Workflow Templates

Automate LinkedIn engagement without sounding like a bot. This workflow: 🌍 Detects language & tone (German / English) 👍 Chooses the right reaction (like / celebrate / support …) 🗣 Generates a personalised comment in your voice and mentions the author 📲 Optional Telegram review – approve ✅ or regenerate ❌ before posting 💸 Runs on cost-efficient GPT-4o mini or Claude 3.5 Haiku ☁️ Publishes comment + reaction via the Unipile API Setup (≈ 15-30 min) Unipile – connect LinkedIn → copy account_id, dsn, then create an Access-Token (X-API-KEY). Telegram (optional) – create a bot, add a credential named YOUR TELEGRAM ACCOUNT. OpenAI / Anthropic – add your API key and keep one LLM node (delete the other). Open the “Defining guardrails” node and replace the credential placeholders. (Optional) Tweak role, comment_length and openers_example_1-3 for your brand voice. Security: no live keys included – all secrets are placeholders. Best for: solopreneurs, marketing teams, personal-branding consultants.

This n8n workflow demonstrates a simple approach to improve chat UX by staggering an AI Agent's reply for users who send in a sequence of partial messages and in short bursts. How it works Twilio webhook receives user's messages which are recorded in a message stack powered by Redis. The execution is immediately paused for 5 seconds and then another check is done against the message stack for the latest message. The purpose of this check lets use know if the user is sending more messages or if they are waiting for a reply. The execution is aborted if the latest message on the stack differs from the incoming message and continues if they are the same. For the latter, the agent receives the buffered messages up to that point and is able to respond to them in a single reply. Requirements A Twilio account and SMS-enabled phone number to receive messages. Redis instance for the messages stack. OpenAI account for the language model. Customising the workflow This workflow should work for other common messaging platforms such as Whatsapp and Telegram. 5 seconds too long or too short? Adjust the wait threshold to suit your customers.

🤖 AI-Powered Lead Enrichment with Explorium MCP & Telegram Who it's for Sales reps, agencies, and growth teams who want to turn basic company info into qualified leads with automated research . Perfect for B2B prospecting. What it does This workflow lets you send a company name or domain via Telegram, and instantly returns: ✅ Enriched company profile (industry, size, tech, pain points) ✅ A clean, structured JSON — ready for your CRM or sales tools How it works 💬 Send company info to your Telegram bot 🔎 Workflow pulls data from Explorium MCP + Tavily 🧠 AI analyzes model, tools, pain points & goals 📤 JSON response sent back via Telegram or logged to your database Requirements 🔐 OpenAI API (GPT-4) 🧠 Explorium MCP API 🌐 Tavily Web Search API 🤖 Telegram Bot API 🗃️ PostgreSQL (for memory/logging) How to set up Add API keys in n8n Connect Telegram bot to webhook Set up PostgreSQL for memory persistence Customize prompts (tone, niche, etc.) Test by sending a company name via Telegram Customization Options 🎯 Focus enrichment on specific industries or keywords 💬 Adjust the email sequence structure & style 🧩 Add extra data sources (e.g. Clearbit, Crunchbase) 🧾 Format JSON to match your CRM schema ⚙️ Add approval step before sending emails Highlights ✅ Uses multi-source enrichment ✅ Works 100% from Telegram ✅ Integrates into any sales pipeline

