrape LinkedIn jobs with Gemini AI and store in Google Sheets using RSS
What Problem Does it Solve This workflow automates the process of finding and collecting job postings from LinkedIn, eliminating the need for manual job searching. It’s designed to save time and ensure you don’t miss out on new opportunities by automatically populating a spreadsheet with key job details. Key Features Automated Data Collection: The workflow pulls job posts from a LinkedIn search via an RSS feed. Intelligent Data Extraction: It scrapes the full job description and uses AI to summarize the key benefits and job responsibilities into a concise format. Centralized Database: All collected and processed information is automatically saved to a Google Sheet, providing a single source of truth for your job search. How It Works The workflow starts when manually triggered. It reads the job posts from a given RSS feed, processing each one individually. For each job, it fetches the full webpage content to extract structured data. This data is then cleaned and passed to an AI model, which generates a brief summary of the job and its benefits. Finally, a new row is either added or updated in a Google Sheet with all the collected details, including the job title, company name, and AI-generated summary. Configuration & Customization This workflow is highly customizable to fit your specific needs. RSS Feed: To get started, you'll need to provide the RSS feed URL for your desired LinkedIn job search. We can help you set this up. AI Model: The workflow uses Google Gemini by default, but it can be adjusted to work with other AI platforms. Data Destination: The output is configured to a Google Sheet, but it can easily be changed to a different platform like Notion or a CRM. AI Prompting: The AI's instructions are customizable, so you can tailor the output to extract different information or match a specific tone. If you need any help Get In Touch
By Abdullah AlshiekhComprehensive customer support with OpenAI O3 + GPT-4.1-mini multi-agent team
Support Director Agent with Customer Support Team Description Complete AI-powered customer support department with a Support Director agent orchestrating specialized support team members for comprehensive customer service operations. Overview This n8n workflow creates a comprehensive customer support department using AI agents. The Support Director agent analyzes support requests and delegates tasks to specialized agents for tier 1 support, technical assistance, customer success, knowledge management, escalation handling, and quality assurance. Features Strategic Support Director agent using OpenAI O3 for complex support decision-making Six specialized support agents powered by GPT-4.1-mini for efficient execution Complete customer support lifecycle coverage from first contact to resolution Automated technical troubleshooting and documentation creation Customer success and retention strategies Escalation management for priority issues Quality assurance and performance monitoring Team Structure Support Director Agent: Strategic support oversight and task delegation (O3 model) Tier 1 Support Agent: First-line support, basic troubleshooting, account assistance Technical Support Specialist: Complex technical issues, API debugging, integrations Customer Success Advocate: Onboarding, feature adoption, retention strategies Knowledge Base Manager: Help articles, FAQs, documentation creation Escalation Handler: Priority issues, VIP customers, crisis management Quality Assurance Specialist: Support quality monitoring, performance analysis How to Use Import the workflow into your n8n instance Configure OpenAI API credentials for all chat models Deploy the webhook for chat interactions Send support requests via chat (e.g., "Customer can't connect to our API endpoint") The Support Director will analyze and delegate to appropriate specialists Receive comprehensive support solutions and documentation Use Cases Complete Support Cycle: Inquiry triage → Resolution → Follow-up → Quality review Technical Documentation: API troubleshooting guides, integration manuals Customer Onboarding: Welcome sequences, feature tutorials, training materials Escalation Management: VIP support protocols, complaint resolution procedures Quality Monitoring: Response evaluation, team performance analytics Knowledge Base: Self-service content creation, FAQ optimization Requirements n8n instance with LangChain nodes OpenAI API access (O3 for Support Director, GPT-4.1-mini for specialists) Webhook capability for chat interactions Optional: Integration with CRM, helpdesk, or ticketing systems Cost Optimization O3 model used only for strategic Support Director decisions GPT-4.1-mini provides 90% cost reduction for specialist tasks Parallel processing