Integrate HTML with 500+ apps and services

📈 Daily Financial News - Description This workflow automates the process of collecting, organizing, and delivering a daily summary of financial news by following these key steps: Scheduled Activation The workflow starts at 7:00 AM each day, triggered by the Schedule Trigger node. News Retrieval The HTTP Request node fetches the latest financial news from FT.com. Content Extraction The Extract Specific Content node scrapes targeted sections of the HTML (headlines, editor's picks, top stories, etc.) using CSS selectors to locate and capture relevant content. News Aggregation The Set Node gathers and organizes the extracted news data, preparing it for summarization. Categories like "Headline #1," "Editor's Picks," and "Europe News" are all structured into a single data block. Summarization An AI Agent (Google Gemini) takes the aggregated news data and creates a concise, HTML-formatted summary tailored to give investors an insightful market snapshot. Email Delivery Finally, the Microsoft Outlook node sends the summary via email to the designated recipient with the subject "Financial news from today." This process ensures that financial news is efficiently curated, summarized, and delivered without manual intervention.

How it works Fetch transaction notification emails (including attachments) Clean up data Let AI (Basic LLM Chain node) generate bookkeeping item Send to Google sheet Details The example fetch email from Gmail lables, suggested using filters to automatically orgianize email into the labels Data will send to "raw data" sheet Example google sheet: https://docs.google.com/spreadsheets/d/1_IhdHj8bxtsfH2MRqKuU2LzJuzm4DaeKSw46eFcyYts/edit?gid=1617968863#gid=1617968863

This workflow with AI agent is designed to navigate through the page to retrieve specific type of information (in this example: social media profile links). The agent is equipped with 2 tools: text tool:** to retrieve all the text from the page, URLs tool:** to extract all possible links from the page. 💡 You can edit prompt and JSON schema connected to the agent in order to return other data then social media profile links. 👉 This workflow uses Supabase as storage (input/output). Feel free to change it to any other database of your choice. 🎬 See this workflow in action in my YouTube video. How it works? The workflow uses the input URL (website) as a starting point to retrieve the data (e.g. example.com). Using the "URLs tool", the agent is able to retrieve all links from the page and navigate to them. For example, if you want to retrieve contact information, agent will try to find a subpage that might contain this information (e.g. example.com/contact) and extract the information using the text tool. Set up steps Connect database with input data (website addresses) or pin sample data to trigger node. Configure the crawling agent to retrieve the desired data (e.g. modify prompt and/or parsing schema). Set credentials for OpenAI. Optionally: split agent tools to separate workflows. If you like this workflow, please subscribe to my YouTube channel and/or my newsletter.

How it works It’s very important to come prepared to Sales calls. This often means a lot of manual research about the person you’re calling with. This workflow delivers a summary of the latest social media activity (LinkedIn + X) for businesses you are about to interact with each day. Scans Your Calendar**: Each morning, it reviews your Google Calendar for any scheduled meetings or calls with companies based on each attendee email address. Fetches Latest Posts**: For each identified company, it fetches recent LinkedIn and X posts and summerizes them using AI to deliver a qucik overview for a busy sales rep. Delivers Insights**: You receive personalized emails via Gmail, each dedicated to a company you’re meeting with that day, containing a reminder of the meeting and a summary of company's recent social media activity. Setup steps The workflow requires you to have the following accounts set up in their respective nodes: Google Calendar GMail Clearbit OpenAI Besides those, you will need an account on the RapidAPI platform and subscribe to the following APIs: Fresh LinkedIn Profile Data Twitter Email example

