Agents & Automations

Use this automation to log every ChatGPT conversation with Perplexity AI into Google Sheets. Track interactions by adding a new row for each chat session.

Use this template to extract candidate information with Eden AI from resumes unloaded to Google Drive into new Exchange person. Created by [email protected]

Who this is for? This workflow is designed for professionals and teams who need real-time, structured insights from Google Search results without manual effort. What problem is this workflow solving? This n8n workflow solves the problem of automating Google Search result extraction, cleanup, summarization, and AI-enhanced formatting for downstream use like sending the results to a webhook or another system. What this workflow doesAutomates Google Search via Bright Data Uses Bright Data’s proxy-based SERP API to run a Google Search query programmatically. Makes the process repeatable and scriptable with different search terms and regions/zones. Cleans and Extracts Useful Content The Google Search Data Extractor uses LLM based cleaning to remove HTML/CSS/JS from the response and extract pure text data. Converts messy, unstructured web content into structured, machine-readable format. Summarizes Search Results Through the Gemini Flash + Summarization Chain, it generates a concise summary of the search results. Ideal for users who don’t have time to read full pages of search results. Formats Data Using AI Agent The AI Agent acts like a virtual assistant that: - Understands search results - Formats them in a readable, JSON-compatible form - Prepares them for webhook deliveryDelivers Results to Webhook Sends the final summary + structured search result to a webhook (could be your app, a Slack bot, Google Sheets, or CRM). How to customize This Workflow to your needs 1. Change the Search Input Default: It searches a fixed query or dataset. Customize: - Accept input from a Google Sheet, Airtable, or a form. - Auto-trigger searches based on keywords or schedules. 2. Customize Summarization Style (LLM Output) Default: General summary using Google Gemini or OpenAI. Customize: - Add tone: formal, casual, technical, executive-summary, etc. - Focus on specific sections: pricing, competitors, FAQs, etc. - Translate the summaries into multiple languages. - Add bullet points, pros/cons, or insight tags. 3. Choose Where the Results Go Options: - Email, Slack, Notion, Airtable, Google Docs, or a dashboard. - Auto-create content drafts for WordPress or newsletters. - Feed into CRM notes or attach to Salesforce leads.

A complete LinkedIn automation system using n8n that transforms viral news stories into engaging posts—all with your personal tone of voice! This system: • Researches trending topics • Writes professional posts • Generates AI images • Publishes directly to LinkedIn with full control over what gets posted.

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

Use this template to monitor a Google Drive folder for new files, extract text using Google Cloud Vision, and add it to Google Sheets for streamlined data management.

This workflow creates a documentation system for n8n instances using Docsify.js. It serves a dynamic documentation website that allows users to: - View an overview of all workflows in a tabular format - Filter workflows by tags - Access automatically generated documentation for each workflow - Edit documentation with a live Markdown preview - Visualize workflow structures using Mermaid.js diagrams 📺 Check out the short 2-min demonstration on LinkedIn. Don't forget to connect! 🔧 Key ComponentsMain Documentation Portal - Serves a Docsify-powered website - Provides a navigation sidebar with workflow tags - Displays workflow status, creation date, and documentation links Documentation Generator - Uses GPT model to auto-generate workflow descriptions - Creates Mermaid.js diagrams of workflow structures - Maintains consistent documentation format Live Editor - Split-screen Markdown editor with preview - Real-time Mermaid diagram rendering - Save/Cancel functionality ⚙️ Technical DetailsEnvironment Setup - Requires write access to the specified project directory - Uses environment variables for n8n instance URL configuration - Implements webhook endpoints for serving documentation ⚠️ Security Considerations Note: The current implementation doesn't include authentication for editing. Consider adding authentication for production use. 🔍 Part of the n8n Observability Series This workflow is part of a broader series focused on n8n instance observability. Check out these related workflows: - Workflow Dashboard - Get comprehensive analytics of your n8n instance - Visualize Your n8n Workflows with Mermaid.js - Create beautiful workflow visualizations Each workflow in this series helps you better understand and manage your n8n automation ecosystem!

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 1. Import the workflow. 2. Ensure you have registered an account, purchased some credits, and created an API key for OpenRouter.ai. 3. Create/adapt the OpenRouter credential with your individual API key for OpenRouter. 4. "Test workflow" and submit an image of a car with a license plate to extract its number. How to adapt By changing the "prompt" in the "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-llama/llama-3.2-90b-vision-instruct - openai/gpt-4o The llama-3.2-11b and even claude-3.5-sonnet didn't recognize all characters in all test images. Using a generic LLM model offers a quick way of prototyping an image-to-text application. For specific use cases in serious and scalable production deployments, consider using an API-based service specifically made for that purpose, such as: - Google Cloud Vision API - Microsoft Azure Computer Vision - Azure AI Document Intelligence - Amazon Textract

Convert Google Docs text to audio and email it. Extract text from Google Docs, transform it with ElevenLabs, upload via FTP, and send through email.