Analyze exchange data, market indexes, and community sentiment from CoinMarketCap—powered by AI. This sub-agent provides access to exchange listings, token holdings, metadata, and high-level metrics like the CMC 100 Index and the Fear & Greed Index. It’s designed for use within your larger CoinMarketCap AI Analyst system or as a standalone workflow. This agent can be triggered by a supervisor or manually used with message and sessionId inputs. Supported Tools (5 Total) 🔍 Exchange Map Get CoinMarketCap IDs, names, and slugs for exchanges (used as lookup before deeper queries). 🧾 Exchange Info Metadata including launch date, social links, country, and operational status. 💰 Exchange Assets Token balances, wallet addresses, and total USD value held by a specific exchange. 📈 CoinMarketCap 100 Index Constituents and weights of the CMC 100 Index, updated live. 😱 Fear & Greed Index Market sentiment score updated daily, ranging from Extreme Fear to Extreme Greed. What You Can Do with This Agent 🔹 Map exchanges to retrieve their ID and slug 🔹 Analyze exchange holdings by token and blockchain 🔹 Pull metadata for major CEXs like Binance or Coinbase 🔹 Compare global sentiment using the Fear & Greed Index 🔹 Access index data to understand CMC’s top 100 crypto asset breakdown Example Queries You Can Use ✅ "What is the latest Fear and Greed Index reading?" ✅ "Get a list of all exchanges on CoinMarketCap." ✅ "What tokens are held by Binance?" ✅ "Retrieve metadata for Coinbase." ✅ "Show me the top assets in the CMC 100 Index." Agent Architecture AI Brain**: GPT-4o-mini Memory**: Window buffer memory using sessionId Tools**: 5 API-connected nodes Trigger**: External input via message and sessionId Setup Instructions Get a CoinMarketCap API Key Apply here: https://coinmarketcap.com/api/ Configure n8n Credentials Use HTTP Header Auth to store your CoinMarketCap API key. Optional: Trigger from a Supervisor Connect to a parent agent using Execute Workflow with message and sessionId inputs. Test Sample Prompts “Get all exchanges”, “Fetch CMC index”, “Show Binance token holdings” Sticky Notes Included Exchange & Community Guide – Explains agent purpose and component connections Usage & Examples – Walkthrough for sample use cases Error Handling & Licensing – Includes API error code reference and licensing details ✅ Final Notes This agent is part of a broader CoinMarketCap AI Analyst System. Visit my Creator profile to download all available sub-agents and supervisor flows. Understand exchange behavior and community sentiment—automated with AI and CoinMarketCap.

AI Database Assistant with Smart Query's & PostgreSQL Integration Description: 🚀 Transform Your Database into an Intelligent AI Assistant This workflow creates a smart database assistant that safely handles natural language queries without crashing your system. Features dual-agent architecture with built-in query limits and PostgreSQL optimization – perfect for commercial applications! ✅ Ideal for: SaaS developers building database search features 🔍 Database administrators providing safe AI access 🛡️ Business teams needing user-friendly data queries 📊 Anyone wanting ChatGPT-like database interaction 🤖 🔧 How It Works 1️⃣ User asks a question – "Show me top 10 popular products" 2️⃣ Main AI Agent – Interprets the request and ensures safety limits 3️⃣ SQL Sub-Agent – Generates precise PostgreSQL queries 4️⃣ Database executes – Returns formatted, limited results safely ⚡ Setup Instructions 1️⃣ Prepare Your Database Ensure PostgreSQL is accessible from n8n Note your table structure and column names Set up database connection credentials 2️⃣ Customize the Templates Replace [YOUR_TABLE_NAME] with your actual table name Update [YOUR_FIELDS] with your column names Modify examples to match your use case Important**: Keep all LIMIT clauses intact! 3️⃣ Configure the Agents Copy Main Agent system message to your primary AI node Copy Sub-Agent system message to your SQL generator node Connect the sub-workflow between both agents 4️⃣ Test & Deploy Test with sample queries like "Show me 5 recent items" Verify query limits work (max 50 results) Deploy and monitor performance 🎯 Why Use This Workflow? ✔️ System Protection – Built-in limits prevent crashes from large queries ✔️ Natural Language – Users ask questions in plain English ✔️ Commercial Ready – Generic templates work with any database ✔️ Dual-Agent Safety – Smart interpretation + precise SQL generation ✔️ PostgreSQL Optimized – Handles complex schemas and data types 🚨 Critical Features Query Limits**: Default 10, maximum 50 results (can be modified) Error Prevention**: No unlimited data retrieval Smart Routing**: Natural language → Safe SQL → Formatted results Customizable**: Works with any PostgreSQL database schema 🔗 Start building your AI database assistant today – safe, smart, and scalable!