What this workflow does Downloads the daily top podcasts of a selected genre Summarizes the content of each podcast in a few paragraphs Sends the summaries and the direct link to each podcast in a formatted email Setup Create a free API key on Taddy here: https://taddy.org/signup/developers Input your user number and API key into the TaddyTopDaily node in the header parameters X-USER-ID and X-API-KEY respectively. Create access credentials for your Gmail as described here: https://developers.google.com/workspace/guides/create-credentials. Use the credentials from your client_secret.json in the Gmail node. In the Genre node, set the genre of podcasts you want a summary for. Valid values are: TECHNOLOGY, NEWS, ARTS, COMEDY, SPORTS, FICTION, etc. Look at api.taddy.org for the full list (they will be displayed in the help docs as PODCASTSERIES_TECHNOLOGY, PODCASTSERIES_NEWS, etc.) Enter your email address in the Gmail node. Change the schedule time for sending email from Schedule to whichever time you want to receive the email. Test: Hit Test Workflow. Check your email for the results. That's it! It should take less than 5 minutes total.

This n8n workflow demonstrates creating a recipe recommendation chatbot using the Qdrant vector store recommendation API. Use this example to build recommendation features in your AI Agents for your users. How it works For our recipes, we'll use HelloFresh's weekly course and recipes for data. We'll scrape the website for this data. Each recipe is split, vectorised and inserted into a Qdrant Collection using Mistral Embeddings Additionally the whole recipe is stored in a SQLite database for later retrieval. Our AI Agent is setup to recommend recipes from our Qdrant vector store. However, instead of the default similarity search, we'll use the Recommendation API instead. Qdrant's Recommendation API allows you to provide a negative prompt; in our case, the user can specify recipes or ingredients to avoid. The AI Agent is now able to suggest a recipe recommendation better suited for the user and increase customer satisfaction. Requirements Qdrant vector store instance to save the recipes Mistral.ai account for embeddings and LLM agent Customising the workflow This workflow can work for a variety of different audiences. Try different sets of data such as clothes, sports shoes, vehicles or even holidays.

This workflow is a experiment to build HTML pages from a user input using the new Structured Output from OpenAI. How it works: Users add what they want to build as a query parameter The OpenAI node generate an interface following a structured output defined in the body The JSON output is then converted to HTML along with a title The HTML is encapsulated in an HTML node (where the Tailwind css script is added) The HTML is rendered to the user via the Webhook response. Set up steps Create an OpenAI API Key Create the OpenAI credentials Use the credentials for both nodes HTTP Request (as Predefined Credential type) and OpenAI Activate your workflow Once active, go to the production URL and add what you'd like to build as the parameter "query" Example: https://production_url.com?query=a%20signup%20form Example of generated page

This n8n workflow, which runs every Monday at 5:00 AM, initiates a comprehensive process to monitor and analyze network security by scrutinizing IP addresses and their associated ports. It begins by fetching a list of watched IP addresses and expected ports through an HTTP request. Each IP address is then processed in a sequential loop. For every IP, the workflow sends a GET request to Shodan, a renowned search engine for internet-connected devices, to gather detailed information about the IP. It then extracts the data field from Shodan's response, converting it into an array. This array contains information on all ports Shodan has data for regarding the IP. A filter node compares the ports returned from Shodan with the expected list obtained initially. If a port doesn't match the expected list, it is retained for further processing; otherwise, it's filtered out. For each such unexpected port, the workflow assembles data including the IP, hostnames from Shodan, the unexpected port number, service description, and detailed data from Shodan like HTTP status code, date, time, and headers. This collected data is then formatted into an HTML table, which is subsequently converted into Markdown format. Finally, the workflow generates an alert in TheHive, a popular security incident response platform. This alert contains details like the title indicating unexpected ports for the specific IP, a description comprising the Markdown table with Shodan data, medium severity, current date and time, tags, Traffic Light Protocol (TLP) set to Amber, a new status, type as 'Unexpected open port', the source as n8n, a unique source reference combining the IP with the current Unix time, and enabling follow and JSON parameters options. This comprehensive workflow thus aids in the proactive monitoring and management of network security.

