AI Automation
923 Ergebnisse — ausschließlich quellenverknüpfte n8n-Referenzen
Detect hallucinations using specialised Ollama model bespoke-minicheck
Fact-Checking Workflow Documentation Overview This workflow is designed for automated fact-checking of texts. It uses AI models to compare a given text with a list of facts and identify potential discrepancies or hallucinations. Components 1. Input The workflow can be initiated in two ways: a) Manually via the "When clicking 'Test workflow'" trigger b) By calling from another workflow via the "When Executed by Another Workflow" trigger Required inputs: facts: A list of verified facts text: The text to be checked 2. Text Preparation The "Code" node splits the input text into individual sentences Takes into account date specifications and list elements 3. Fact Checking Each sentence is individually compared with the given facts Uses the "bespoke-minicheck" Ollama model for verification The model responds with "Yes" or "No" for each sentence 4. Filtering and Aggregation Sentences marked as "No" (not fact-based) are filtered The filtered results are aggregated 5. Summary A larger language model (Qwen2.5) creates a summary of the results The summary contains: Number of incorrect factual statements List of incorrect statements Final assessment of the article's accuracy Usage Ensure the "
C
UTM Link Creator & QR Code Generator with Scheduled Google Analytics Reports
UTM Link Creator & QR Code Generator with Scheduled Google Analytics Reports This workflow enables marketers to generate UTM-tagged links, convert them into QR codes, and automate performance tracking in Google Analytics with scheduled reports every 7 days. This solution helps monitor traffic sources from different marketing channels and optimize campaign performance based on analytics data. Prerequisites Before implementing this workflow, ensure you have the following: Google Analytics 4 (GA4) Account & Access Ensure you have a GA4 property set up. Access to the GA4 Data API to schedule performance tracking. Refer to the Google Analytics Data API Overview for more information. Airtable Account & API Key Create an Airtable base to store UTM links, QR codes, and analytics data. Obtain an Airtable API key from your Account Settings. Detailed instructions are available in the Airtable API Authentication Guide. Step-by-Step Guide to Setting Up the Workflow 1. Generate UTM Links Create a form or interface to input: Base URL** (e.g., https://example.com) Campaign Name** (utm_campaign) Source** (utm_source) Medium** (utm_medium) Term** (Optional: utm_term) Content** (Optional: utm_content
Allow Users to Send a Sequence of Messages to an AI Agent in Telegram
Use Case When creating chatbots that interface through applications such as Telegram and WhatsApp, users can often sends multiple shorter messages in quick succession, in place of a single, longer message. This workflow accounts for this behaviour. What it Does This workflow allows users to send several messages in quick succession, treating them as one coherent conversation instead of separate messages requiring individual responses. How it Works When messages arrive, they are stored in a Supabase PostgreSQL table The system waits briefly to see if additional messages arrive If no new messages arrive within the waiting period, all queued messages are: Combined and processed as a single conversation Responded to with one unified reply Deleted from the queue Setup Create a table in Supabase called message_queue. It needs to have the following columns: user_id (uint8), message (text), and message_id (uint8) Add your Telegram, Supabase, OpenAI, and PostgreSQL credentials Activate the workflow and test by sending multiple messages the Telegram bot in one go Wait ten seconds after which you will receive a single reply to all of your messages How to Modify it to Your Needs Change the val
Extract license plate number from image uploaded via an n8n form
What it does This is a simplistic demo workflow showing how to extract a license plate number from an image of a car submitted via a form – or in more general terms showcasing how you can: use a form trigger to upload files and feed it into an LLM use a changeable LLM model for image-to-text analysis Set up steps Import the workflow Ensure you have registered and account, purchased some credits and created and API key for OpenRouter.ai Create/adapt the OpenRouter credential with your indivial API key for OpenRouter "Test workflow" and submit an image of a car with license plate to extract its number How to adapt By changing the "prompt" in th "Settings" node you can quickly adapt this exemplatory workflow to other image-to-text use cases, such as: summarization: "summarize what's seen in the image" location finding: "identify the location where the image was taken" text extraction: "extract all text from the image and return it as markdown" Thanks to using OpenRouter, you also can quickly experiment with finding good model choices by simply changing the "model" in the "Settings" node. The following models gave good results for this demo use-case: google/gemini-2.0-flash-001 meta-ll
