Workflow Templates

This template shows how to use the Question and Answer tool to save costs in RAG use cases. Who is this for? This template is for everyone who wants to start giving knowledge to their Agents through RAG. Requirements Have a PDF with custom knowledge that you want to provide to your agent. Setup No setup required. Just hit Execute Workflow, upload your knowledge document and then start chatting. How to customize this to your needs Add custom instructions to your Agent by changing the prompts in it. Add a different way to load in knowledge to your vector store, e.g. by looking at some Google Drive files or loading knowledge from a table. Describe your data properly in the Q&A tool Exchange the Simple Vector Store nodes with your own vector store tools ready for production. Add a more sophisticated way to rank files found in the vector store. For more information read our docs on RAG in n8n.

AI evaluation in n8n This is a template for n8n's evaluation feature. Evaluation is a technique for getting confidence that your AI workflow performs reliably, by running a test dataset containing different inputs through the workflow. By calculating a metric (score) for each input, you can see where the workflow is performing well and where it isn't. How it works This template shows how to calculate a workflow evaluation metric: whether a specific tool was called by an agent. We use an evaluation trigger to read in our dataset It is wired up in parallel with the regular trigger so that the workflow can be started from either one. More info We make sure that the agent outputs the list of tools that it used We then check whether the expected tool (from the dataset) is in that list Finally we pass this information back to n8n as a metric

It allows you to automate candidate retrieval and onboarding in your HR processes. How it works It monitors a Gmail address for new emails with a PDF attachment It expects the PDF to be a candidate’s CV, extracts the text using OCR, and then structures the data using ChatGPT Once the data is processed, it connects to Notion and adds (or updates) an entry in the specified database How to use Configure your Gmail account and provide your ChatGPT API key Provide an API key for the OCR service in a variable named OCR_SPACE_API_KEY Connect your Notion account Once everything is configured, the workflow will monitor your inbox for new emails. Just send an email with a PDF attachment to the configured address Requirements In addition to Gmail, ChatGPT, and Notion, the system uses a third-party OCR API (OCR SPACE). You’ll need to create an account and obtain an API key You must map the fields returned by ChatGPT to the Notion database, or use the same field names we are using Customising It should be easy to replace Notion with PostgreSQL or another database if needed

Who is this for? This workflow is designed for developers, DevOps engineers, and automation specialists who manage multiple n8n workflows and need a reliable way to monitor for failures and receive alerts in real time. What problem is this workflow solving? Monitoring multiple workflows can be challenging, especially when silent failures occur. This workflow helps ensure you're immediately informed whenever another workflow fails, reducing downtime and improving system reliability. What this workflow does The solution consists of two parts: ERROR NOTIFIER: A centralized workflow that sends alerts through your chosen communication channel (e.g., Telegram, WhatsApp, Gmail). ERROR ALERTER: A node snippet to be added to any workflow you want to monitor. It captures errors and triggers the ERROR NOTIFIER workflow. Once set up, this system provides real-time error alerts for all integrated workflows. Setup Import both workflows: ERROR NOTIFIER (centralized alert handler) ERROR ALERTER (to be added to your monitored workflows) Add credentials for your preferred alert channel: WhatsApp (OAuth or API) Telegram Gmail Discord Slack Activate the workflows: Ensure ERROR NOTIFIER is active and ready to receive triggers. Paste ERROR ALERTER at the end of each workflow you want to monitor, connecting it to the error branch. Sign up for a free consultation and find out how n8n can help you.