This workflow demonstrates how to export SQL to XML and present the data nicely formatted using an XSL Template. The upper part of the workflow starts with a webhook. Then it gets several random records from the SQL table and converts them into an XML string. Then a final XML file is created that contains a link to the XML Stylesheet file. The lower part of the workflow contains a helper Webhook that reads an XSL Template from the GitHub gist and serves it back via the Respond to Webhook node. This is required to comply with the CORS rules of modern browsers. These rules dictate that both XML data and a stylesheet file should come from the same domain.

Extract Title tag and meta description from url for SEO analysis. How it works The workflows takes records from Airtable, get the url in the records and extract from the related webpage the title tag (<title>) and meta description (<meta name="description" content="Some content">). If title tag and/or meta description tag isn't available on the webpage, the result will be empty. Setup Set a Base in Airtable with a table with the following structure: url (field type url), title tag (field type text string), meta desc (field type text field) Minimum suggested table structure is: url (https://example.com), title (Title example), meta desc* (This is the meta description of the example page) Connect Airtable to both Airtable nodes in the template and, with the following formula, get all the records that miss title tag and meta desc. Formula: AND(url != "", {title tag} = "", {meta desc} = "") Insert the url to be analyzed in the table in the field url and let the workflow do the rest. Extra You can also calculate the length for title tag and meta desc using formula field inside Airtable. This is the formula: LEN({title tag}) or LEN({meta desc}) You can automate the process calling a Webhook from Airtable. For this, you need an Airtable paid plan.

The News Site from Colt, a telecom company, does not offer an RSS feed, therefore web scraping is the choice to extract and process the news. The goal is to get only the newest posts, a summary of each post and their respective (technical) keywords. Note that the news site offers the links to each news post, but not the individual news. We collect first the links and dates of each post before extracting the newest ones. The result is sent to a SQL database, in this case a NocoDB database. This process happens each week thru a cron job. Requirements: Basic understanding of CSS selectors and how to get them via browser (usually: right click → inspect) ChatGPT API account - normal account is not sufficient A NocoDB database - of course you may choose any type of output target Assumptions: CSS selectors work on the news site The post has a date with own CSS selector - meaning date is not part of the news content "Warnings" Not every site likes to be scraped, especially not in high frequency Each website is structured in different ways, the workflow may then need several adaptations.

Usage This workflow gets all the posts from your WordPress site and sorts them into a clear format before publishing them to medium. Step 1. Set up the HTTP node and set the URL of the source destination. This will be the URL of the blog you want to use. We shall be using https://mailsafi.com/blog for this. Step 2. Extract the URLs of all the blogs on the page This gets all the blog titles and their URLs. Its an easy way to sort ou which blogs to share and which not to share. Step 3. Split the entries for easy sorting or a cleaner view. Step 4. Set a new https node with all the blog URLs that we got from the previous steps. Step 5. Extract the contents of the blog Step 6. Add the medium node and then set the contents that you want to be shared out. Execute your workflow and you are good to go

