Workflow Templates

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. How it works This workflow is a simple AI Agent that connects to Langfuse so send tracing data to help monitor LLM interactions. The main idea is to create a custom LLM model that allows the configuration of callbacks, which are used by langchain to connect applications such Langfuse. This is achieves by using the "langchain code" node: Connects a LLM model sub-node to obtain the model variables (model name, temp and provider) - Creates a generic langchain initChatModel with the model parameters. Return the LLM to be used by the AI Agent node. 📋 Prerequisites Langfuse instance (cloud or self-hosted) with API credentials LLM API key (Gemini, OpenAI, Anthropic, etc.) n8n >= 1.98.0 (required for LangChain code node support in AI Agent) ⚙️ Setup Add these to your n8n instance: Langfuse configuration LANGFUSE_SECRET_KEY=your_secret_key LANGFUSE_PUBLIC_KEY=your_public_key LANGFUSE_BASEURL=https://cloud.langfuse.com # or your self-hosted URL LLM API key (example for Gemini) GOOGLE_API_KEY=your_api_key Alternative: Configure these directly in the LangChain code node if you prefer not to use environment variables Import the workflow JSON Connect your preferred LLM model node Send a test message to verify tracing appears in Langfuse

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Automatically transform audio files into professional transcription reports with AI-powered speech recognition, timestamp generation, and formatted Google Docs output. What this workflow does Monitors Gmail for incoming audio attachments Downloads and processes audio files using VLM Run AI transcription Generates accurate transcriptions with precise timestamps and segmentation Creates professional reports in Google Docs with formatted output Handles asynchronous processing for long audio files without timeouts Setup Prerequisites: Gmail account, VLM Run API credentials, Google Docs access, self-hosted n8n. You need to install VLM Run community node Quick Setup: Configure Gmail OAuth2 for email monitoring Add VLM Run API credentials for audio transcription Set up Google Docs OAuth2 for report generation Create target Google Doc for transcription reports Update document URL in workflow nodes Test with sample audio file and activate Perfect for Meeting recordings and conference calls Voice memos and dictation workflows Interview transcriptions and journalism Podcast episode documentation Accessibility compliance and documentation Legal proceedings and court recordings Educational content and lecture notes Customer service call analysis Key Benefits Human-level accuracy** - Advanced AI speech recognition with automatic punctuation Timestamp precision** - Segmented transcriptions with exact time markers Multi-format support** - Handles MP3, WAV, M4A, AAC, OGG, FLAC files Asynchronous processing** - No timeouts for long audio files Professional formatting** - Beautifully structured Google Docs reports Automatic workflow** - Zero manual intervention required Saves hours per recording** - Transforms manual transcription into instant results Searchable documentation** - Google Docs integration enables easy content discovery How to customize Extend by adding: Speaker identification and diarization Integration with project management tools (Notion, Asana, Trello) Automatic summary generation from transcripts Translation to multiple languages Slack notifications for completed transcriptions Integration with CRM systems for call logging Audio quality enhancement preprocessing Custom formatting templates for different use cases Automatic keyword extraction and tagging Integration with calendar systems for meeting context This workflow revolutionizes audio documentation by combining cutting-edge AI transcription with professional report generation, making spoken content instantly accessible, searchable, and shareable across your organization.

This workflow converts Notion pages to markdown, and then converts that markdown back to Notion blocks. It will triple the content of the last updated page it finds. This is useless by itself, but you can copy-paste from this workflow to create your own. Prerequisites A notion account with some pages or databases Setup instructions Create a notion credential and share some pages as described here: https://docs.n8n.io/integrations/builtin/credentials/notion/ How it works The HTTP Request gets notion child blocks from a page, because the default n8n block only gets plain text and no links. The first code block converts it to markdown. The second code block converts it back to Notion blocks The last HTTP block appends everything to the original Notion page, essentially duplicating it for the purpose of demoing the script. I hope in the future we get official n8n blocks that extract markdown, or use markdown to write to Notion. There is community block that also does this, but this template is easier: you can simply copy-paste the blocks from this workflow.