A Very Simple "Human in the Loop" Email Response System Using AI and IMAP
Functionality This workflow automates the handling of incoming emails by summarizing their content, generating appropriate responses, and validating the responses through a "Human-in-the-Loop" system. It integrates with IMAP email services (e.g., Gmail, Outlook) and uses AI models to streamline the email response process. The workflow ensures that all AI-generated responses are reviewed by a human before being sent, maintaining a high level of professionalism and accuracy. This approach is particularly useful for businesses that receive a high volume of emails and need to respond quickly while ensuring quality control. How It Works Email Trigger: The workflow starts with the Email Trigger (IMAP) node, which monitors an email inbox for new messages. When a new email arrives, it triggers the workflow. Email Preprocessing: The Markdown node converts the email's HTML content into plain text for easier processing by the AI models. Email Summarization: The Email Summarization Chain node uses an AI model (OpenAI) to generate a concise summary of the email. The summary is limited to 100 words and is written in a professional tone. Email Response Generation: The Write email node uses an AI
Slack slash commands AI Chat Bot
This is a response chatbot in public channels through slash commands. I explain more in detail through the YouTube video, but it's only available in Korean. How it works? When you request the created slash command in Slack, the request comes to the webhook. Then, the Switch Node branches appropriately according to each slash command request. Here, a slash command called /ask is connected to the chatbot, and the chatbot generates answers to the questions asked. The final node responds to the channel. Set up steps Create a Slack app. Add chat:write permission in Slack OAuth&Permissions>Scopes. Create a Command in Slack Slash Commands menu and enter the n8n Webhook node's URL. Complete creating the Slash Commands. Enter the created command in the Switch node. 슬래시 커맨드를 통한 공개 채널에서의 응답 챗봇 입니다. 유튜브 영상에 더 자세하게 설명 드립니다. 설명 슬랙에 생성한 슬래시 커맨드를 슬랙에서 요청하면 웹훅에 요청이 들어옵니다. 이후 Switch Node에서 각 슬래시 커맨드의 요청에 따라 알맞게 분기합니다. 여기에서는 /ask라는 슬래시 커맨드가 챗봇으로 연결되어 있고, 챗봇에서 질문한 내용의 답변을 생성합니다. 마지막 노드에서 채널로 응답을 합니다. 설정 방법 Slack 앱을 만드세요. Slack OAuth&Permissions>Scopes 에서 chat:write 권한을 추가하세요. Slack Slash Commands 메뉴에서 Command를 생성하고, n8n Webhook 노드의 url을 입력하세요. Slash Slash Commands 생성을 완료하세요. Switch 노드에 생성한 커맨드를
SUse OpenRouter in n8n versions <1.78
What it is: In version 1.78, n8n introduced a dedicated node to use the OpenRouter service, which lets you to use a lot of different LLM models and providers and change models on the fly in an agentic workflow. For prior n8n versions, there's a workaround to make OpenRouter accessible, by using the OpenAI node with a OpenRouter-specific BaseURL. This trivial workflow demonstrates this for version before 1.78, so that you can use different LLM model dynamically with the available n8n nodes for OpenAI LLM and OpenAI credentials. What you can do: Use any of the OpenRouter models Have the model even dynamically configured or changing (by some external config, some rule, or some specific chat message) Setup steps: Import the workflow Ensure you have registered and account, purchased some credits and created and API key for OpenRouter.ai Configure the "OpenRouter" credentials with your own credentials, using an OpenAI type credential, but making sure in the credential's config form its "Base URL" is set to https://openrouter.ai/api/v1 so OpenRouter is used instead of OpenAI. Open the "Settings" node and change the model value to any valid model id from the OpenRouter models list or even
W
Upload to Instagram, TikTok & YouTube from Google Drive
Description This automation template is designed for content creators, digital marketers, and social media managers looking to simplify their video posting workflow. It automates the process of generating engaging video descriptions and uploading content to both Instagram and TikTok, making your social media management more efficient and error-free. Who Is This For? Content Creators & Influencers:** Streamline your video uploads and focus more on creating content. Digital Marketers:** Ensure consistent posting across multiple platforms with minimal manual intervention. Social Media Managers:** Automate repetitive tasks and maintain a steady online presence. What Problem Does This Workflow Solve? Manually creating descriptions and uploading videos to different platforms can be time-consuming and error-prone. This workflow addresses these challenges by: Automating Video Uploads:** Monitors a designated Google Drive folder for new videos. Generating Descriptions:** Uses OpenAI to transcribe video audio and generate engaging, customized social media descriptions. Ensuring Multi-Platform Consistency:** Simultaneously posts your video with the generated description to Instagram and TikTo