Overview This N8N workflow facilitates advanced URL parsing and shortening, incorporating metadata extraction, OpenGraph tag handling, and integration with Switchy API for link management. It employs various nodes for URL processing, metadata extraction, and creation or updating of shortened links with enriched metadata. Features URL Metadata Extraction:** Parses URLs to extract metadata such as titles, descriptions, images, and favicons. OpenGraph API Integration:** Utilizes OpenGraph API for detailed metadata retrieval. Switchy API Integration:** Manages shortened links via the Switchy API. GitHub API Integration:** Uses GitHub for hosting images related to the URLs. Screenshot Capabilities:** Captures screenshots of web pages as part of metadata. API Authorization and Configuration:** Manages API keys and configurations for external service integration. Workflow Structure Split In Batches: Processes URLs in batches. API Auth: Configures API authorization. URL Processing Nodes: Extract metadata using various nodes like Get Headers, OpenGraph API, and Meta tags Scraper. Conditional Nodes: Include IF OpenGraph Invalid and If - Enable ScreenShots for logic handling. Data Aggregation: Uses nodes like Method 1 - META for final metadata aggregation. Switchy API: Handles link creation and updating. GitHub Integration: Hosts screenshots and images on a personal GitHub repository. Final Output: Provides the shortened URL after processing. API Stack | API | Description | |---------------------------------|-------------------------------------------------| | switchy | For creating and updating shortened links. | | opengraph | To retrieve URL metadata using OpenGraph tags. | | dub.sh | Used for scraping meta tags from web pages. | | microlink | Captures screenshots of web pages. | | pxl.to | Alternative service for capturing screenshots. | | favicone | Retrieves favicons for given URLs. | | github | Hosts images and screenshots on GitHub repo. | | statically | Used for CDN services and image hosting. | | Other APIs | Additional APIs used for various purposes. | GitHub Repository Setup To use this workflow, ensure your GitHub API is linked for hosting images. Set up a repository where the workflow can upload screenshots and other related images. This repository will be referenced in the workflow nodes where images are handled. Configuration Before running the workflow, set up the necessary API keys and configurations in the API Auth node. Adjust batch size and other parameters as needed. Error Handling The workflow includes nodes like Stop and Error for robust error handling, post an issue and mention the creator using N8N community. Contributions This workflow is open for community contributions. Enhancements and improvements are welcome.

This workflow monitor G2 reviews URLS. When a new review is published, it will: trigger a Slack notification record the review in Google Sheets To install it, you'll need: access to Slack, Google Sheets and ScrapingBee Full guide here: https://lempire.notion.site/Scrape-G2-reviews-with-n8n-3f46e280e8f24a68b3797f98d2fba433?pvs=4

What this template does This workflow will collect order data as it is produced, then send a summary email of all orders at the end of every day, formatted in a table. It receives new orders via webhook and stores in Airtable. At 7PM every day, it sends a summary email with the day's orders in a HTML table Setup: Instructions Video Create a new table in Airtable and give it a field time with type date, orderID with type number, and orderPrice also with type number. Create a new access token if you haven't already at https://airtable.com/create/tokens/new. Make sure to give the token the scopes data.records:read, data.records:write, schema.bases:read and access to whichever table you choose to store the orders. A pop-up window appears with the token. Use this token to make Create New Credential > Access Token for Airtable in the Store Order and Airtable Get Today's Orders nodes. Create access credentials for your Gmail as described here: https://developers.google.com/workspace/guides/create-credentials. Use the credentials from your client_secret.json in the Send to Gmail node. In the Store Order node, change Base and Table to the database and table in your Airtable account you wish to use to store orders. Make sure to use these same values in the Airtable Get Today's Orders node. Every time an order is created in your system, send a POST request to Webhook from your order software. Each request must contain a single order containing fields 'orderID' and 'orderPrice' (or, edit Set Order Fields to select which incoming fields you wish to save) Change the schedule time for sending email from Everyday at 7PM to whichever time you choose. Test: Activate the workflow. From the node Webhook, copy Production URL Send the following CURL request to the URL given to you: curl -X POST -H "Content-Type: application/json" -d '{"orderID": 12345, "orderPrice": 99.99}' YOUR_URL_HERE It should say Node executed successfully. Now check your Airtable and confirm the order was stored in the right place.

