Workflow Templates

Load Jira open issues with comments into Pinecone + RAG Agent (Direct Tool or MCP) Who’s it for This workflow is designed for support teams, data engineers, and AI developers who want to centralize Jira issue data into a vector database. It collects open issues and their associated comments, converts them into embeddings, and loads them into Pinecone for semantic search, retrieval-augmented generation (RAG), or AI-powered support bots. It’s also published as an MCP tool, so external applications can query the indexed issues directly. How it works The workflow automates Jira issue extraction, comment processing, and vector storage in Pinecone. Importantly, the Pinecone index is recreated at every run so that it always reflects the current set of unresolved tickets. Trigger – A schedule trigger runs the workflow at defined times (e.g., 8, 11, 14, and 17 on weekdays). Issue extraction with pagination – Calls the Jira REST API to fetch open issues matching a JQL query (unresolved cases created in the last year). Pagination is fully handled: issues are retrieved in batches of 25, and the workflow continues iterating until all open issues are loaded. Data transformation – Extracts key fields (issue ID, key, summary, description, product, customer, classification, status, registration date). Comments integration – Fetches all comments for each issue, filters out empty/irrelevant ones (images, dots, empty markdown), and merges them with the issue data. Text cleaning – Converts HTML descriptions into clean plain text for processing. Embedding generation – Uses the OpenAI Embeddings node to vectorize text. Vector storage with index recreation – Loads embeddings and metadata into Pinecone under the jira namespace and the openissues index. The namespace is cleared at every run to ensure the index contains only unresolved tickets. Document chunking – Splits long issue texts into smaller chunks (512 tokens, 50 overlap) for better embedding quality. MCP publishing – Exposes the Pinecone index as an MCP tool (openissues), enabling external systems to query Jira issues semantically. How to set up Jira – Configure a Jira account and generate a token. Update the Jira node with credentials and adjust the JQL query if needed. OpenAI – Set up an OpenAI API key for embeddings. Configure embedding dimensions (default: 512). Pinecone – Create an index (e.g., openissues) with matching dimensions (512). Configure Pinecone API credentials and namespace (jira). The index will be cleared automatically at every run before reloading unresolved issues. Schedule – Adjust the cron expression in the Schedule Trigger to fit your update frequency. Optional MCP – If you want to query Jira issues via MCP, configure the MCP trigger and tool nodes. Requirements Jira account with API access and permissions to read issues and comments. OpenAI API key with access to the embedding model. Pinecone account with an index created (dimensions = 512). n8n instance with credentials set up for Jira, OpenAI, and Pinecone. How to customize the workflow JQL query**: Modify it to control which issues are extracted (e.g., by project, type, or time window). Pagination size**: Adjust the maxResults parameter (default 25) if you want larger or smaller batches per iteration. Metadata fields**: Add or remove fields in the “Extract Relevant Info” code node. Chunk size**: Adjust chunk size/overlap in the Document Chunker for different embedding strategies. Embedding model**: Switch to a different embedding provider if preferred. Vector store**: Replace Pinecone with another supported vector database if needed. Downstream use**: Extend with notifications, dashboards, or AI assistants that consume the vector data. AI Chatbot for Jira open tickets with SLA insights Who’s it for This workflow is designed for commercial teams, customer support, and service managers who need quick, conversational access to unresolved Jira tickets. It enables them to check whether a client has open issues, see related details, and understand SLA implications without manually browsing Jira. How it works Chat interface** – Provides a web-based chat that team members can use to ask natural language questions such as: “Are there any issues from client ACME?” “Do we have tickets that have been open for a long time?” AI Agent** – Powered by OpenAI, it interprets questions and queries the Pinecone vector store (openissues index, jira namespace). Memory** – Maintains short-term chat history for more natural conversations. Ticket retrieval** – Uses Pinecone embeddings (dimension = 512) to fetch unresolved tickets enriched with metadata: Issue key, description, customer, product, severity color, status, AM contract type, and SLA. SLA integration** – Service levels (Basic, Advanced, Full Service, with optional Fast Support) are provided via the SLA node. The agent explains which SLA applies based on ticket severity, registration date, and contract type. AI response** – Returns a friendly, collaborative summary of all tickets found, including: Ticket identifier Description Customer and product Severity level (Red, Yellow, Green, White) Ticket status Contract level and SLA explanation Setup Configure Jira → Pinecone index (openissues, 512 dimensions) already populated with unresolved tickets. Provide OpenAI API credentials. Ensure the SLA node includes the correct service-level definitions. Adjust chat branding (title, subtitle, CSS) if desired. Requirements Jira account with API access. Pinecone account with an index (openissues, dimensions = 512). OpenAI API key. n8n instance with LangChain and chatTrigger nodes enabled. How to customize Change the SLA node text if your service levels differ. Adjust the chat interface design (colors, title, subtitle). Expand metadata in Pinecone (e.g., add project type, priority, or assigned team). Train with additional examples in the system message to refine AI behavior.