enables simultaneous agent execution Solution template library reduces redundant response generation Integration Options Connect to helpdesk systems (Zendesk, Freshdesk, Intercom, etc.) Integrate with CRM platforms (Salesforce, HubSpot, etc.) Link to knowledge base systems (Confluence, Notion, etc.) Connect to monitoring tools for proactive support Building Blocks Disclaimer Important Note: This workflow is designed as a foundational building block for your customer support automation. While it provides a comprehensive multi-agent framework, you may need to customize prompts, add specific integrations, or modify agent behaviors to match your exact business requirements and support processes. Consider this a starting point that can be extended and tailored to your unique customer support needs. Contact & Resources Website: nofluff.online YouTube: @YaronBeen LinkedIn: Yaron Been Tags CustomerSupport HelpDesk TechnicalSupport CustomerSuccess SupportAutomation QualityAssurance KnowledgeManagement EscalationManagement ServiceExcellence CustomerExperience n8n OpenAI MultiAgentSystem SupportTech CX Troubleshooting CustomerCare SupportOps
By Yaron BeenStacey – your Telegram AI assistant (powered by MCP, Gemini & Google tools)
> This n8n template builds Stacey, an AI assistant that runs inside Telegram. Stacey listens to your messages, understands what you want using AI, and intelligently routes commands to MCP-connected tools — like Gmail, Google Calendar, a blog writer, and more. > > For optimal performance, we recommend using OpenAI’s GPT-4o model. In this template, Google Gemini is used as a free alternative. --- 💡 Who is this for? This workflow is designed for: AI tool creators and automation builders Entrepreneurs who want an intelligent Telegram assistant Support and scheduling teams who use Google tools Agencies that build & resell AI automations Users looking to automate everyday actions like emails, scheduling, blog writing, and contact lookups --- 🧠 What this workflow does Listens to Telegram messages (text and voice) Transcribes audio using Whisper (optional) Uses Stacey, an AI agent powered by Gemini (or GPT-4o if you upgrade), to: Understand the user's intent Choose the correct tool using MCP logic Execute tasks using Gmail, Google Calendar, blog writer, and more Responds to the user naturally with confirmations and outputs --- ⚙️ Prerequisites Before using this workflow, make sure you have: A self-hosted or cloud-based n8n instance A Telegram Bot Token from @BotFather Google OAuth2 credentials for: Gmail Google Calendar Optional: OpenAI or Whisper API key for voice transcription Optional: Tavily API key for live web search Gemini (Google AI) is preconfigured in the template but can be swapped --- 🚀 Step-by-Step Setup ✅ Step 1: Add Required Credentials in n8n Go to Settings → Credentials and add: Telegram API: Your bot token from BotFather Google OAuth2: Gmail: Scope https://www.googleapis.com/auth/gmail.modify Calendar: Scope https://www.googleapis.com/auth/calendar Gemini / Palm API: Used for the language model (Optional) OpenAI Whisper: For voice transcription (Optional) Tavily: For real-time internet searches --- ✅ Step 2: Import the Workflow Go to n8n Click Workflows → Import from File Upload ai_assistant.json Connect your saved credentials to the correct nodes: Telegram Trigger & Sender Gmail, Calendar, Tavily, Gemini, Whisper ✅ Step 2.5: Import the Content Creator Sub-Workflow The Content Creator is implemented as a modular sub-workflow and invoked through the Map Server as part of the MCP logic. To set it up: Go to Workflows → Import from File Upload contentcreatortool.json (provided in your files) Save it with a name like “Content Creator Tool” 🔗 Integration with MCP: This tool is triggered via the MCP Map Server using an Execute Workflow node The AI agent chooses this tool when the user request involves writing blog posts, emails, product descriptions, etc. Make sure the tool ID or name in the Map Server matches what the AI agent uses in its logic You can customize this sub-workflow to: Adjust writing prompts (e.g., tone, format, target audience) Add branching for different content types (e.g., blog vs. email) Send outputs directly to Gmail, Google Docs, or Sheets --- ✅ Step 3: Set Up Your Telegram Bot Talk to @BotFather Use /newbot to create a bot and get your token Paste this token into: Telegram Trigger node (Telegram Trigger1) Telegram Send Message node (Response1) Make sure your bot’s privacy is set correctly (use /setprivacy) --- ✅ Step 4: Customize Your Assistant’s Personality Open the “AI Agent” node In the systemMessage field, you'll find a prompt that defines Stacey: Her role is to delegate user requests to the right MCP tool Includes examples, tone, rules, and logic You can