Fetch Dynamic Prompts from GitHub and Auto-Populate n8n Expressions in Prompt
Who Is This For? This workflow is designed for AI engineers, automation specialists, and content creators who need a scalable system to dynamically manage prompts stored in GitHub. It eliminates manual updates, enforces required variable checks, and ensures that AI interactions always receive fully processed prompts. 🚀 What Problem Does This Solve? Manually managing AI prompts can be inefficient and error-prone. This workflow: ✅ Fetches dynamic prompts from GitHub ✅ Auto-populates placeholders with values from the setVars node ✅ Ensures all required variables are present before execution ✅ Processes the formatted prompt through an AI agent 🛠 How This Workflow Works This workflow consists of three key branches, ensuring smooth prompt retrieval, variable validation, and AI processing. 1️⃣ Retrieve the Prompt from GitHub (HTTP Request → Extract from File → SetPrompt) The workflow starts manually or via an external trigger. It fetches a text-based prompt stored in a GitHub repository. The Extract from File Node retrieves the content from the GitHub file. The SetPrompt Node stores the prompt, making it accessible for processing. 📌 Note: The prompt must contain n8n expression format v
Open Deep Research - AI-Powered Autonomous Research Workflow
Open Deep Research - AI-Powered Autonomous Research Workflow Description This workflow automates deep research by leveraging AI-driven search queries, web scraping, content analysis, and structured reporting. It enables autonomous research with iterative refinement, allowing users to collect, analyze, and summarize high-quality information efficiently. How it works 🔹 User Input The user submits a research topic via a chat message. 🧠 AI Query Generation A Basic LLM generates up to four refined search queries to retrieve relevant information. 🔎 SERPAPI Google Search The workflow loops through each generated query and retrieves top search results using the SerpAPI API. 📄 Jina AI Web Scraping Extracts and summarizes webpage content from the URLs obtained via SerpAPI. 📊 AI-Powered Content Evaluation An AI Agent evaluates the relevance and credibility of the extracted content. 🔁 Iterative Search Refinement If the AI finds insufficient or low-quality information, it generates new search queries to improve results. 📜 Final Report Generation The AI compiles a structured markdown report, including sources with citations. Set Up Instructions 🚀 Estimated setup time: ~10-15 minutes ✅ Re
Host Your Own AI Deep Research Agent with n8n, Apify and OpenAI o3
This template attempts to replicate OpenAI's DeepResearch feature which, at time of writing, is only available to their pro subscribers. > An agent that uses reasoning to synthesize large amount of online information and complete multi-step research tasks for you. Source Though the inner workings of DeepResearch have not been made public, it is presumed the feature relies on the ability to deep search the web, scrape web content and invoking reasoning models to generate reports. All of which n8n is really good at! Using this workflow, n8n users can enjoy a variation of the Deep Research experience for themselves and their teams at a fraction of the cost. Better yet, learn and customise this Deep Research template for their businesses and/or organisations. Check out the generated reports here: https://jimleuk.notion.site/19486dd60c0c80da9cb7eb1468ea9afd?v=19486dd60c0c805c8e0c000ce8c87acf How it works A form is used to first capture the user's research query and how deep they'd like the researcher to go. Once submitted, a blank Notion page is created which will later hold the final report and the researcher gets to work. The user's query goes through a recursive series of web serc
WAuthor and Publish Blog Posts From Google Sheets
What it is: An automation to plan→draft→finalize and publish your textual blog post ideas to your wordpress blog Works in stages and hand back control to you in between those You can use a Google Spreadsheet for planning topics and configuring LLM models and prompts What it does: plans→drafts→finalizes blog post topics you specify in a Google Spreadsheet using an LLM with prompts that also ar configured in that spreadsheet (even which model to use) savs the results in the corresponding columns of the "Schedule" sheet in the spreadsheet hands control back to the user for inspecting or changing the results and for setting the next "Action" for th workflow Finally publishes the blog post to your Wordpress instance Limitations Probably slightly over-engineered ;-) No media generation yet some LLM models don't work because of their output format How it works: The Workflow is triggered manually or scheduled every hour It ingests a Google Spreadsheet to get Config for prompts/context tc Blog-Topics and their status and next action Depending on each blog topics "Status" and "Action" it then either uses an LLM for th next action ("plan"→"draft"→"final" actions) or publishes the written cont