AI-powered alt text generation from Google Sheets to WordPress media Who's it for WordPress site owners, content managers, and accessibility advocates who need to efficiently add alt text descriptions to multiple images for better SEO and web accessibility compliance. What it does This workflow automates the process of generating and updating alt text for WordPress media files using AI analysis. It reads image URLs from a Google Sheet, analyzes each image with Claude AI to generate accessibility-compliant descriptions, updates the sheet with the generated alt text, and automatically applies the descriptions to the corresponding WordPress media files. The workflow includes error handling to skip unsupported media formats and continue processing. How it works Input: Provide a Google Sheets URL containing image URLs and WordPress media IDs Authentication: Retrieves WordPress credentials from a separate sheet and generates Base64 authentication Processing: Loops through each image URL in the sheet AI Analysis: Claude AI analyzes each image and generates concise, accessible alt text (max 125 characters) Error Handling: Automatically skips unsupported media formats and continues with the next item Update Sheet: Writes the generated alt text back to the Google Sheet WordPress Update: Updates the WordPress media library with the new alt text via REST API Requirements Google Sheets with image URLs and WordPress media IDs WordPress site with Application Passwords enabled Claude AI (Anthropic) API credentials WordPress admin credentials stored in Google Sheets Export Media URLs WordPress plugin for generating the media list How to set up Step 1: Export your WordPress media URLs Install the "Export Media URLs" plugin on your WordPress site Go to the plugin settings and check both ID and URL columns for export (these are mandatory for the workflow) Export your media list to get the required data Step 2: Configure WordPress Application Passwords Go to WordPress Admin → Users → Your Profile Scroll down to "Application Passwords" section Enter application name (e.g., "n8n API") Click "Add New Application Password" Copy the generated password immediately (it won't be shown again) Step 3: Set up Google Sheets Duplicate this Google Sheets template to get the correct structure. The template includes two sheets: Sheet 1: "Export media" - Paste your exported media data with columns: ID (WordPress media ID) URL (image URL) Alt text (will be populated by the workflow) Sheet 2: "Infos client" - Add your WordPress credentials: Admin Name: Your WordPress username KEY: The application password you generated Domaine: Your site URL without https:// (format: "example.com") Step 4: Configure API credentials Add your Anthropic API credentials to the Claude node Connect your Google Sheets account to the Google Sheets nodes How to customize Language: The Claude prompt is in French - modify it in the "Analyze image" node for other languages Alt text length: Adjust the 125-character limit in the Claude prompt Batch processing: Change the batch size in the Split in Batches node Error handling: The workflow automatically handles unsupported formats, but you can modify the error handling logic Authentication: Customize for different WordPress authentication methods This workflow is perfect for managing accessibility compliance across large WordPress media libraries while maintaining consistent, AI-generated descriptions. It's built to be resilient and will continue processing even when encountering unsupported media formats.

How it works This beginner-friendly workflow demonstrates the core building blocks of n8n. It guides you through: Triggers – Start workflows manually, on a schedule, via webhooks, or through chat. Data processing** – Use Set and Code nodes to create, transform, and enrich data. Logic and branching – Apply conditions with IF nodes and merge different branches back together. API integrations** – Fetch external data (e.g., users from an API), split arrays into individual items, and extract useful fields. AI-powered steps** – Connect to OpenAI for generating fun facts or build interactive assistants with chat triggers, memory, and tools. Responses** – Return structured results via webhooks or summary nodes. By the end, it demonstrates a full flow: creating data → transforming it → making decisions → calling APIs → using AI → responding with outputs. Set up steps Time required: 5–10 minutes. What you need: An n8n instance (cloud or self-hosted). Optional: API credentials (e.g., OpenAI) if you want to test AI features. Setup flow: Import this workflow. Add your API keys where needed (OpenAI, etc.). Trigger the workflow manually or test with webhooks. >👉 Detailed node explanations and examples are already included as sticky notes inside the workflow itself, so you can learn step by step as you explore.