Workflow Description Who is this for? This workflow is designed for sales and revenue teams using Gong and Salesforce to track and analyze sales calls. It helps automate the extraction, filtering, and preprocessing of Gong call data for further AI analysis. What problem is this solving? Sales teams often generate large amounts of call data, but not all calls are relevant for deeper analysis. This workflow filters calls based on predefined criteria, extracts relevant metadata, and formats the data before passing it to an AI processing pipeline. What this workflow does Triggers on new Gong calls synced to Salesforce** every hour. Filters calls based on opportunity stage** (Discovery or Meeting Booked). Retrieves Gong call details** via API. Formats call data into a structured JSON object** for AI processing. Passes the structured data to a Gong Call Preprocessor workflow** for further insights. Setup Ensure that you have connected Salesforce and Gong APIs with valid credentials. Modify the Salesforce query in Get all custom Salesforce Gong Objects to match your organization’s requirements. Set the schedule trigger interval in the Run Hourly node if needed. Connect this workflow to an AI processing workflow to analyze call transcripts. Workflow Templates: CallForge - 01 - Filter Gong Calls Synced to Salesforce by Opportunity Stage CallForge - 02 - Prep Gong Calls with Sheets & Notion for AI Summarization CallForge - 03 - Gong Transcript Processor and Salesforce Enricher CallForge - 04 - AI Workflow for Gong.io Sales Calls CallForge - 05 - Gong.io Call Analysis with Azure AI & CRM Sync CallForge - 06 - Automate Sales Insights with Gong.io, Notion & AI CallForge - 07 - AI Marketing Data Processing with Gong & Notion CallForge - 08 - AI Product Insights from Sales Calls with Notion How to customize Change filtering logic: Adjust the **opportunity stage filter (Check if Opportunity Stage is Meeting Booked or Discovery) to match your sales process. Modify data formatting**: Add or remove fields in the Format call into correct JSON Object node to customize the output. Adjust trigger frequency**: Change the Run Hourly node to run at a different interval if required.

How it works This advanced workflow transforms your long-form audio content (like podcast episodes or webinar recordings) into digestible, ready-to-use marketing assets. It's designed for podcasters, content creators, and marketers who want to maximize their content's reach. It automatically: Takes a full transcript of your audio/video content as input. Generates a concise, comprehensive summary of the episode using advanced AI. Extracts a list of key topics and keywords from the transcript, perfect for SEO, tagging, and content categorization. Delivers the summary and keywords directly to your inbox or a connected tool for easy access. Streamline your content repurposing pipeline and unlock new value from your audio and video assets with intelligent automation! Set up steps Setting up this powerful workflow typically takes around 20-30 minutes, as it involves multiple AI steps. You'll need to: Obtain API keys for your preferred AI service (e.g., OpenAI, Google AI). Have access to a method for generating transcripts from your audio/video (e.g., manually pasting, or using a separate transcription service like AssemblyAI, Whisper, etc.). Connect your preferred email service (e.g., Gmail) to receive the output. All detailed setup instructions and specific configuration guidance are provided within the workflow itself using sticky notes.

This n8n template demonstrates how to obtain token usage from AI Agents and places the data into a spreadsheet that calculates the estimated cost of the execution. Obtaining the token usage from AI Agents is tricky, because it doesn't provide all the data from tool calls. This workflow taps into the workflow execution metadata to extract token usage information. Works well with OpenAI, Google and Anthropic. Other LLM providers might need small tweaks. How it works The AI Agent executes and then calls a subworkflow to calculate the token usage. The data is stored in Google Sheets The spreadsheet has formulas to calculate the estimated cost of the execution. How to use The AI Agent is used as an example. Feel free to replace this with other agents you have. Call the subworkflow AFTER all the other branches have finished executing. Requirements LLM account (OpenAI, Gemini...) for API usage. Google Drive and Sheets credentials n8n API key of your instance

How it Works This meta-workflow is designed to intelligently scan all your active workflows in n8n, identify those that contain Webhook nodes, and automatically generate a Swagger (OpenAPI) specification based on them. The output Swagger document reflects all accessible endpoints from your Webhook nodes, making it easier to: Visualize your API structure Share your endpoints Integrate with tools like Postman or Swagger UI Enhanced Parameter Support If you want the Swagger to reflect request parameters (e.g., query or body fields), you can annotate your Webhook nodes using the Note section. When configured properly, these annotations enrich your Swagger documentation with parameter names, types, and descriptions. Setup Steps Add the WebhookDocs to n8n Import the WebhookDocs JSON file into your n8n instance. Activate the WebhookDocs (you can also use the test-endpoint) Annotate Webhook Nodes (Optional but Recommended) To enable parameter documentation, open the Note section of each Webhook node and add annotations in the following format: //@body field_name string description //@query field_name string description Open the page https://n8n.youristance.com/webhook/swagger