This workflow automatically checks the status of your websites using UptimeRobot API. If any site is down or unstable, it will: Generate a natural-language alert message using GPT-4o Push the message to a LINE group (with funny IT-style encouragement) Log all DOWN status entries into your Supabase database Wait 30 minutes before repeating 🔧 How It Works Schedule Trigger – Runs on a fixed interval (every few minutes). UptimeRobot Node – Fetches website monitor data. Code Node (Filter) – Filters only websites with status 8 (may be down) or 9 (down). IF Node – If any site is down, proceed. LangChain LLM Node – Formats alert with a humorous message using GPT-4o. Line Notify (HTTP Request) – Sends the alert to your LINE group. Loop Over Items – Loops through all monitors. Filter Down (Status = 9) – Selects only “fully down” sites. Supabase Node – Logs these into synlora_uptime_down table. Wait Node – Delays next alert by 30 minutes to avoid spamming. ⚙️ Setup Steps Required: 🔗 UptimeRobot API Key 📲 LINE Channel Access Token and Group ID 🧠 OpenAI Key (GPT-4o Mini) 🗃️ Supabase Project & Table Step-by-step: Go to UptimeRobot → Get API key and ensure monitors are set up. Create a Supabase table with fields: website, status, uptime_id. Create a LINE Messaging API bot, join it to your group, and get: Access Token Group ID (userId or groupId) Add your OpenAI API Key for GPT-4o Mini (or switch to your preferred LLM). Import the workflow JSON into n8n. Set credentials in all necessary nodes. Activate the workflow.

🔁 What This Workflow Does This automation fetches daily AI-related articles from trusted RSS feeds, summarizes them using OpenAI (GPT), and generates a ready-to-post LinkedIn update in your writing style. It then emails the post to you every morning for review and publishing. High-Level Steps: Triggers every morning via Cron. Fetches latest AI news from multiple RSS sources. Filters recent articles (last 24 hrs). Summarizes each article using OpenAI (ChatGPT). Generates a LinkedIn-style post using your tone. Sends the post to your Gmail for review. ⚙️ Setup Steps Estimated setup time: 15–30 minutes You’ll need: OpenAI API key Gmail account connected in n8n RSS feed URLs (defaults are provided) Add your email in the Gmail node to receive daily posts. Add your tone/style prompt in the ChatGPT nodes (instructions inside workflow).

How it works Automatically generates trending LinkedIn content topics using AI Researches current industry angles and hooks Writes posts in your authentic voice using OpenAI Creates professional images with DALL-E Posts everything on schedule without manual intervention Set up steps Connect OpenAI API for content generation and image creation Link LinkedIn API for automated posting Configure scheduling triggers (daily/weekly posting) Customize prompts to match your writing style and industry Set up content approval workflows (optional) Results you can expect 400% increase in profile views within 3 weeks Generate 120+ posts per month vs manual 12 posts Free up 15+ hours weekly for revenue-generating activities Consistent posting schedule that builds audience engagement Professional content that converts followers to clients Time to set up: 30-45 minutes Technical level: Beginner to intermediate APIs required: OpenAI, LinkedIn API Cost: OpenAI usage fees only (approximately $5-15/month) This workflow transforms LinkedIn content creation from a time-consuming daily task into a fully automated system that works while you sleep. Perfect for entrepreneurs, marketers, and content creators who want consistent LinkedIn presence without the manual effort.

This n8n template demonstrates how to calculate the evaluation metric "RAG document groundedness" which in this scenario, measures the ability to provide or reference information included only in retrieved vector store documents. The scoring approach is adapted from https://cloud.google.com/vertex-ai/generative-ai/docs/models/metrics-templates#pointwise_groundedness How it works This evaluation works best for an agent that requires document retrieval from a vector store or similar source. For our scoring, we need to collect the agent's response and the documents retrieved and use an LLM to assess if the former is based off the latter. A key factor is to look out information in the response which is not mentioned in the documents. A high score indicates LLM adherence and alignment whereas a low score could signal inadequate prompt or model hallucination. Requirements n8n version 1.94+ Check out this Google Sheet for a sample data https://docs.google.com/spreadsheets/d/1YOnu2JJjlxd787AuYcg-wKbkjyjyZFgASYVV0jsij5Y/edit?usp=sharing