🧠 Overview Generate empathetic, professional reply drafts for customer or user messages. The workflow detects sentiment, tone, and risk level, drafts a concise response, sanitizes PII/links/emojis, and auto-escalates risky or low-confidence cases to human review. ⚙️ How It Works Input — Manual Test or Webhook Trigger AI Agent (Empathy) — returns { sentiment, tone, reply, confidence, needs_handover } Post-Process & Sanitize — removes URLs/hashtags, masks PII, caps length Risk & Handover Rules — checks confidence threshold, risk words, and negativity Routing — auto-send safe replies or flag to Needs Review 🧩 Setup Instructions (3–5 min) Open Set Config1 and adjust: MAX_LEN (default 600) ADD_FOLLOWUP_QUESTION (true/false) FORMALITY (auto | casual | polite) EMOJI_ALLOWED (true/false), BLOCK_LINKS (true/false) RISK_WORDS (e.g., refund, lawsuit, self-harm) Connect Anthropic credential to Anthropic Chat Model (Optional) Replace Manual Trigger with Webhook Trigger for real-time use > Tip: If you need to show literal angle brackets in messages, use backticks like `<example>` (no HTML entities needed). 📚 Use Cases 1) SaaS Billing Complaints Input:** “I was billed after canceling. This is unacceptable.” Output:** Calm, apologetic reply with refund steps; escalates if refund is in RISK_WORDS or confidence < 0.45. 2) Product Bug Reports Input:** “Upload fails on large files since yesterday.” Output:** Acknowledges impact, requests logs, offers workaround; routes to auto-send if low risk and high confidence. 3) Delivery/Logistics Delays Input:** “My order is late again. Should I file a complaint?” Output:** Empathetic apology, ETA guidance, partial credit policy note; escalates if language indicates legal action. 4) Community Moderation / Abuse Input:** “Support is useless—you’re all scammers.” Output:** De-escalating, policy-aligned response; auto-flags due to negative sentiment + risk keyword match. 5) Safety / Self-harm Mentions Input:** “I feel like hurting myself if this isn’t fixed.” Output:* *Immediate escalation**, inserts approved resources; never auto-sends. 🚨 Auto-Escalation Rules (defaults) Negative** sentiment Message matches any RISK_WORDS confidence < 0.45 Mentions of legal, harassment, or self-harm context 🧪 Notes & Best Practices 🔐 No hardcoded API keys — use n8n Credentials 🧭 Tune thresholds and RISK_WORDS to your org policy 🧩 Works on self-hosted or cloud n8n ✅ Treat outputs as drafts; ship after human/policy review 🔗 Resources GitHub (template JSON):** https://github.com/yskmtb0714/n8n-workflows/blob/main/empathy-reply-assistant.json

📧 AI-Powered Email Categorization & Labeling in Zoho Mail This n8n template demonstrates how to use AI text classification to automatically categorize incoming emails in Zoho Mail and apply the correct label (e.g., Support, Billing, HR). It saves time by keeping your inbox structured and ensures emails are routed to the right category. Use cases include: Routing customer support requests to the correct team. Organizing billing and finance communications separately. Streamlining HR and recruitment email handling. Reducing inbox clutter and ensuring no important message is missed. ℹ️ Good to know You’ll need to configure Zoho OAuth credentials — see Self Client Overview, Authorization Code Flow, and Zoho Mail OAuth Guide. The labels must already exist in Zoho Mail (e.g., Support, Billing, HR). The workflow fetches these labels and applies them automatically. The Zoho Mail API domain changes depending on your account region: .com → Global accounts (https://mail.zoho.com/api/...) .eu → EU accounts (https://mail.zoho.eu/api/...) .in → India accounts (https://mail.zoho.in/api/...) Example: For an EU account, the endpoint would be: https://mail.zoho.eu/api/accounts/<accountID>/updatemessage The AI model used for text classification may incur costs depending on your provider (e.g., OpenRouter). Start by testing with a small set of emails before enabling for your full inbox. 🔄 How it works A new email in Zoho Mail triggers the workflow. OAuth authentication retrieves access to Zoho Mail’s API. All available labels are fetched, and a label map (display name → ID) is created. The AI model analyzes the subject and body to predict the correct category. The workflow routes the email to the right category branch. The matching Zoho Mail label is applied (final node is deactivated by default). 🛠️ How to use Create the required labels (e.g., Support, Billing, HR, etc.) in your Zoho Mail account before running the workflow. Replace the Zoho Mail Account ID in the Set Account ID node. Configure your Zoho OAuth credentials in the Get Access Token node. Update the API base URL to match your Zoho account’s region (.com, .eu, .in, etc.). Activate the Apply Label to Email node once ready for production. Optionally, adjust categories in the AI classifier prompt to fit your organization’s needs. 📋 Requirements Zoho Mail account with API access enabled. Labels created in Zoho Mail for each category you want to classify. OAuth credentials set up in n8n. Correct Zoho Mail API domain (.com, .eu, .in) based on your account region. An AI model (via OpenRouter or other provider) for text classification. 🎨 Customising this workflow This workflow can be adapted to many inbox management scenarios. Examples include: Auto-routing customer inquiries to specific departments. Prioritizing VIP client emails with special labels. Filtering job applications directly into an HR-managed folder.