S🤖🧠 AI Agent Chatbot + LONG TERM Memory + Note Storage + Telegram
This workflow template creates an AI agent chatbot with long-term memory and note storage using Google Docs and Telegram integration. Google Docs Integration 📄 n8n Google Docs Node Setup Google Credentials Telegram Integration 💬 Telegram Setup Core Features 🌟 AI Agent Integration 🤖 Implements a sophisticated AI agent with memory management capabilities Uses GPT-4o-mini and DeepSeek models for intelligent conversation handling Maintains context awareness through session management Memory System 🧠 Long-term memory storage using Google Docs Separate note storage system for specific information Window buffer memory for maintaining conversation context Intelligent memory retrieval and storage mechanisms Communication Interface 💬 Telegram integration for message handling Real-time message processing and response generation Technical Components 🔧 Memory Architecture 📚 Dual storage system separating memories from notes Automated memory retrieval before each interaction Structured memory saving with timestamps AI Models 🤖 Primary GPT-4o-mini mini model for general interactions DeepSeek-V3 Chat for specialized processing Custom agent system with tool integration Storage Integration
RAG:Context-Aware Chunking | Google Drive to Pinecone via OpenRouter & Gemini
Workflow based on the following article. https://www.anthropic.com/news/contextual-retrieval This n8n automation is designed to extract, process, and store content from documents into a Pinecone vector store using context-based chunking. The workflow enhances retrieval accuracy in RAG (Retrieval-Augmented Generation) setups by ensuring each chunk retains meaningful context. Workflow Breakdown: 🔹 Google Drive - Retrieve Document: The automation starts by fetching a source document from Google Drive. This document contains structured content, with predefined boundary markers for easy segmentation. 🔹 Extract Text Content - Once retrieved, the document’s text is extracted for processing. Special section boundary markers are used to divide the text into logical sections. 🔹 Code Node - Create Context-Based Chunks: A custom code node processes the extracted text, identifying section boundaries and splitting the document into meaningful chunks. Each chunk is structured to retain its context within the entire document. 🔹 Loop Node - Process Each Chunk: The workflow loops through each chunk, ensuring they are processed individually while maintaining a connection to the overall document c
B
Test Webhooks in n8n Without Changing WEBHOOK_URL (PostBin & BambooHR Example)
Using PostBin to Test Webhooks Without Changing WEBHOOK_URL How it Works Many new n8n users struggle with testing webhooks when running n8n on localhost, as external services cannot reach localhost. This workflow introduces a technique using PostBin, which provides a temporary, publicly accessible URL to receive webhook requests. Generates a temporary webhook endpoint via PostBin. Uses this endpoint in place of localhost to test webhooks. Captures and displays the incoming webhook request data. Enables debugging and iterating without modifying the WEBHOOK_URL environment variable. Set Up Steps Estimated time:** ~5–10 minutes Create a PostBin instance to generate a publicly accessible webhook URL. Copy the PostBin URL and use it as the webhook destination in n8n. Trigger the webhook from an external service or manually. Inspect the request payload in PostBin to verify data reception. (EXAMPLE) Using PostBin for Webhook Testing in a BambooHR Integration How it Works In this example, we apply the PostBin technique to a BambooHR integration. Instead of manually configuring a webhook in BambooHR, this workflow automates webhook registration using the BambooHR API. The workflow: Uses the
CAutomate Pinterest Analysis & AI-Powered Content Suggestions With Pinterest API
Automate Pinterest Analysis & AI-Powered Content Suggestions With Pinterest API This workflow automates the collection, analysis, and summarization of Pinterest Pin data to help marketers optimize content strategy. It gathers Pinterest Pin performance data, analyzes trends using an AI agent, and delivers actionable insights to the Marketing Manager via email. This setup is ideal for content creators and marketing teams who need weekly insights on Pinterest trends to refine their content calendar and audience engagement strategy. Prerequisites Before setting up this workflow, ensure you have the following: Pinterest API Access & Developer Account Sign up at Pinterest Developers and obtain API credentials. Ensure you have access to both Organic and Paid Pin data. Airtable Account & API Key Create an account at Airtable and set up a database. Obtain an API key from Account Settings. AI Agent for Trend Analysis An AI-powered agent (such as OpenAI's GPT or a custom ML model) is required to analyze Pinterest trends. Ensure integration with your workflow automation tool (e.g., Zapier, Make, or a custom Python script). Email Automation Setup Configure an SMTP email service (e.g., Gmail, Ou