Use case Workshop We are using this workflow in our workshops to teach how to use Tools a.k.a functions with artificial intelligence. In this specific case, we will use a generic "AI Agent" node to illustrate that it could use other models from different data providers. Enhanced Weather Forecasting In this small example, it's easy to demonstrate how to obtain weather forecast results from the Open-Meteo site to accurately display the upcoming days. This can be used to plan travel decisions, for example. What this workflow does We will make an HTTP request to find out the geographic coordinates of a city. Then, we will make other HTTP requests to discover the weather for the upcoming days. In this workshop, we demonstrate that the AI will be able to determine which tool to call first—it will first call the geolocation tool and then the weather forecast tool. All of this within a single client conversation call. Setup Insert an OpenAI Key and activate the workflow. by Davi Saranszky Mesquita https://www.linkedin.com/in/mesquitadavi/

This n8n workflow demonstrates how to transform natural language date and time expressions into structured data with 96%+ accuracy. Parse complex expressions like "early next July", "2 weeks after project launch", or "end of Q3" into precise datetime objects with confidence scoring, timezone intelligence, and business rules validation for any automation workflow. Good to know Achieves 96%+ accuracy on complex natural language date expressions At time of writing, this is the most advanced open-source date parser available Includes AI learning that improves over time with user corrections Supports 6 languages with auto-detection (English, Spanish, French, German, Italian, Portuguese) Sub-millisecond response times with intelligent caching Enterprise-grade with business intelligence and timezone handling How it works Natural Language Input**: Receives date expressions via webhook, form, email, or chat AI-Powered Parsing**: Your world-class date parser processes the text through: 50+ custom rule patterns for complex expressions Multi-language auto-detection and smart translation Confidence scoring (0.0-1.0) for AI decision-making Ambiguity detection with helpful suggestions Business Intelligence**: Applies enterprise rules automatically: Holiday calendar awareness (US + International) Working hours validation and warnings Business day auto-adjustment Timezone normalization (IANA format) Smart Scheduling**: Creates calendar events with: Structured datetime objects (start/end times) Confidence metadata for workflow decisions Alternative interpretations for ambiguous inputs Rich context for follow-up actions Integration Ready**: Outputs connect seamlessly to: Google Calendar, Outlook, Apple Calendar CRM systems (HubSpot, Salesforce) Project management tools (Notion, Asana) Communication platforms (Slack, Teams) How to use The webhook trigger receives natural language date requests from any source Replace the MCP server URL with your deployed date parser endpoint Configure timezone preferences for your organization Customize business rules (working hours, holidays) in the parser settings Connect calendar integration nodes for automatic event creation Add notification workflows for scheduling confirmations Use Cases Meeting Scheduling**: "Schedule our quarterly review for early Q3" Project Management**: "Set deadline 2 weeks after product launch" Event Planning**: "Book venue for the weekend before Labor Day" Personal Assistant**: "Remind me about dentist appointment next Tuesday morning" International Teams**: "Team standup tomorrow morning" (auto-timezone conversion) Seasonal Planning**: "Launch campaign in late spring 2025" Requirements Natural Language Date Parser MCP server (provided code) Webhook endpoint or form trigger Calendar integration (Google Calendar, Outlook, etc.) Optional: Slack/Teams for notifications Optional: Database for learning pattern storage Customizing this workflow Multi-language Support**: Enable auto-detection for global teams Business Rules**: Configure company holidays and working hours Learning System**: Enable AI learning from user corrections Integration Depth**: Connect to your existing calendar and CRM systems Confidence Thresholds**: Set minimum confidence levels for auto-scheduling Ambiguity Handling**: Route unclear dates to human review or clarification requests Sample Input/Output Input Examples: "early next July" "2 weeks after Thanksgiving" "next Wednesday evening" "Q3 2025" "mañana por la mañana" (Spanish) "first thing Monday" Rich Output: { "parsed": [{ "start": "2025-07-01T00:00:00Z", "end": "2025-07-10T23:59:59Z", "timezone": "America/New_York" }], "confidence": 0.95, "method": "custom_rules", "business_insights": [{ "type": "business_warning", "message": "Selected date range includes July 4th holiday" }], "predictions": [{ "type": "time_preference", "suggestion": "You usually schedule meetings at 10 AM" }], "ambiguities": [], "alternatives": [{ "interpretation": "Early July 2026", "confidence": 0.15 }], "performance": { "cache_hit": true, "response_time": "0.8ms" } } Why This Workflow is Unique World-Class Accuracy**: 96%+ success rate on complex expressions AI Learning**: Improves over time with user feedback Global Ready**: Multi-language and timezone intelligence Business Smart**: Enterprise rules and holiday awareness Performance Optimized**: Sub-millisecond cached responses Context Aware**: Provides confidence scores and alternatives for AI decision-making Transform your scheduling workflows from rigid form inputs to natural, conversational date requests that your users will love!