This n8n template scrapes a list of AI grants from grants.gov and qualifies them using AI; determining interest and eligibility for the business. It then sends an email alert of interesting items to team members in an email. The template also shows how you can use the "Remove Duplicates" node to simplify deduplication of external listings without the need to manage this yourself. Not particularly interested in AI Grants? This template works for other tender websites as long as you're able to scrape them. How it works A scheduled trigger is set to fetch a list of AI grants listed on the grants.gov website in the past day. A Remove Duplicates node is used to track Grant IDs to filter out those already processed by the workflow. New grants are summarized and analysed by AI nodes to determine eligibility and interest which is then saved to an Airtable database. Another scheduled trigger starts a little later than the first to collect and summarize the new grants The results are then compiled into an email template using the HTML node, in the form of a newsletter designed to alert and brief team members of new AI grants. This email is then sent to a list of subscribers using the gmail node. How to use Make a copy of sample Airtable here: https://airtable.com/appiNoPRvhJxz9crl/shrRdP6zstgsxjDKL The filters for fetching the grants is currently set to the "AI" category. Feel free to change this to include more categories. Not interested in grants, this template can works for other sources of leads just change the endpoint and how you're defining the item ID to track. Requirements Airtable for database OpenAI for LLM Note: These are not hard requirements and can be exchanged for services available to you. customising the workflow "Eligibility" criteria at this stage may be better served by identifying hard blockers instead ie. certifications, geographical considerations or certain legal checks. Be sure to mention any hard blockers into the Eligibility prompt. Not particularly interested in AI prompts? This template works for other tender websites as long as you're able to scrape them.

This n8n template demonstrates a simple approach to using AI to automate the generation of blog content which aligns to your organisation's brand voice and style by using examples of previously published articles. In a way, it's quick and dirty "training" which can get your automated content generation strategy up and running for very little effort and cost whilst you evaluate our AI content pipeline. How it works In this demonstration, the n8n.io blog is used as the source of existing published content and 5 of the latest articles are imported via the HTTP node. The HTML node is extract the article bodies which are then converted to markdown for our LLMs. We use LLM nodes to (1) understand the article structure and writing style and (2) identify the brand voice characteristics used in the posts. These are then used as guidelines in our final LLM node when generating new articles. Finally, a draft is saved to Wordpress for human editors to review or use as starting point for their own articles. How to use Update Step 1 to fetch data from your desired blog or change to fetch existing content in a different way. Update Step 5 to provide your new article instruction. For optimal output, theme topics relevant to your brand. Requirements A source of text-heavy content is required to accurately breakdown the brand voice and article style. Don't have your own? Maybe try your competitors? OpenAI for LLM - though I recommend exploring other models which may give subjectively better results. Wordpress for blog but feel free to use other preferred publishing platforms. Customising this workflow Ideally, you'd want to "train" your agent on material which is similar to your output ie. your social media post may not get the best results from your blog content due to differing formats. Typically, this brand voice extraction exercise should run once and then be cached somewhere for reuse later. This would save on generation time and overall cost of the workflow.

This workflow uses AI to analyze customer sentiment from product feedback. If the sentiment is negative, AI will determine whether offering a coupon could improve the customer experience. Upon completing the sentiment analysis, the workflow creates a personalized email templates. This solution streamlines the process of engaging with customers post-purchase, particularly when addressing dissatisfaction, and ensures that outreach is both personalized and automated. This workflow won the 1st place in our last AI contest. Note that to use this template, you need to be on n8n version 1.19.4 or later.

This n8n template builds a meeting assistant that compiles timely reminders of upcoming meetings filled with email history and recent LinkedIn activity of other people on the invite. This is then discreetly sent via WhatsApp ensuring the user is always prepared, informed and ready to impress! How it works A scheduled trigger fires hourly to check for upcoming personal meetings. When found, the invite is analysed by an AI agent to pull email and LinkedIn details of the other invitees. 2 subworkflows are then triggered for each invitee to (1) search for last email correspondence with them and (2) scrape their LinkedIn profile + recent activity for social updates. Using both available sources, another AI agent is used to summarise this information and generate a short meeting prep message for the user. The notification is finally sent to the user's WhatsApp, allowing them ample time to review. How to use There are a lot of moving parts in this template so in it's current form, it's best to use this for personal rather than team calendars. The LinkedIn scraping method used in this workflow requires you to paste in your LinkedIn cookies from your browser which essentially let's n8n impersonate you. You can retrieve this from dev console or ask someone technical for help! Note: It may be wise to switch to other LinkedIn scraping approaches which do not impersonate your own account for production. Requirements OpenAI for LLM Gmail for Email Google Calendar for upcoming events WhatsApp Business account for notifications Customising this workflow Try adding information sources which are relevant to you and your invitees. Such as company search, other social media sites etc. Create an on-demand version which doesn't rely on the scheduled trigger. Sometimes you want to know prepare for meetings hours or days in advance where this could help immensely.