S🐋🤖 DeepSeek AI Agent + Telegram + LONG TERM Memory 🧠
This n8n workflow template is designed to integrate a DeepSeek AI agent with Telegram, incorporating long-term memory capabilities for personalized and context-aware responses. Here's a detailed breakdown: Core Features Telegram Integration Uses a webhook to receive messages from Telegram users. Validates user identity and message content before processing. AI-Powered Responses Employs DeepSeek's AI models for conversational interactions. Includes memory capabilities to personalize responses based on past interactions. Error Handling Sends an error message if the input cannot be processed. Model Options 🧠 DeepSeek-V3 Chat**: Handles general conversational tasks. DeepSeek-R1 Reasoning**: Provides advanced reasoning capabilities for complex queries. Memory Buffer Window**: Maintains session context for ongoing conversations. Quick Setup 🛠️ Telegram Webhook Configuration Set up a webhook using the Telegram Bot API: https://api.telegram.org/bot{my_bot_token}/setWebhook?url={url_to_send_updates_to} Replace {my_bot_token} with your bot's token and {url_to_send_updates_to} with your n8n webhook URL. Verify the webhook setup using: https://api.telegram.org/bot{my_bot_token}/getWebhookInf
Effortless Email Management with AI-Powered Summarization & Review
How it Works This workflow automates the handling of incoming emails, summarizes their content, generates appropriate responses using a retrieval-augmented generation (RAG) approach, and obtains approval or suggestions before sending replies. Below is an explanation of its functionality divided into two main sections: Email Handling and Summarization: The process begins with the Email Trigger (IMAP) node which listens for new emails in a specified inbox. Once an email is received, the Markdown node converts its HTML content into plain text if necessary, followed by the Email Summarization Chain that uses AI to create a concise summary of up to 100 words. Response Generation and Approval: A Write email node generates a professional response based on the summarized content, ensuring brevity and professionalism while keeping within the word limit. Before sending out any automated replies, the system sends these drafts via Gmail for human review and approval through the Gmail node configured with free-text response options. If approved, the finalized email is sent back to the original sender using the Send Email node; otherwise, it loops back for further edits or manual intervention. A
AI-powered email processing autoresponder and response approval (Yes/No)
How it Works This workflow is designed to automate the process of handling incoming emails, summarizing their content, generating appropriate responses, and obtaining approval before sending replies. Below are the key operational steps: Email Reception and Summarization: The workflow starts with an Email Trigger (IMAP) node that listens for new emails in a specified inbox. Once an email is received, its HTML content is processed by a Markdown node to convert it into plain text if necessary, followed by an Email Summarization Chain node which uses AI to create a concise summary of the email's content using prompts tailored for this purpose. Response Generation and Approval: A Write email node generates a professional response based on the summarized content, utilizing predefined templates and guidelines such as keeping responses under 100 words and ensuring they're formatted correctly in HTML. Before sending out any automated replies, the system sends these drafts via Gmail for human review and approval through a Gmail node configured with double-approval settings. If approved (Approve?), the finalized email is sent back to the original sender using the Send Email node; otherwise, i
AI Automated HR Workflow for CV Analysis and Candidate Evaluation
How it Works This workflow automates the process of handling job applications by extracting relevant information from submitted CVs, analyzing the candidate's qualifications against a predefined profile, and storing the results in a Google Sheet. Here’s how it operates: Data Collection and Extraction: The workflow begins with a form submission (On form submission node), which triggers the extraction of data from the uploaded CV file using the Extract from File node. Two informationExtractor nodes (Qualifications and Personal Data) are used to parse specific details such as educational background, work history, skills, city, birthdate, and telephone number from the text content of the CV. Processing and Evaluation: A Merge node combines the extracted personal and qualification data into a single output. This merged data is then passed through a Summarization Chain that generates a concise summary of the candidate’s profile. An HR Expert chain evaluates the candidate against a desired profile (Profile Wanted), assigning a score and providing considerations for hiring. Finally, all collected and processed data including the evaluation results are appended to a Google Sheets document v