🤖 Human-like Evolution API Agent with Redis & PostgreSQL This production-ready template builds a sophisticated AI Agent using Evolution API that mimics human interaction patterns. Unlike standard chatbots that reply instantly to every incoming message, this workflow uses a Smart Redis Buffering System. It waits for the user to finish typing their full thought (text, audio, or image albums) before processing, creating a natural, conversational flow. It features a Hybrid Memory Architecture: active conversations are cached in Redis for ultra-low latency, while the complete chat history is securely stored in PostgreSQL. To optimize token usage and maintain long-term coherence, a Context Refiner Agent summarizes the conversation history before the Main AI generates a response. ✨ Key Features Human-like Buffering:** The agent waits (configurable time) to group consecutive messages, voice notes, and media albums into a single context. This prevents fragmented replies and feels like talking to a real person. Hybrid Memory:* Combines *Redis* (Hot Cache) for speed and *PostgreSQL** (Cold Storage) for permanent history. Context Refinement:** A specialized AI step summarizes past interactions, allowing the Main Agent to understand long conversations without exceeding token limits or increasing costs. Multi-Modal Support:** Natively handles text, audio transcription, and image analysis via Evolution API. Parallel Processing:** Manages "typing..." status and session checks in parallel to reduce response latency. 📋 Requirements To use this workflow, you must configure the Evolution API correctly: Evolution API Instance: You need a running instance of Evolution API. Configuration Guide N8n Community Node: Install the Evolution API node in your n8n instance. n8n-nodes-evolution-api Database: A PostgreSQL database for chat history and a Redis instance for the buffer/cache. AI Models: API keys for your LLM (OpenAI, Anthropic, or Google Gemini). ⚙️ Setup Instructions Install the Node: Go to Settings > Community Nodes in n8n and install n8n-nodes-evolution-api. Credentials: Configure credentials for Redis, PostgreSQL, and your AI provider (e.g., OpenAI/Gemini). Database Setup: Create a chat_history table in PostgreSQL (columns must match the Insert node). Redis Connection: Configure your Redis credentials in the workflow nodes. Global Variables: Set the following in the "Global Variables" node: wait_buffer: Seconds to wait for the user to stop typing (e.g., 5s). wait_conversation: Seconds to keep the cache alive (e.g., 300s). max_chat_history: Number of past messages to retrieve. Webhook: Point your Evolution API instance to this workflow's Webhook URL. 🚀 How it Works Ingestion: Receives data via Evolution API. Detects if it's text, audio, or an album. Smart Buffering: Holds the execution to collect all parts of the user's message (simulating a human reading/listening). Context Retrieval: Checks Redis for the active session. If empty, fetches from PostgreSQL. Refinement: The Refiner Agent summarizes the history to extract key details. Response: The Main Agent generates a reply based on the refined context and current buffer, then saves it to both Redis and Postgres. 💡 Need Assistance? If you’d like help customizing or extending this workflow, feel free to reach out: 📧 Email: johnsilva11031@gmail.com 🔗 LinkedIn: John Alejandro Silva Rodríguez

🤖💬 Smart Telegram AI Assistant with Memory Summarization & Dynamic Model Selection > Optimize your AI workflows, cut costs, and get faster, more accurate answers. 📋 Description Tired of expensive AI calls, slow responses, or bots that forget your context? This Telegram AI Assistant template is designed to optimize cost, speed, and precision in your AI-powered conversations. By combining PostgreSQL chat memory, AI summarization, and dynamic model selection, this workflow ensures you only pay for what you really need. Simple queries get routed to lightweight models, while complex requests automatically trigger more advanced ones. The result? Smarter context, lower costs, and better answers. This template is perfect for anyone who wants to: ⚡ Save money by using cheaper models for easy tasks. 🧠 Keep context relevant with AI-powered summarization. ⏱️ Respond faster thanks to optimized chat memory storage. 💬 Deliver better answers directly inside Telegram. ✨ Key Benefits 💸 Cost Optimization: Automatically routes simple requests to Gemini Flash Lite and reserves Gemini Pro only for complex reasoning. 🧠 Smarter Context: Summarization ensures only the most relevant chat history is used. ⏱️ Faster Workflows: Storing user + agent messages in a single row reduces DB queries by half and saves ~0.3s per response. 🎤 Voice Message Support: Convert Telegram voice notes to text and reply intelligently. 🛡️ Error-Proof Formatting: Safe MarkdownV2 ensures Telegram-ready answers. 💼 Use Case This template is for anyone who needs an AI chatbot on Telegram that balances cost, performance, and intelligence. Customer support teams can reduce expenses by using lightweight models for FAQs. Freelancers and consultants can offer faster AI-powered chats without losing context. Power users can handle voice + text seamlessly while keeping conversations memory-aware. Whether you’re scaling a business or just want a smarter assistant, this workflow adapts to your needs and budget. 