Overview In cold email campaigns, the lead's company name is the 2nd most frequently inserted variable after their first name. They're critical for effective cold email personalization. However, company names are often messy and can contain taglines, legal suffixes (e.g. LLC, Inc.), and other variations that would never be written out by a human in an email. If your email starts with "I came across Techwave Solutions LLC on LinkedIn...", it's a dead giveaway that you're sending a tempalted email and a response is much less likely. This simple workflow uses AI to clean up messy company names in a Google Sheet so that your cold email campaigns can achieve better results. How It Works A form is submitted with a Google Sheet url The workflow grabs the leads and uses an LLM node to clean the company names The updated leads are saved back in a new sheet within the original spreadsheet Setup Steps Add your Google Sheets and OpenAI (or your AI model provider of choice) credentials to n8n Create a Google Sheet with your list of leads. IMPORTANT: the sheet MUST have a column called "Company" (Optional). The AI workflow has a highly optimized system prompt. However, you may achieve better results by updating the list of examples in the prompt with companies (real or fake) in the industry you're targeting. If you have any questions or feedback about this workflow, or would like me to build custom workflows for your business, email me at n8n@paperjam.agency.

This n8n workflow provides a ready-to-use API endpoint for extracting structured data from images. It processes an image URL using an AI-powered OCR model and returns the extracted details in a structured JSON format. Use Cases Document OCR** – Extract details from ID cards, invoices, receipts, etc. Text Extraction from Images** – Process screenshots, scanned documents, and photos. Automated Form Processing** – Digitize and capture information from paper forms. Business Card Data Extraction** – Extract names, emails, and phone numbers from business cards. How It Works Send a GET request with an image URL and define the required extraction parameters. The image is converted to base64 for processing. The AI model (Gemini API - Flash Lite) extracts relevant text. The response returns structured JSON data containing only the requested fields. Features ✔️ No-Code API Setup – Easily integrate into any application. ✔️ Customizable Extraction – Modify the request parameters to fit your needs. ✔️ AI-Powered OCR – Uses advanced models for accurate text recognition. ✔️ Automated Processing – Ideal for document processing and digitization. Integration Works with any frontend/backend system that supports API calls. Can be used for workflow automation in CRM, ERP, and document management solutions. Supports further customization based on specific OCR requirements.

Company Website Chatbot Agent Overview This workflow implements a modular Website AI Chatbot Assistant capable of handling multiple types of customer interactions autonomously. Instead of relying on a single large agent to handle all logic and tools, this system routes user queries to specialized sub-agents—each dedicated to a specific function. By using a manager-style orchestration layer, this approach prevents overloading a single AI model with excessive context, leading to cleaner routing, faster execution, and easier scaling as your automation needs grow. How It Works 1. Chat Trigger The flow is initiated when a chat message is received via the website widget. 2. Manager Agent (Ultimate Website AI Assistant) The central LLM-based agent is responsible for parsing the message and deciding which specialized sub-agent to route it to. It uses an OpenAI GPT model for natural language understanding and a lightweight memory system to preserve recent context. 3. Sub-Agent Routing calendarAgent: Handles availability checks and books meetings on connected calendars. RAGAgent: Searches company documentation or FAQs to provide accurate responses from your internal knowledge base. ticketAgent: Forwards requests to human support by generating and sending support tickets to a designated email. Setup Instructions Embed the Chatbot Use a custom HTML widget or script to embed the chatbot interface on your website. Connect the frontend to the webhook that triggers the When chat message received node. Configure Your OpenAI Key Insert your API key in the OpenAI Chat Model node. Adjust the model parameters for temperature, max tokens, etc., based on how formal or creative you want the bot to be. Customize Sub-Agents calendarAgent: Connect to your Google or Outlook calendar. RAGAgent: Link to a vector store or document database via API or native integration. ticketAgent: Set the destination email and format for ticket generation (e.g. via SendGrid or SMTP). Deploy in Production Host on n8n Cloud or your self-hosted instance. Monitor usage through the Executions tab and refine prompts based on user behavior. Benefits Modular system with dedicated logic per function Reduces token bloat by offloading complexity to sub-agents Easy to scale by adding more tools (e.g. CRM, analytics) Fast and responsive user experience for customers on your site Cleaner code structure and easier debugging