SChat with Postgresql Database
Who is this template for? This workflow template is designed for any professionals seeking relevent data from database using natural language. How it works Each time user ask's question using the n8n chat interface, the workflow runs. Then the message is processed by AI Agent using relevent tools - Execute SQL Query, Get DB Schema and Tables List and Get Table Definition, if required. Agent uses these tool to form and run sql query which are necessary to answer the questions. Once AI Agent has the data, it uses it to form answer and returns it to the user. Set up instructions Complete the Set up credentials step when you first open the workflow. You'll need a Postgresql Credentials, and OpenAI api key. Template was created in n8n v1.77.0
AI-Powered Email Automation for Business: Summarize & Respond with RAG
This workflow is ideal for businesses looking to automate their email responses, especially for handling inquiries about company information. It leverages AI to ensure accurate and professional communication. How It Works Email Trigger: The workflow starts with the Email Trigger (IMAP) node, which monitors an email inbox for new messages. When a new email arrives, it triggers the workflow. Email Preprocessing: The Markdown node converts the email's HTML content into plain text for easier processing by the AI models. Email Summarization: The Email Summarization Chain node uses an AI model (DeepSeek R1) to generate a concise summary of the email. The summary is limited to 100 words and is written in Italian. Email Classification: The Email Classifier node categorizes the email into predefined categories (e.g., "Company info request"). If the email does not fit any category, it is classified as "other". Email Response Generation: The Write email node uses an AI model (OpenAI) to draft a professional response to the email. The response is based on the email content and is limited to 100 words. The Review email node uses another AI model (DeepSeek) to review and format the drafted respo
Modular & Customizable AI-Powered Email Routing: Text Classifier for eCommerce
How It Works Form Submission: The workflow starts with the On form submission node, which triggers when a user submits a contact form. The form collects the user's name, email, and message. Text Classification: The Text Classifier node uses an AI model (GPT-4) to classify the submitted message into one of the predefined categories: Request Quote: For quote requests. Product info: For general product inquiries. General problem: For issues or problems related to products. Order: For questions about placed orders. Other: For any messages that don’t fit the above categories. Email Routing: Based on the classification, the workflow routes the message to the appropriate department via email: Prod. Dep.: For product-related inquiries. Quote Dep.: For quote requests. Gen. Dep.: For general problems. Order Dep.: For order-related questions. Other Dep.: For all other inquiries. Each email includes the user's name, email, message, and the classified category. Data Logging: The workflow logs the form submission and classification results into a Google Sheets document. Each department has its own sheet where the data is appended, including: User’s name, email, and message. Submission date and t
BBambooHR AI-Powered Company Policies and Benefits Chatbot
How it works This workflow enables companies to provide instant HR support by automating responses to employee queries about policies and benefits: Retrieves company policies, benefits, and HR documents from BambooHR. Uses AI to analyze and answer employee questions based on company records. Identifies the most relevant contact person for escalations. Seamlessly integrates with company systems to provide real-time HR assistance. Set up steps: Estimated time: ~20 minutes Connect your BambooHR account to allow policy retrieval. Configure AI parameters and access control settings. (Optional) Set up the employee lookup tool for personalized responses. Test the chatbot to ensure accurate responses and seamless integration. Benefits This workflow is perfect for HR teams looking to enhance employee support while reducing manual inquiries. Outperform BambooHR's "Ask BambooHR" Chatbot #1. Superior specificity of replies to general inquiries #2. More appropriate escalations when responding to sensitive employee concerns