💬 Example Interactions Quick Q&A** → Routed to Gemini Flash Lite for fast, low-cost answers. Complex problem-solving** → Sent to Gemini Pro for in-depth reasoning. Voice messages** → Automatically transcribed, summarized, and answered. Long conversations** → Context is summarized, ensuring precise and efficient replies. 🔑 Required Credentials Telegram Bot API** (Bot Token) PostgreSQL** (Database connection) Google Gemini API** (Flash Lite, Flash, Pro) ⚙️ Setup Instructions 🗄️ Create the PostgreSQL table (chat_memory) from the Gray section SQL. 🔌 Configure the Telegram Trigger with your bot token. 🤖 Connect your Gemini API credentials. 🗂️ Set up PostgreSQL nodes with your DB details. ▶️ Activate the workflow and start chatting with your AI-powered Telegram bot. 🏷 Tags telegram ai-assistant chatbot postgresql summarization memory gemini dynamic-routing workflow-optimization cost-saving voice-to-text 🙏 Acknowledgement A special thank you to Davide for the inspiration behind this template. His work on the AI Orchestrator that dynamically selects models based on input type served as a foundational guide for this architecture. 💡 Need Assistance? Want to customize this workflow for your business or project? Let’s connect: 📧 Email: johnsilva11031@gmail.com 🔗 LinkedIn: John Alejandro Silva Rodríguez

This workflow automates business intelligence. Submit one URL, and it scrapes the website, uses AI to perform a comprehensive analysis, and generates a professional report in Google Doc and PDF format. It's perfect for agencies, freelancers, and consultants who need to streamline client research or competitive analysis. How It Works The workflow is triggered by a form input, where you provide a single website URL. Scrape: It uses Firecrawl to scrape the sitemap and get the full content from the target website. Analyze: The main workflow calls a Tools Workflow (included below) which uses Google Gemini and Perplexity AI agents to analyze the scraped content and extract key business information. Generate & Deliver: All the extracted data is formatted and used to populate a template in Google Docs. The final report is saved to Google Drive and delivered via Gmail. What It Generates The final report is a comprehensive business analysis, including: Business Overview: A full company description. Target Audience Personas: Defines the demographic and psychographic profiles of ideal customers. Brand & UVP: Extracts the brand's personality matrix and its Unique Value Proposition (UVP). Customer Journey: Maps the typical customer journey from Awareness to Loyalty. Required Tools This workflow requires n8n and API keys/credentials for the following services: Firecrawl (for scraping) Perplexity (for AI analysis) Google Gemini (for AI analysis) Google Services (for Docs, Drive, and Gmail) ⚠️ Required: Tools Workflow This workflow will not work without its "Tools" sub-workflow. Please create a new, separate workflow in n8n, name it (e.g., "Business Analysis Tools"), and paste the following code into it. { "name": "Business Analysis Workflow Tools", "nodes": [ { "parameters": { "workflowInputs": { "values": [ { "name": "function" }, { "name": "keyword" }, { "name": "url" }, { "name": "location_code" }, { "name": "language_code" } ] } }, "type": "n8n-nodes-base.executeWorkflowTrigger", "typeVersion": 1.1, "position": [ -448, 800 ], "id": "e79e0605-f9ac-4166-894c-e5aa9bd75bac", "name": "When Executed by Another Workflow" }, { "parameters": { "rules": { "values": [ { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "8d7d3035-3a57-47ee-b1d1-dd7bfcab9114", "leftValue": "serp_search", "rightValue": "={{ $json.function }}", "operator": { "type": "string", "operation": "equals", "name": "filter.operator.equals" } } ], "combinator": "and" }, "renameOutput": true, "outputKey": "serp_search" }, { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "bb2c23eb-862d-4582-961e-5a8d8338842c", "leftValue": "ai_mode", "rightValue": "={{ $json.function }}", "operator": { "type": "string", "operation": "equals", "name": "filter.operator.equals" } } ], "combinator": "and" }, "renameOutput": true, "outputKey": "ai_mode" }, { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "4603eee1-3888-4e32-b3b9-4f299dfd6df3", "leftValue": "internal_links", "rightValue": "={{ $json.function }}", "operator": { "type": "string", "operation": "equals", "name": "filter.operator.equals" } } ], "combinator": "and" }, "renameOutput": true, "outputKey": "internal_links" } ] }, "options": {} }, "type": "n8n-nodes-base.switch", "typeVersion": 3.2, "position": [ -208, 784 ], "id": "72c37890-7054-48d8-a508-47ed981551d6", "name": "Switch" }, { "parameters": { "method": "POST", "url": "https://api.dataforseo.com/v3/serp/google/organic/live/advanced", "authentication": "genericCredentialType", "genericAuthType": "httpBasicAuth", "sendBody": true, "specifyBody": "json", "jsonBody": "=[\n {\n \"keyword\": \"{{ $json.keyword.replace(/[:'\"\\\\/]/g, '') }}\",\n \"location_code\": {{ $json.location_code }},\n \"language_code\": \"{{ $json.language_code }}\",\n \"depth\": 10,\n \"group_organic_results\": true,\n \"load_async_ai_overview\": true,\n \"people_also_ask_click_depth\": 1\n }\n]", "options": { "redirect": { "redirect": { "followRedirects": false } } } }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 384, 512 ], "id": "6203f722-b590-4a25-8953-8753a44eb3cb", "name": "SERP Google", "credentials": { "httpBasicAuth": { "id": "n5o00CCWcmHFeI1p", "name": "DataForSEO" } } }, { "parameters": { "content": "## SERP Google", "height": 272, "width": 688, "color": 4 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 288, 432 ], "id": "81593217-034f-466d-9055-03ab6b2d7d08", "name": "Sticky Note3" }, { "parameters": { "assignments": { "assignments": [ { "id": "97ef7ee0-bc97-4089-bc37-c0545e28ed9f", "name": "platform", "value": "={{ $json.tasks[0].data.se }}", "type": "string" }, { "id": "9299e6bb-bd36-4691-bc6c-655795a6226e", "name": "type", "value": "={{ $json.tasks[0].data.se_type }}", "type": "string" }, { "id": "2dc26c8e-713c-4a59-a353-9d9259109e74", "name": "keyword", "value": "={{ $json.tasks[0].data.keyword }}", "type": "string" }, { "id": "84c9be31-8f1d-4a67-9d13-897910d7ec18", "name": "results", "value": "={{ $json.tasks[0].result }}", "type": "array" } ] }, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 592, 512 ], "id": "a916551a-009b-403f-b02e-3951d54d2407", "name": "Prepare SERP output" }, { "parameters": { "content": "# Google Organic Search API\n\nThis API lets you retrieve real-time Google search results with a wide range of parameters and custom settings. \nThe response includes structured data for all available SERP features, along with a direct URL to the search results page. \n\n👉 Documentation\n", "height": 272, "width": 496, "color": 4 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 976, 432 ], "id": "87672b01-7477-4b43-9ccc-523ef8d91c64", "name": "Sticky Note17" }, { "parameters": { "method": "POST", "url": "https://api.dataforseo.com/v3/serp/google/ai_mode/live/advanced", "authentication": "genericCredentialType", "genericAuthType": "httpBasicAuth", "sendBody": true, "specifyBody": "json", "jsonBody": "=[\n {\n \"keyword\": \"{{ $json.keyword }}\",\n \"location_code\": {{ $json.location_code }},\n \"language_code\": \"{{ $json.language_code }}\",\n \"device\": \"mobile\",\n \"os\": \"android\"\n }\n]", "options": { "redirect": { "redirect": {} } } }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 384, 800 ], "id": "fb0001c4-d590-45b3-a3d0-cac7174741d3", "name": "AI Mode", "credentials": { "httpBasicAuth": { "id": "n5o00CCWcmHFeI1p", "name": "DataForSEO" } } }, { "parameters": { "content": "## AI Mode", "height": 272, "width": 512, "color": 6 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 288, 720 ], "id": "2cea3312-31f8-4ff0-b385-5b76b836274c", "name": "Sticky Note11" }, { "parameters": { "assignments": { "assignments": [ { "id": "b822f458-ebf2-4a37-9906-b6a2606e6106", "name": "keyword", "value": "={{ $json.tasks[0].data.keyword }}", "type": "string" }, { "id": "10484675-b107-4157-bc7e-b942d8cdb5d2", "name": "result", "value": "={{ $json.tasks[0].result[0].items }}", "type": "array" } ] }, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 592, 800 ], "id": "6b1e7239-ee2b-4457-8acb-17ce87415729", "name": "Prepare AI Mode Output" }, { "parameters": { "content": "# Google AI Mode API\n\nThis API provides AI-generated search result summaries and insights from Google. \nIt returns detailed explanations, overviews, and related information based on search queries, with parameters to customize the AI overview. \n\n👉 Documentation\n", "height": 272, "width": 496, "color": 6 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 800, 720 ], "id": "d761dc57-e35d-4052-a360-71170a155f7b", "name": "Sticky Note18" }, { "parameters": { "content": "## Input", "height": 384, "width": 544, "color": 7 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ -528, 672 ], "id": "db90385e-f921-4a9c-89f3-53fc5825b207", "name": "Sticky Note" }, { "parameters": { "assignments": { "assignments": [ { "id": "b865f4a0-b4c3-4dde-bf18-3da933ab21af", "name": "platform", "value": "={{ $json.platform }}", "type": "string" }, { "id": "476e07ca-ccf6-43d4-acb4-4cc905464314", "name": "type", "value": "={{ $json.type }}", "type": "string" }, { "id": "f1a14eb8-9f10-4198-bbc7-17091532b38e", "name": "keyword", "value": "={{ $json.keyword }}", "type": "string" }, { "id": "181791a0-1d88-481c-8d98-a86242bb2135", "name": "results", "value": "={{ $json.results[0].items }}", "type": "array" } ] }, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 800, 512 ], "id": "83fef061-5e0b-417c-b1f6-d34eb712fac6", "name": "Sort Results" }, { "parameters": { "content": "## Internal Links", "height": 272, "width": 272, "color": 5 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 288, 1024 ], "id": "9246601a-f133-4ca3-aac8-989cb45e6cd2", "name": "Sticky Note7" }, { "parameters": { "method": "POST", "url": "https://api.firecrawl.dev/v2/map", "sendHeaders": true, "headerParameters": { "parameters": [ { "name": "Authorization", "value": "Bearer your-firecrawl-apikey" } ] }, "sendBody": true, "specifyBody": "json", "jsonBody": "={\n \"url\": \"https://{{ $json.url }}\",\n \"limit\": 400,\n \"includeSubdomains\": false,\n \"sitemap\": \"include\"\n }", "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 368, 1104 ], "id": "fd6a33ae-6fb3-4331-ab6a-994048659116", "name": "Get Internal Links" }, { "parameters": { "content": "# Firecrawl