customize Stacey’s: Name Behavior Supported tools --- ✅ Step 5: Define Your MCP Tools (if extending) This template includes: Send Email Reply to Email Get Emails Label Emails Create/Update/Delete Events Content Creator Search Web with Tavily Calculator To extend: Add a new tool node Link it to MCP Server Trigger Reference it in the prompt in AI Agent node --- ✅ Step 6: Test the Workflow Open Telegram and message your bot: “Send an email to John about the new budget” “Schedule a meeting Friday at 3 PM with Alex” “Write a blog post about solar energy” “What’s in my inbox?” “Translate this message” (if extended with translation tools) The bot will: Interpret the intent Ask for any missing data Trigger the right tool Send confirmation via Telegram --- ✨ Customization Ideas ✏️ Add Voice Transcription Enable the Download File and Transcribe nodes Requires OpenAI Whisper API key 🧠 Upgrade to GPT-4o Replace the Gemini node with an OpenAI Chat node Connect GPT-4o for improved reasoning and language understanding 🧩 Add More Tools Notion, Slack, Salesforce, Hubspot, WhatsApp, and more can be added Just route them via MCP and update the AI prompt --- 🧪 Troubleshooting Telegram not responding? Ensure correct bot token and webhook connection Make sure the bot is not in privacy mode if needed Gmail actions not working? Double-check your OAuth scopes Ensure Gmail API is enabled in your Google Cloud project AI not responding or behaving poorly? Consider upgrading to OpenAI GPT-4o for better reasoning Revisit and refine your system prompt --- 🧾 Summary Name: Stacey – AI Telegram Assistant Built with: n8n + Gemini + Google + MCP Logic Telegram acts as the front-end Gemini or GPT-4o powers intelligence MCP routes user intent to the right tool Fully extensible and no-code friendly --- 🌟 Credits & License Created by David Olusola Free to use, modify, and resell with attribution. If this helped you, please rate the template or follow me on the n8n Creator Page. ---
By David OlusolaDiscover company data by name with uProc
Do you want to discover company-related information to enrich a signup process? This workflow enriches any company by name using the uProc Get Company by Name tool. This tool combines Google Maps and emails research on the internet to return results. You get no results if the company has no presence on Google Maps. You need to add your credentials (Email and API Key - real -) located at Integration section to n8n. You can replace node "Create Company Item" with any other supported service returning Company names and countries, like Hubspot, Google Sheets, MySQL, or Typeform. You can set up the uProc node with several parameters: country: the country name you want to use. name: the name of the company you need to locate. Every "uProc" node returns the next fields per every located company: name: Contains the company's given name. email: Contains the company's given email. cif: Contains company's cif number. address: Contains company's formatted address. city: Contains the city location of the company. state: Contains province location of the company. county: Contains state location of the company country: Contains country location of the company zipcode: Contains zipcode code of the company phone: Contains phone number of the company website: Contains website of the company latitude: Contains latitude of the company longitude: Contains longitude of the company Next, you can save results to a CRM or Google Sheets, and prepare returned email or phone to launch an email or telemarketing campaign.
By Miquel ColomerJira project management automation with Google Gemini & MCP server
Jira MCP Server Integration with n8n Overview Transform your Jira project management with the power of AI and automation! This n8n workflow template demonstrates how to create a seamless integration between chat interfaces, AI processing, and Jira Software using MCP (Model Context Protocol) server architecture. What This Workflow Does Chat-Driven Automation: Trigger Jira operations through simple chat messages AI-Powered Issue Creation: Automatically generate detailed Jira issues with descriptions and acceptance criteria Complete Jira Management: Get issue status, changelogs, comments, and perform full CRUD operations Memory Integration: Maintain context across conversations for smarter automations Zero Manual Entry: Eliminate repetitive data entry and human errors Key Features ✅ Natural Language Processing: Use Google Gemini to understand and process chat requests ✅ MCP Server Integration: Secure, efficient communication with Jira APIs ✅ Comprehensive Jira Operations: Create, read, update, delete issues and comments ✅ Smart Memory: Context-aware conversations for better automation ✅ Multi-Action Workflow: Handle multiple Jira operations