This workflow enriches new Pipedrive organization's data by adding a note to the organization object in Pipedrive. It assumes there is a custom "website" field in your Pipedrive setup, as data will be scraped from this website to generate a note using OpenAI. Then, a notification is sent in Slack. ⚠️ Disclaimer This workflow uses a scraping API. Before using it, ensure you comply with the regulations regarding web scraping in your country or state. Important Notes The OpenAI model used is GPT-4o, chosen for its large input token capacity. However, it is not the cheapest model if cost is very important to you. The system prompt in the OpenAI Node generates output with relevant information, but feel free to improve or modify it according to your needs. How It WorksNode 1: Pipedrive Trigger - An Organization is Created This is the trigger of the workflow. When an organization object is created in Pipedrive, this node is triggered and retrieves the data. Make sure you have a "website" custom field in Pipedrive (the name of the field in the n8n node will appear as a random ID and not with the Pipedrive custom field name). Node 2: ScrapingBee - Get Organization's Website's Homepage Content This node scrapes the content from the URL of the website associated with the Pipedrive Organization created in Node 1. The workflow uses the ScrapingBee API, but you can use any preferred API or simply the HTTP request node in n8n. Node 3: OpenAI - Message GPT-4o with Scraped Data This node sends HTML-scraped data from the previous node to the OpenAI GPT-4o model. The system prompt instructs the model to extract company data, such as products or services offered and competitors (if known by the model), and format it as HTML for optimal use in a Pipedrive Note. Node 4: Pipedrive - Create a Note with OpenAI Output This node adds a Note to the Organization created in Pipedrive using the OpenAI node output. The Note will include the company description, target market, selling products, and competitors (if GPT-4o was able to determine them). Node 5 & 6: HTML To Markdown & Code - Markdown to Slack Markdown These two nodes format the HTML output to Slack Markdown. The Note created in Pipedrive is in HTML format, as specified by the System Prompt of the OpenAI Node. To send it to Slack, it needs to be converted to Markdown and then to Slack Markdown. Node 7: Slack - Notify This node sends a message in Slack containing the Pipedrive Organization Note created with this workflow.

Who is this for? Everyone! Did you dream of asking an AI, "What hotel did I stay in for holidays last summer?" or "What were my marks last semester like?" Dream no more, as vector similarity searches and this workflow are the foundations to make it possible (as long as the information appears in your e-mails 😅). 100% Local and Open Source! This workflow is designed to use locally-hosted open source. Ollama as LLM provider, nomic-embed-text as the embeddings model, and pgvector as the vector database engine, on top of Postgres. Structured AND Vectorized This workflow combines structured and semantic search on your e-mail. No need for enterprise setups! Leverage the convenience of n8n and open source to get a bleeding edge solution. Setup You will need a PGVector database with embeddings for all your email. Use my other template Gmail to Vector Embeddings with PGVector and Ollama to set it up in a breeze! Make a copy of my Email Assistant: Convert Natural Language to SQL Queries with Phi4-mini and PostgreSQL; you will need it for structured searches. Install this template and modify the Call the SQL composer Workflow step to point at your copy of the SQL workflow. Adjust the rest of the necessary steps: Telegram Trigger, AI Chat model, AI Embeddings... Activate the workflow and chat around!

Monitor Google Drive for new files,Analyze images with ChatGPT,Log results in Google Sheets for streamlined data management.

Get concise summaries of your Gong calls and send them to your sales team on Slack to boost customer sales insights and intelligence. The scenario is set to execute every morning at 8:00 am and will summarize calls that occurred in the past 24 hours.

What it is: An automation to plan → draft → finalize and publish your textual blog post ideas to your WordPress blog. Works in stages and hands 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 are also configured in that spreadsheet (including which model to use). Saves 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 the 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, etc. - Blog topics and their status and next action. Depending on each blog topic's "Status" and "Action," it then either uses an LLM for the next action ("plan" → "draft" → "final" actions) or publishes the written content to your WordPress instance ("publish" actions). Set up steps: 1. Import the workflow. 2. Make your own copy of the Google Spreadsheet. 3. Update the credentials using your individual credentials for: - Google Spreadsheets - OpenRouter 4. Edit the "Settings" node and enter your individual values for: - Your spreadsheet copy URL - Your WordPress blog URL - Your WordPress blog username - Your WordPress blog app password (a 4x4 alphanumeric sequence), that you probably have to create first, for which your WordPress user has to have 2-factor authentication enabled. 5. In your own copy of the spreadsheet: - Individualize the "Config" sheet's "Value" column for the prompts/context/etc. - Populate the "Schedule" sheet with at least one line in which you specify: - A "Topic" - A "Scheduled" date (YYYY-MM-DD HH:mm:ss) - A "Status" of "idea" - An "Action" of "plan" (to kick off that action).