This n8n template demonstrates how to use OpenAI's Responses API with existing LLM and AI Agent nodes. Though I would recommend just waiting for official support, if you're impatient and would like a round-about way to integrate OpenAI's responses API into your existing AI workflows then this template is sure to satisfy! This approach implements a simple API wrapper for the Responses API using n8n's builtin webhooks. When the base url is pointed to these webhooks using a custom OpenAI credential, it's possible to intercept the request and remap for compatibility. How it works An OpenAI subnode is attached to our agent but has a special custom credential where the base_url is changed to point at this template's webhooks. When executing a query, the agent's request is forwarded to our mini chat completion workflow. Here, we take the default request and remap the values to use with a HTTP node which is set to query the Responses API. Once a response is received, we'll need to remap the output for Langchain compatibility. This just means the LLM or Agent node can parse it and respond to the user. There are two response formats, one for streaming and one for non-streaming responses. How to use You must activate this workflow to be able to use the webhooks. Create the custom OpenAI credential as instructed. Go to your existing AI workflows and replace the LLM node with the custom OpenAI credential. You do not need to copy anything else over to the existing template. Requirements OpenAI account for Responses API Customising this workflow Feel free to experiment with other LLMs using this same technique! Keep up to date with the Responses API announcements and make modifications as required.

RAG over a PDF with Weaviate This workflow allows you to upload a PDF file and ask questions about it using the Question and Answer Chain and the Weaviate Vector Store nodes. Who it's for This workflow is the simplest possible implementation of RAG with Weaviate in n8n. It's intended to act as an extendable template for RAG over your own documents. Prerequisites An existing Weaviate cluster. You can view instructions for setting up a local cluster with Docker here or a Weaviate Cloud cluster here. API keys to generate embeddings and power chat models. We use OpenAI, but feel free to switch out the models as you like. Self-hosted n8n instance. See this video for how to get set up in just three minutes. How it works Part 1: Manually upload data In this example, we manually upload a 100+ page article from arXiv called "A Survey of Large Language Models". But you can replace this with your own more advanced data pipeline, if you wish. Part 2: Embed and load data into Weaviate collection Here, we generate embeddings for the full-text of the article and store them in Weaviate. Part 3: Perform RAG over PDF file with Weaviate In this part of the workflow, you can enter your query by running the Chat Node and get a RAG response grounded in context via the Question and Answer Chain node. How to run the workflow Go through the prerequisites, creating a Weaviate cluster (can be local or cloud), downloading self-hosted n8n, and adding your API keys and other credentials. Select the embedding and chat models you'd like to use. Upload a PDF file you want to ask questions about. Execute the rest of the workflow.

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. n8n Workflow Template: AI‑Powered Mental Health Support Bot Overview: This template enables you to build a Telegram bot that delivers real‑time, empathetic mental health support. Incoming messages tagged with #vent, #insight, or #cope are routed to GPT‑4o via the AI/ML API, which returns tailored, compassionate responses. How it works: Telegram Trigger listens for new chat messages or voice notes. Show Typing Indicator immediately signals “typing…” in the chat. Switch Node examines the text prefix and routes to one of four branches (Vent, Insight, Cope, or default). Set Prompt nodes build a JSON payload with a specific role‑play prompt for each branch. AI/ML API node (model gpt-4o) generates the response. Telegram node sends the AI’s answer back to the user. Setup Steps: Connect your Telegram bot token in the Telegram credentials. Add your AI/ML API key (GPT‑4o) in n8n’s credential settings. Activate the workflow and deploy your n8n instance webhook URL to BotFather. Test by sending #vent I’m stressed, #insight Why do I feel…, or any tag in your Telegram chat. This plug‑and‑play workflow brings AI‑driven emotional support directly into Telegram.

This workflow sends the contents of an email to a Notion database. The email must be labeled with a specific label for the workflow to trigger. The email subject will be the title of the Notion page, and a snippet of the email body will be the content of the Notion page. The email link will be added to the Notion page as a property. Prerequisites Notion account and Notion credentials. Google account and Google credentials. How it works On scheduled intervals, find all emails with a specific label. For each email, check if the email already exists in the Notion database. If it does not exist, create a new page in the Notion database, otherwise do nothing. When the task in the Notion database is checked off, the label will be removed from the email. Setup This workflow requires that you set up a Notion database or use an existing one with at least the following fields: Title (title) Thread ID (text) Email thread (URL) Additionally, create a label that will be used to trigger the workflow in Gmail. In this workflow, the label is called "Notion".