from a single trigger Demo Video 🎥 Watch the Complete Demo: Automate Jira Issue Creation with n8n & AI | MCP Server Integration Prerequisites Before setting up this workflow, ensure you have: n8n instance (cloud or self-hosted) Jira Software account with appropriate permissions Google Gemini API credentials MCP Server configured and accessible Basic understanding of n8n workflows Setup Guide Step 1: Import the Workflow Copy the workflow JSON from this template In your n8n instance, click Import > From Text Paste the JSON and click Import Step 2: Configure Google Gemini Open the Google Gemini Chat Model node Add your Google Gemini API credentials Configure the model parameters: Model: gemini-pro (recommended) Temperature: 0.7 for balanced creativity Max tokens: As per your requirements Step 3: Set Up MCP Server Connection Configure the MCP Client node: Server URL: Your MCP server endpoint Authentication: Add required credentials Timeout: Set appropriate timeout values Ensure your MCP server supports Jira operations: Issue creation and retrieval Comment management Status updates Changelog access Step 4: Configure Jira Integration Set up Jira credentials in n8n: Go to Credentials > Add Credential Select Jira Software API Add your Jira instance URL, email, and API token Configure each Jira node: Get Issue Status: Set project key and filters Create Issue: Define issue type and required fields Manage Comments: Set permissions and content rules Step 5: Memory Configuration Configure the Simple Memory node: Set memory key for conversation context Define memory retention duration Configure memory scope (user/session level) Step 6: Chat Trigger Setup Configure the When Chat Message Received trigger: Set up webhook URL or chat platform integration Define message filters if needed Test the trigger with sample messages Usage Examples Creating a Jira Issue Chat Input: Can you create an issue in Jira for Login Page with detailed description and acceptance criteria? Expected Output: New Jira issue created with structured description Automatically generated acceptance criteria Proper labeling and categorization Getting Issue Status Chat Input: What's the status of issue PROJ-123? Expected Output: Current issue status Last updated information Assigned user details Managing Comments Chat Input: Add a comment to issue PROJ-123: "Ready for testing in staging environment" Expected Output: Comment added to specified issue Notification sent to relevant team members Customization Options Extending Jira Operations Add more Jira operations (transitions, watchers, attachments) Implement custom field handling Create multi-project workflows AI Enhancement Fine-tune Gemini prompts for better issue descriptions Add custom validation rules Implement approval workflows Integration Expansion Connect to Slack, Discord, or Teams Add email notifications Integrate with time tracking tools Troubleshooting Common Issues MCP Server Connection Failed Verify server URL and credentials Check network connectivity Ensure MCP server is running and accessible Jira API Errors Validate Jira credentials and permissions Check project access rights Verify issue type and field configurations AI Response Issues Review Gemini API quotas and limits Adjust prompt engineering for better results Check model parameters and settings Performance Tips Optimize memory usage for long conversations Implement rate limiting for API calls Use error handling and retry mechanisms Monitor workflow execution times Best Practices Security: Store all credentials securely using n8n's credential system Testing: Test each node individually before running the complete workflow Monitoring: Set up alerts for workflow failures and API limits Documentation: Keep track of custom configurations and modifications Backup: Regular backup of workflow configurations and credentials Happy Automating! 🚀 This workflow template is designed to boost productivity and eliminate manual Jira management tasks. Customize it according to your team's specific needs and processes.
By Rohit DabraAutomated sprint reports from Jira to stakeholders via Gmail