Built this for a dedicated Slack outage-notifications channel — works well on both desktop and mobile. This is for: - IT Administrators & small MSPs looking to streamline M365 alerts from one or multiple mailboxes into a single or specific Slack channels - IT Admins who prefer ChatOps over management-by-email What does it do - Scans for M365 outage alerts emails (every 1 min) - Checks if it impacts a specific user region (if the alert calls it out, countries have to be manually set) - Summarizes the incident using OpenAI o4-mini (cheap model - or you can swap for local Ollama) - Sends a Slack Block to your outage channel with incident link (can be extended) - Deletes the original alert email after successful delivery CredentialsOutlook: Create an Outlook credential (OAuth2.0) to point to the mailbox (regular or shared) where M365 service alerts will be received. Slack: Create a Slack bot credential with access to the Slack channel you want updates posted to. OpenAI: Create an OpenAI credential that has access to the GPT-4O-MINI model. Recommend you use projects in OpenAI so that you may set a per-project budget and not impact other projects. Review this OpenAI documentation for more info on managing Projects in the API portal. Expect this to consume no more than 1-2 cents per month on average. Setup - Download & import the workflow - Modify the first Outlook block (Check for 365 Service Alert) to use the Outlook credential - Modify the OpenAI block's system prompt to call out the countries your users reside in - ie. "- Assume the organization has users primarily in the U.S. and Australia. If those regions are affected, state: 'Your users may have been affected.' Otherwise, add: 'No impact expected for your user base.' " ← swap U.S. & Australia for desired countries - Modify the Slack block (Post outage to Slack) to specify the channel updates will be posted to Sample Slack Output

Combine Tech News in a Personalized Weekly Newsletter. This n8n template automates the collection, storage, and summarization of technology news from top sites, turning it into a concise, personalized weekly newsletter. If you like staying informed but want to reduce daily distractions, this workflow is perfect for you. It leverages RSS feeds, vector databases, and LLMs to read and curate tech content on your behalf—so you only receive what truly matters. How it works A daily scheduled trigger fetches articles from multiple popular tech RSS feeds like Wired, TechCrunch, and The Verge. Fetched articles are: - Normalized to extract titles, summaries, and publish dates. - Converted to vector embeddings via OpenAI and stored in memory for fast semantic querying. A weekly scheduled trigger activates the AI summarization flow: The AI is provided with your interests (e.g., AI, games, gadgets) and the desired number of items (e.g., 15). It queries the vector store to retrieve relevant articles and summarizes the most newsworthy stories. The summary is converted into a clean, email-friendly format and sent to your inbox. How to use - Connect your OpenAI and Gmail accounts to n8n. - Customize the list of RSS feeds in the “Set Tech News RSS Feeds” node. - Update your interests and number of desired news items in the “Your Topics of Interest” node. - Activate the workflow and let the automation run on schedule. Customizing this workflow Want to use different sources? Swap in your own RSS feeds, or use an API-based news aggregator. Replace the in-memory vector store with Pinecone, Weaviate, or another persistent vector DB for longer-term storage. Adjust the agent's summarization style to suit internal updates, industry-specific briefings, or even entertainment recaps. Prefer chat over email? Replace the email node with a Telegram bot to receive your personalized tech newsletter directly in a Telegram chat.

This n8n template demonstrates how to convert HTML into a PDF, compress the generated PDF, and return it as a binary response using the PDF Toolkit from www.customjs.space. Notice: Community nodes can only be installed on self-hosted instances of n8n. What this workflow does: - Convert the requested HTML to PDF. - Compress the PDF file. - Use a Code node to handle URLs pointing to PDF files if they exceed 6MB. - Compress the PDF pages. Requirements: - Self-hosted n8n instance - CustomJS API key for compressing PDF files - HTML Data to convert PDF files - Code node for handling URL that indicates PDF file Workflow Steps: - Manual Trigger: Runs with user interaction. - HTML to PDF: Request HTML Data and convert HTML to PDF. Request PDF from URL. - Compress Pages from PDF: Compress PDF as a binary file. Usage: 1. Get API key from customJS: - Sign up to customJS platform. - Navigate to your profile page. - Press "Show" button to get API key. 2. Set Credentials for CustomJS API on n8n: - Copy and paste your API key generated from CustomJS here. 3. Design workflow: - A Manual Trigger for starting workflow. - HTTP Request Nodes for downloading PDF files. - Code node for handling URL that indicates PDF file. - Compress PDF files. You can replace logic for triggering and returning results. For example, you can trigger this workflow by calling a webhook and get a result as a response from the webhook. Simply replace Manual Trigger and Write to Disk nodes.