This workflow automatically syncs Shopify orders with your Zendesk tickets. Using this workflow, Shopify orders will be added or have their information updated straight to your Zendesk tickets. Prerequisites Shopify account and Shopify credentials Zendesk account and Zendesk credentials How it works Shopify Trigger starts the workflow whenever an order is updated. Zendesk node finds if the order already exists and has a ticket assigned. Set node keeps and passes only ticket ID. Merge by Key node combines the Shopify order data with the Zendesk ticket data. If node splits the workflow conditionally, checks if the ticket already exists or not. If order is new, Zendesk node creates a new ticket for the order.

Overview This workflow leverages the LangChain code node to implement a fully customizable conversational agent. Ideal for users who need granular control over their agent's prompts while reducing unnecessary token consumption from reserved tool-calling functionality (compared to n8n's built-in Conversation Agent). Setup Instructions Configure Gemini Credentials: Set up your Google Gemini API key (Get API key here if needed). Alternatively, you may use other AI provider nodes. Interaction Methods: Test directly in the workflow editor using the "Chat" button Activate the workflow and access the chat interface via the URL provided by the When Chat Message Received node Customization Options Interface Settings: Configure chat UI elements (e.g., title) in the When Chat Message Received node Prompt Engineering: Define agent personality and conversation structure in the Construct & Execute LLM Prompt node's template variable ⚠️ Template must preserve {chat_history} and {input} placeholders for proper LangChain operation Model Selection: Swap language models through the language model input field in Construct & Execute LLM Prompt Memory Control: Adjust conversation history length in the Store Conversation History node Requirements: ⚠️ This workflow uses the LangChain Code node, which only works on self-hosted n8n. (Refer to LangChain Code node docs)

Quickly transform any LinkedIn profile URL into a concise, AI‑generated professional summary — perfect for recruiters, sales teams, and hiring managers who need instant insights into prospects or candidates without manual research. How it works The workflow polls a Google Sheet for new or updated rows containing LinkedIn profile URLs. For each URL, the Real‑Time LinkedIn Scraper API (via RapidAPI) pulls experience and education sections. Extracted profile data is sent to OpenAI’s GPT model, which generates a clean, structured summary highlighting key strengths, career trajectory, and differentiators. The generated summary is written back into a new column in the same row of your Google Sheet for easy review and sharing. Set up steps Connect your Google account and select the spreadsheet + worksheet containing your list of LinkedIn URLs. Sign up for the Real‑Time LinkedIn Scraper API on RapidAPI, copy your API key, and add it to the workflow’s HTTP Request node. Insert your OpenAI API key credentials. Ensure your Google Sheet has one column for “linkedin_url” and create two empty columns named “full_name” and "summary" (or customize them based on your needs). Run a single row through the workflow to verify scraping accuracy and summary formatting, then turn on the workflow for continuous automation. With this template, eliminate hours of manual profile review — instantly gain actionable insights and focus on what really matters: building relationships and closing deals.

This workflow creates/updates/deletes a Notion database page when an issue is created/updated/deleted in Jira. Subsequent updates to the issue's title or status in Jira are updated in the Notion database. If you require more fields to send to Notion, this template is easily extendible which will be described in setup. The Notion database will require setup before the workflow can be used. Prerequisites Notion account and Notion credentials. Jira account and Jira credentials. How it works When a new issue is created in Jira, the workflow creates a new page in the Notion database will all the required fields. When the issue's title or status is updated in Jira, the workflow updates the specific Notion database page identified by the "Issue Key" field in Notion. If the status in Jira is set to "Done", the workflow will mark the Notion database page "Done" field as true. When the issue is deleted in Jira, the workflow archives the Notion database page. Setup This workflow requires that you set up a Notion database. To do so, follow the steps below: In Notion, create a new database. Add the following columns to the database: Done (with type "Checkbox") Title (renamed from "Name") Status (with the following options: "To Do", "In Progress", "Done") Link (with type "URL") Issue ID (with type "Number") Issue Key (with type "Text") Add any other fields you require to the database. Your database should look something like this Share the database to n8n. By default, the workflow will fill all the fields provided above, except for any other additional fields you add.