Description Automated workflow that generates a Sprint Report from Jira and delivers it by Gmail. The flow fetches sprint issues from Jira, validates and normalizes the data, calculates metrics (tickets, story points, blockers, completion rate), generates an HTML report, and sends it by email. Context This template helps teams keep stakeholders updated automatically of the current sprint. Instead of manually compiling Jira data, the report is generated and sent on schedule (e.g., every Friday at 17:00). It’s production-friendly, reusable, and works across Jira projects. Target Users Scrum Masters and Agile Coaches who need sprint reports for retrospectives. Product Owners who want a weekly overview of sprint progress. Project Managers tracking Jira delivery KPIs. Engineering teams wanting automated status reporting without extra overhead. Technical Requirements Jira Cloud project + API email + API token + permission to read issues. Gmail credential for notifications. Workflow Steps Trigger – Schedule (e.g., Friday at 17:00). Edit Fields – Configure Jira base URL, project key, email recipients. Get Many Issues – Fetch sprint issues with JQL (project = <KEY> AND sprint in openSprints()). Validation & Normalization – Clean/validate fields (status, assignee, priority, story points, sprint info). Metrics Calculation – Aggregate KPIs (done, in progress, blockers, story points, completion %). HTML Report Generation – Build a styled email-friendly HTML summary + detailed table. Send Gmail – Deliver report to stakeholders. Key Features Automated Sprint Reports: No manual copy-paste. Metrics overview: Tickets done vs total, blockers, story points. Detailed table: Issue key, summary, status, assignee, priority, SP. Email delivery: HTML report with Jira links sent to stakeholders. Fully customizable: Adjust fields, KPIs, and recipients easily. Expected Output 📊 HTML Sprint Report with KPIs and issue table. ✅ Email delivered to stakeholders via Gmail. 🔗 Jira links embedded for easy navigation. How it works ⏰ Trigger – Runs on schedule (e.g., every Friday at 17:00). 🧾 Fetch Issues – JQL filters sprint tickets. 📊 Metrics – Done vs total, SP progress, blockers. 💻 Generate HTML – Clean, styled table and summary. ✉️ Notify – Send Gmail with full sprint report to stakeholders. Tutorial video: Watch the Youtube Tutorial video About me : I’m Yassin a Project & Product Manager Scaling tech products with data-driven project management. 📬 Feel free to connect with me on Linkedin
By Yassin ZeharFind valid vouchers and promo codes with SerpAPI, Decodo, and GPT-5 Mini
Promo Seeker finds fresh, working promo codes and vouchers on the web so your team never misses a deal. This n8n workflow uses SerpAPI and Decodo Scrapper for real-time search, an agent powered by GPT-5 Mini for filtering and validation, and Chat Memory to keep context—saving time, reducing manual checks, and helping marketing or customer support teams deliver discounts faster to customers (and yes, it's better at hunting promos than your inbox). 💡 Why Use Promo Seeker? Speed: Saves hours per week by automatically finding and validating current promo codes, so you can publish deals faster. Simplicity: Eliminates manual searching across sites, no more copy-paste scavenger hunts. Accuracy: Reduces false positives by cross-checking results and keeping only working vouchers—fewer embarrassed "expired code" moments. Edge: Combine search APIs with an AI agent to surface hard-to-find, recently-live offers—win over competitors who still rely on manual scraping. ⚡ Perfect For Marketing teams: Quickly populate newsletters, landing pages, or ads with valid promos. Customer support: Give verified discount codes to users without ping-ponging between tabs. Deal aggregators & affiliates: Discover fresh vouchers faster and boost conversion rates. 🔧 How It Works ⏱ Trigger: A user message via the chat webhook starts the search (Message node). 📎 Process: The agent queries SerpAPI and Decodo Scrapper to collect potential promo codes and voucher pages. 🤖 Smart Logic: The Promo Seeker Agent uses GPT-5 Mini with Chat Memory to filter for fresh, working promos and to verify validity and relevance. 💌 Output: Results are returned to the chat with clear, copy-ready promo codes and source links. 🗂 Storage: Chat Memory stores context and recent searches so the agent avoids repeating old results and can follow up with improved queries. 🔐 Quick Setup Import JSON file to your n8n instances Add credentials: SerpAPI, Azure OpenAI (Gpt 5 Mini), Decodo API Customize: Search parameters (brands, regions, validity window), agent system message, and result formatting Update: Azure OpenAI endpoint and API key in the Gpt 5 Mini credentials; add your SerpAPI key and Decodo key Test: Run a few queries like "latest Amazon promo" or "food delivery voucher" and confirm returned codes are valid 🧩 You'll Need Active n8n instances SerpAPI account and API key Azure OpenAI (for GPT-5 Mini) with key and endpoint Decodo account/API key 🛠️ Level Up Ideas Push verified promos to a Slack channel or email digest for the team. Add scheduled scans to detect newly expired codes and remove them from lists. Integrate with a CMS to auto-post verified deals to landing pages. Made by: khaisa Studio Tags: promo, vouchers, discounts Category: Marketing Automation Need custom work? Contact Us
By Khaisa StudioAutomated client journey appointment reminders & follow-ups with Twilio