Who this is for? The Brand Content Extract, Summarization & Sentiment Analysis workflow is designed for professionals and teams who need to monitor, understand, and act on public brand perception at scale. It is ideal for: - Brand Managers - Looking to track how their brand is portrayed online. - Marketing Analysts - Seeking insights from competitor and industry content. - PR & Communications Teams - Evaluating media tone and potential reputation risks. - Data Scientists & AI Developers - Automating content intelligence pipelines. - Growth Hackers - Performing large-scale web listening for campaign optimization. What problem is this workflow solving? Manually tracking and interpreting how your brand is mentioned across blogs, news sites, or product reviews is labor-intensive and unscalable. Traditional scraping tools return raw data but lack insights like summarization, sentiment analysis, etc. This workflow addresses: - Scalable extraction of brand-related content using Bright Data's infrastructure. - Textual data extract for easy decision-making or alerting. - Automated summarization of verbose or multi-paragraph articles using Gemini. - Sentiment analysis of how a brand is being portrayed. What this workflow does Receives input: A brand URL for the data extraction and analysis. Uses Bright Data's Web Unlocker to extract content from relevant sites. Cleans and preprocesses the scraped content for readability. Sends the content to Google Gemini for: - Enriched results including: - Cleaned content - Summary - Sentiment Analysis Sends the response to a target system via Webhook notification. Persists the response to disk. Setup 1. Sign up at Bright Data. 2. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. 3. In n8n, configure the Header Auth account under Credentials (Generic Auth Type: Header Authentication). The Value field should be set with the Bearer XXXXXXXXXXXXXX. The XXXXXXXXXXXXXX should be replaced by the Web Unlocker Token. 4. A Google Gemini API key (or access through Vertex AI or proxy). 5. Update the Set URL and Bright Data Zone for setting the brand content URL and the Bright Data Zone name. 6. Update the Webhook HTTP Request node with the Webhook endpoint of your choice. How to customize this workflow to your needs - Update Source: Update the workflow input to read from Google Sheet or Airbase for dynamically tracking multiple brands or topics. - AI Prompt Customization: Tailor Gemini prompts for: - Summary length (brief vs. detailed) - Detailed Sentiment with the custom structured data format. - Brand-specific tone detection (e.g., trust, excitement, dissatisfaction) - Output Destinations: Configure the output node to send the responses to various platforms, such as Slack, CRM systems, or databases.

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, 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, 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 for further review or reporting purposes. Set Up Steps To replicate this workflow within your own n8n environment, follow these steps: Configuration: Begin by setting up an n8n instance if you haven't already; you can sign up directly on their website or self-host the application. Import the provided JSON configuration into your n8n workspace. Ensure that all necessary credentials (e.g., Google Drive, Google Sheets, OpenAI API keys) are correctly configured under the Credentials section since some nodes require external service integrations like Google APIs and OpenAI for language processing tasks. Customization: Adjust the parameters of each node according to your specific requirements. For example, modify the fields in the formTrigger node to match what kind of information you wish to collect from applicants. Customize the prompts given to AI models in nodes like Qualifications, Summarization Chain, and HR Expert so they align with the type of analyses you want performed on the candidates' profiles. Update the destination settings in the Google Sheets node to point towards your own spreadsheet where you would like the final outputs recorded. Need help customizing? Contact me for consulting and support or add me on LinkedIn.

Effortlessly summarize RSS feed content using Hugging Face, create engaging voice-overs with ElevenLabs, and conveniently email audio files for streamlined content consumption.

Automatically clean up your Gmail inbox by deleting unwanted emails, validated by Gemini AI. Ideal for anyone tired of manual inbox cleanup, this workflow helps you save time while staying in control, with full transparency via Telegram alerts. How it works: - Scans Gmail inbox in adjustable 2-week batches - Uses Gemini AI to decide if an email should be deleted or skipped - Applies a label to skipped emails to avoid rechecking in future runs - Deletes unwanted emails and sends a Telegram message with the AI's reasoning - Also notifies on skipped emails, with explanation included Set up steps: - Connect your Gmail, Gemini AI, and Telegram accounts - Adjust the AI baseline to control sensitivity (e.g. how strict the filtering should be) - Set your batch range (default: last 2 weeks, adjustable) - Define your Telegram chat/channel for notifications Note: Thanks to n8n's modular design, you can easily switch Gemini for another AI model (like OpenAI, Claude, etc.) or replace Telegram with Discord, Slack, or even email, no code changes needed, just swap the nodes.