How it works: This workflow automates the entire LinkedIn content distribution process — from AI-powered post creation to auto-posting on both personal LinkedIn profiles and LinkedIn groups, using GPT-4o and Google Sheets as the content source and control panel. Auto-generates professional LinkedIn posts from spreadsheet topics using GPT-4o. Posts to your LinkedIn profile and multiple groups. Updates status to avoid duplicate posting. Fully customizable and reusable with your spreadsheet. Set up Steps Create and Upload the Spreadsheet Name it: Linkedin Post Sheet1 (for post topics): Columns: ID | Linkedin Post Title | Status Add post titles under Linkedin Post Title Set Status to Pending Create new sheet name as "Groups" (for group distribution): Column: GroupIds Add LinkedIn Group IDs, one per row Connect Google Sheets Nodes Connect your Google account to these nodes: Linkedin Post topic (Reads post topics) Get group id (Reads LinkedIn groups) Update Status (Writes back the status after posting) Configure GPT-4o (OpenAI) Add your OpenAI API key in the Linkedin Post creator node This node will generate high-quality content from your topic titles Connect LinkedIn Account Add your LinkedIn credentials in the Linkedin user detail node Ensure appropriate permissions to post on profile and groups Activate the Workflow : Once live, the workflow will: Monitor the Google Sheet for Pending posts. Generate content via GPT-4o. Post to: Your LinkedIn Profile Each LinkedIn Group listed in the Groups sheet Update the post Status to Posted Customization Tips Want to personalize this template? Change AI tone or style in the OpenAI node prompt Add a scheduler node if you'd like to post at fixed intervals Use a Slack or Telegram approval step before posting Integrate analytics tools to track post performance Suggested Sticky Notes for Workflow | Node or Section | Sticky Note Content | | ---------------------- | --------------------------------------------------------------------------- | | Linkedin Post topic | Reads the topic titles and statuses from Sheet1 | | OpenAI (GPT-4o) | Generates content using topic title — you can modify the tone/prompt here | | Linkedin user detail | Your personal LinkedIn credentials — required to post | | Group loop | Iterates through LinkedIn Group IDs and posts the content | | Update Status | Updates spreadsheet so the topic isn't re-posted |

Use case When working with multiple teams, bugs must get in front of the right team as quickly as possible to be resolved. Normally this includes a manual grooming of new bugs that have arrived in your ticketing system (in our case Linear). We found this way too time-consuming. That's why we built this workflow. What this workflow does This workflow triggers every time a Linear issue is created or updated within a certain team. For us at n8n, we created one general team called Engineering where all bugs get added in the beginning. The workflow then checks if the issue meets the criteria to be auto-moved to a certain team. In our case, that means that the description is filled, that it has the bug label, and that it's in the Triage state. The workflow then classifies the bug using OpenAI's GPT-4 model before updating the team property of the Linear issue. If the AI fails to classify a team, the workflow sends an alert to Slack. Setup Add your Linear and OpenAi credentials Change the team in the Linear Trigger to match your needs Customize your teams and their areas of responsibility in the Set me up node. Please use the format Teamname. Also, make sure that the team names match the names in Linear exactly. Change the Slack channel in the Set me up node to your Slack channel of choice. How to adjust it to your needs Play around with the context that you're giving to OpenAI, to make sure the model has enough knowledge about your teams and their areas of responsibility Adjust the handling of AI failures to your needs How to enhance this workflow At n8n we use this workflow in combination with some others. E.g. we have the following things on top: We're using an automation that enables everyone to add new bugs easily with the right data via a /bug command in Slack (check out this template if that's interesting to you) This workflow was built using n8n version 1.30.0

This n8n workflow demonstrates how to automate oftern time-consuming form filling tasks in the early stages of the tendering process; the Request for Proposal document or "RFP". It does this by utilising a company's knowledgebase to generating question-and-answer pairs using Large Language Models. How it works A buyer's RFP is submitted to the workflow as a digital document that can be parsed. Our first AI agent scans and extracts all questions from the document into list form. The supplier sets up an OpenAI assistant prior loaded with company brand, marketing and technical documents. The workflow loops through each of the buyer's questions and poses these to the OpenAI assistant. The assistant's answers are captured until all questions are satisified and are then exported into a new document for review. A sales team member is then able to use this document to respond quickly to the RFP before their competitors. Example Webhook Request curl --location 'https://<n8n_webhook_url>' \ --form 'id="RFP001"' \ --form 'title="BlueChip Travel and StarBus Web Services"' \ --form 'reply_to="jim@example.com"' \ --form 'data=@"k9pnbALxX/RFP Questionnaire.pdf"' Requirements An OpenAI account to use AI services. Customising the workflow OpenAI assistants is only one approach to hosting a company knowledgebase for AI to use. Exploring different solutions such as building your own RAG-powered database can sometimes yield better results in terms of control of how the data is managed and cost.