Map API\n\nThis endpoint maps a website from a single URL and returns the list of discovered URLs (titles and descriptions when available) — extremely fast and useful for selecting which pages to scrape or for quickly enumerating site links. (Firecrawl)\n\nIt supports a search parameter to find relevant pages inside a site, location/languages options to emulate country/language (uses proxies when available), and SDK + cURL examples in the docs,\n\n👉 Documentation\n\n[1]: https://docs.firecrawl.dev/features/map \"Map | Firecrawl\"\n", "height": 272, "width": 624, "color": 5 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 560, 1024 ], "id": "08457204-93ff-4586-a76e-03907118be3c", "name": "Sticky Note24" } ], "pinData": { "When Executed by Another Workflow": [ { "json": { "function": "serp_search", "keyword": "villanyszerelő Largo Florida", "url": null, "location_code": 2840, "language_code": "hu" } } ] }, "connections": { "When Executed by Another Workflow": { "main": [ [ { "node": "Switch", "type": "main", "index": 0 } ] ] }, "Switch": { "main": [ [ { "node": "SERP Google", "type": "main", "index": 0 } ], [ { "node": "AI Mode", "type": "main", "index": 0 } ], [ { "node": "Get Internal Links", "type": "main", "index": 0 } ] ] }, "SERP Google": { "main": [ [ { "node": "Prepare SERP output", "type": "main", "index": 0 } ] ] }, "AI Mode": { "main": [ [ { "node": "Prepare AI Mode Output", "type": "main", "index": 0 } ] ] }, "Prepare SERP output": { "main": [ [ { "node": "Sort Results", "type": "main", "index": 0 } ] ] }, "Sort Results": { "main": [ [] ] } }, "active": false, "settings": { "executionOrder": "v1" }, "versionId": "6fce16d1-aa28-4939-9c2d-930d11c1e17f", "meta": { "instanceId": "1ee7b11b3a4bb285563e32fdddf3fbac26379ada529b942ee7cda230735046a1" }, "id": "VjpOW2V2aNV9HpQJ", "tags": [] } `

Here’s a clean, English-only template description you can paste into the n8n “Description” field. Overview This workflow analyzes customer survey responses, groups them by sentiment (positive / neutral / negative), generates themes and insights with an AI agent, and delivers a consolidated report to your destinations (Google Sheets, Slack). It runs on a daily schedule and uses batch-based AI analysis for accuracy. Flow: Schedule → Fetch from Sheets → Group & batch (Code) → AI analysis → Aggregate → Save/Notify (Sheets, Slack) What You’ll Need A survey data source (Google Sheets recommended) AI model credentials (e.g., OpenAI or OpenRouter) Optional destinations: Google Sheets (summary sheet), Slack channel Setup Data source (Google Sheets) In Get Survey Responses, replace YOUR_SHEET_ID and YOUR_SHEET_NAME with your sheet details. Ensure the sheet includes columns like: 満足度 (Rating), 自由記述コメント (Comment), 回答日時 (Timestamp). AI model Add credentials to your preferred LLM node (OpenAI/OpenRouter). Keep the prompt’s JSON-only requirement so the structured parser can consume it reliably. Destinations Save to Sheet: set your output documentId / sheetName. Slack: set the target channelId on the Slack node. How It Works Daily Schedule Trigger — starts the workflow at your chosen time. Get Survey Responses (Sheets) — reads survey data. Group & Prepare Data (Code) — classifies by rating (>=4: positive, =3: neutral, <3: negative) and creates batches (max 50 per batch). Loop Over Batches — feeds each sentiment batch to the AI separately for cleaner signals. Analyze Survey Batch (AI Agent) — returns structured JSON: themes, insights, recommendations. Add Metadata (Code) — attaches original sentiment and item counts to each AI result. Aggregate Results (Code) — merges all batches; outputs Top Themes, Key Insights, Priority Recommendations, and an Executive Summary. Save to Sheet / Slack — appends the summary to a sheet and posts highlights to Slack. Data Assumptions (Columns) Your source should include at least: 満足度 (Rating) — integer 1–5 自由記述コメント (Comment) — string 回答日時 (Timestamp) — ISO string or date Outputs Consolidated summary** containing: Top themes (with example quotes) Key insights Priority recommendations Executive summary Destinations**: Google Sheets (one row per run) and Slack (high-level highlights) Customize Adjust sentiment thresholds (e.g., require >=5 for positive) or batch size (default 50) in the Code node. Tailor the AI prompt or the output JSON schema to your domain. Add more outputs (CSV export, database insert, additional channels) in parallel after the Aggregate step. Before You Run (Checklist) [ ] Add credentials for Sheets / AI / Slack in Credentials [ ] Update documentId, sheetName, and Slack channelId [ ] Confirm your column names match the Code node references [ ] Verify schedule time and timezone (e.g., Asia/Tokyo) Troubleshooting Parser errors on AI output: ensure the model response is **JSON-only; reduce temperature or simplify schema if needed. Only some batches run**: check batch size in Loop and ensure each sentiment bucket actually contains responses. No output to Sheets/Slack**: verify credentials, IDs, and required fields; confirm permissions. Security & Template Notes Do not include credentials in the template file. Users add their own after import. Use Sticky Notes to document Overview, Setup, Processing Logic, and Output choices. This template already includes guideline-friendly notes.