How It Works ⚙️ This workflow is a comprehensive, AI-powered system that acts as a virtual client relationship manager for any appointment-based business. It handles the entire client journey—from appointment booking to follow-up and re-engagement—all on autopilot. Appointment Trigger: The workflow starts when a new event is created in your Google Calendar. Client Data Management: It queries your client CRM database (Airtable or Google Sheets) to check if the client's email exists, preparing to send a personalized message. Dynamic Reminders: An If node splits the workflow. It sends a personalized welcome message for new clients and a standard reminder for returning clients, drastically reducing no-shows. Post-Appointment Follow-up: A Wait node pauses the workflow until after the appointment ends. It then sends a personalized "thank you" message via Twilio with a link to a review or survey. Re-engagement Loop: A separate Cron trigger runs weekly, automatically identifying clients who haven't rebooked in a set period (e.g., 30 days) and sends them a personalized offer to encourage them to return. Data Logging: It automatically logs all client data and engagement actions into a central database like Airtable or Google Sheets, creating a real-time dashboard for your business. How to Set Up 🛠️ Import the Workflow: Copy the provided workflow JSON and import it into your n8n instance. Configure Credentials: Google Calendar: Add your OAuth2 credential. Twilio: Add your API credentials. Google Sheets / Airtable: Add your credentials for your chosen CRM. Customize Workflow Nodes: Node 1 (Google Calendar Trigger): Select your Google Calendar credential and the calendar you use for bookings. Node 2 (Google Sheets / Airtable): Connect to your client CRM. Adjust the filter to search by the client's email from the calendar event. Node 4 & 5 (Twilio Reminders): Replace YOURTWILIONUMBER with your Twilio number. Customize the message body to fit your business. Node 6 (Wait): Adjust the Wait Duration if you want to send the follow-up message at a different time after the appointment. Node 7 (Twilio Follow-up): Replace the placeholder [LINK TO YOUR REVIEW/SURVEY PAGE] with your actual link. Nodes 8, 9, 10 (Re-engagement Loop): This is an optional, high-value part of the workflow. Configure the Cron node to run on your desired schedule. Adjust the filter in the Find Clients node to your specific re-engagement criteria (e.g., last visit date is older than 30 days). Save & Activate: Once all settings and credentials are configured, save the workflow and click the "Inactive" toggle in the top-right corner to make it live.
By MarthAutomate company ICP scoring with Explorium data and Claude AI analysis
🧠 ICP Scoring Agent (n8n + Explorium + LLM) This workflow automates Ideal Customer Profile (ICP) scoring for any company using a combination of Explorium data and an LLM-driven evaluation framework. --- 🔧 How It Works Input: Company name is submitted via form. Data Enrichment: Explorium's MCP Server is used to fetch firmographic, hiring, and tech data about the company. Scoring Logic: An AI agent (LLM) applies a 3-pillar framework to assess and score the company. Output: A structured JSON or Google Doc summary is generated using the AgentGeeks formatter. --- 📊 Scoring System (100 points total) | Pillar | Max Points | |------------------------------|------------| | Strategic Fit | 40 | | AI / Tech Readiness | 40 | | Engagement & Reachability | 20 | 🧠 Scoring Criteria Strategic Fit: Industry, size, use case, buyer roles Tech Readiness: AI maturity, hiring trends, stack visibility Reachability: Geography, contactability, data quality --- 🎯 Verdict Scale 🟩 90–100: Ideal ICP ✅ 70–89: Good Fit 🟨 40–69: Medium Fit ❌ < 40: Poor Fit --- 📦 Workflow Components Trigger: Form submission via webhook MCP Client: Pulls enriched company data via Explorium's MCP API AI Agent: Uses Anthropic Claude (or other LLM) to calculate scores Output: Results are posted to a structured endpoint (e.g. Google Doc or JSON API) --- 🧰 Dependencies n8n (self-hosted or cloud) Explorium MCP credentials and access LLM API (e.g., Anthropic Claude, OpenAI, etc.) Optional: AgentGeeks formatter or similar doc generator --- 💼 Use Case This ICP scoring system is designed for GTM and sales teams to: Automate lead prioritization Qualify accounts before outbounding Sync ICP data into CRMs, routing systems, or reporting layers --- 📈 Example Output in Google Doc json { "company": "Acme Inc.", "score": 87, "verdict": "Good Fit", "pillars": { "strategic_fit": 35, "tech_readiness": 37, "reachability": 15 }, "summary": "Acme Inc. is a mid-sized SaaS company with strong AI hiring activity and a buyer profile aligned to enterprise IT. Moderate reachability via firmographic signals." }
By Itamar