Quick Overview This workflow enriches leads from Google Sheets by finding and validating LinkedIn profile URLs with SerpAPI and Anthropic, then scraping matched profiles with Apify to extract a relevant company and discover its website domain via SerpAPI, saving results back to Google Sheets. How it works Starts manually and reads lead rows from Google Sheets for LinkedIn enrichment. Searches Google via SerpAPI for likely LinkedIn results, filters out unwanted domains/file types, and keeps the best candidates. Uses Anthropic to validate the best match (LinkedIn profile or company website) from the search results and writes the selected URL, confidence, and status back to Google Sheets. Runs a second search pass for selected rows using SerpAPI with the lead’s employer name included, validates again with Anthropic, and updates Google Sheets. Reads rows marked as having a LinkedIn URL and processes them in batches with a wait to reduce rate-limit issues. Scrapes each LinkedIn profile with Apify to collect emails and work history, selects a relevant property-management-related company, and then uses SerpAPI to find and extract the company’s website domain. Updates Google Sheets with the chosen company, job title, LinkedIn details, extracted domain, and flags indicating whether to proceed to downstream email-finding steps. Setup Connect a Google Sheets OAuth2 credential and replace YOUR_GOOGLE_SHEET_ID (and sheet tab selection) in all Google Sheets nodes. Add your SerpAPI API key in both SerpAPI HTTP Request nodes and update the search query location terms (for example, YOUR_LOCATION/Ontario) to match your targeting. Add an Anthropic credential, confirm the model selection, and edit the AI system prompt keywords (industry, titles, and location rules) to match your use case. Add your Apify token in the Apify HTTP Request node and ensure the referenced LinkedIn scraper actor is available in your Apify account. Ensure your Google Sheet contains the required columns used by the workflow (for example First Name, Last Name, Employer Name, enrichment_status, serp_url, is_linkedin, ai_reason, company_name, job_title, domain, proceed_to_prospeo, and row_number).

B2B Lead Enrichment | Attio CRM This n8n template automates B2B lead research and enrichment for Attio CRM. It combines data from Apollo.io, LinkedIn scraping, and news sources with AI-powered analysis to generate actionable sales intelligence - turning hours of manual BDR research into minutes. Who is this for? Sales teams using Attio CRM who want to reduce time spent on lead research BDRs/SDRs who need rich prospect context before outreach Revenue operations teams looking to automate CRM enrichment at scale What problem does this workflow solve? Before reaching out to a prospect, sales reps typically spend 15-30 minutes researching company background, recent news, leadership team, and LinkedIn activity. This workflow automates that entire research process, freeing BDRs to focus on relationship building instead of data gathering. How it works Trigger: Manually execute (adapt to webhook or form trigger for automation) Apollo Enrichment: Fetches comprehensive company data by domain Parallel Processing: Three branches run simultaneously: News articles → Tavily extraction → AI summary LinkedIn company page → Scrape Creators → AI summary Leadership search (with web search) → Apollo person lookup → LinkedIn profiles → AI summary Validation: An LLM Critic agent verifies all claims using web search Final Output: Lead Enrichment Agent generates a structured dossier CRM Sync: Updates Attio company and people records Good to Know Estimated API Costs (per enrichment): Apollo.io: Varies by plan (credits-based) Scrape Creators: ~$0.01-0.05 per profile Tavily: ~$0.01 per extraction OpenAI GPT-4o: ~$0.10-0.30 depending on content length Rate Limits: Leadership profiles are processed sequentially to respect API limits. For bulk enrichment, consider adding delays between executions. Requirements Apollo.io account with API access Scrape Creators API key (for LinkedIn scraping) Tavily API key (for article extraction) OpenAI API key (GPT-4o model access) Attio CRM account with API access Setup Import the workflow into n8n Configure credentials for each service: Apollo API (HTTP Header Auth with x-api-key) Scrape Creators API Tavily API OpenAI API Attio API Add these custom fields to your Attio Companies object: positioning (text) conversation_points (text) leadership_conversations (text) enrichment_status (select with "complete" option) Test with a single domain before running at scale Customizing this workflow Trigger: Replace manual trigger with a webhook (real-time enrichment on new leads) or schedule node (batch processing) AI Prompts: Adjust the system prompts in AI agents to match your industry or ideal customer profile Output Fields: Modify the final Code node to map to your specific Attio field structure News Timeframe: Change the 6-month lookback in Apollo:LatestNews to your preferred range Leadership Depth: Adjust the number of leadership profiles to enrich based on your needs Made by www.fenrirlabs.nl

Who is it for This workflow is for anyone who is using N8N. It's especially helpful if you are a DevOps and your N8N instance is self hosted. If you carea lot about security and number of failed executions and at the same time you are using InfluxDB to monitor status of your systems, this will perfectly fit in your stack. How it works This automation is fairly simple. It uses native N8N nodes to gather data from itself. Then it is parsing this data to be compatible with InfluxDB input. And finally it is sending this data to InfluxDB for further processing. Remember to set up Setup is really simple and you just need to provide just three variables. First is your InfluxDB URL, second is your InfluxDB organization, and third is your InfluxDB bucket name. Of course, to set up N8N nodes and gather data from them, you will need your instance API key. And that's all. How it looks in InfluxDB? See below Schedule Audits Audits don't need to be run often, but I would recommend it to be run on regular basis. This way you can see real data series in InfluxDB. I think that once a day should be enough, but it depends on your N8N usage of course Thank you, perfect! Glad I could help. Visit my profile for other automations for businesses. And if you are looking for dedicated software development, do not hesitate to reach out! You can also see automations on my Sailing Byte's GitHub N8N repository.