If you previously upgraded to n8n version 0.214.3, some of your workflows might have been accidentally rewired in the wrong way. This issue affected nodes with more than one output, such as If, Switch, and Compare Datasets. This workflow helps you identify potentially affected workflows and nodes that you should check. ❗️Please ensure that you run this workflow as the instance owner.❗️

Instructions This automation enables you to just upload any Image (via Form) of a Logo Sheet, containing multiple Images of Product Logos (most likely) which brings them in some context to one another. After submitting an AI-Agent eats that Logo Sheet, turning it into an List of "Productname" and "Attributes", also checks if Tools are kind of similar to another, given the Context of the Image. We utilize AI Vision capabilities for that. NOTE: It might not be able to extract all informations. For a "upload and forget it" Workflow it works for me. You can even run it multiple times, to be sure. But if you need to make sure it extracts everything you might need to think about an Multi-Agent Setup with Validation-Agent Steps. Once the Agent finishes the extraction, it will traditionally and deterministicly add those Attributes to Airtable (Creates those, if not already existing.) and also Upserts the Tool Informations. It uses MD5 Hashes for turning Product Names into.. something fancy really, you could also use it without that, but I wanted to have something that looks atleast like an ID. Setup Set Up the Airtable like shown below. Update and set Credentials for all Airtable Nodes. Check or Adjust the Prompt of the Agent matching your use-case. Activate the Workflow. Open the Form (default: https://your-n8n.io/form/logo-sheet-feeder) Enjoy growing your Airtable. Enjoy the workflow! ❤️ let the work flow — Workflow Automation & Development

Intro This workflow needs a user to authenticate by using an openid connect provider in order to call the webhook. If the user is not authenticated, it starts a login process by using an Authorization Code with PKCE https://datatracker.ietf.org/doc/html/rfc7636, a standard way to authenticate users with openid connect. Then, after the user logs in, the webhook is refreshed and gets the user's token from a cookie. With this token, all details about the user are requested through the userinfo endpoint on the identity provider. How to set up with Keycloak Keycloak Keycloak is an open source identity and access management solution. Feel free to get a demo realm at https://please-open.it or get your own Keycloak server up and running. After creating a realm, go to "Realm Settings" and click on "OpenID Endpoint Configuration" Retrieve authorization_endpoint, token_endpoint and userinfo_endpoint values. Set those variables in the "Set variables" node. In Keycloak, create a new client (name it as you want) Disable the client authentication, check only "standard flow" : At the third step, put the webhook url in "valid redirect URIs", fill "Web origins" with a "+". You're done, open the webhook and it asks you to authenticate. Usage User informations The userinfo node returns this structure about the user has logged in : [ { "sub":"73a6543f-f420-4fa6-9811-209e903c348b", "email_verified":true, "preferred_username": "[email protected]", "email": "[email protected]" } ] I can use those infos in my workflow for custom operations. APIs calls the "code" node returns me a cookie named "n8n-custom-auth" which is the access_token returned by the identity provider. This access_token can be used to call APIs connected to this identity provider (for example, we call userinfo API with this token). Example : asks a user to log in with his Google account then call an API (Gmail, drive...) with his own token. How it works We published a blog post about this flow, how it works and how you can use it : https://blog.please-open.it/n8n-openid-client/

This workflow automates the process of gathering LinkedIn advice articles, extracting their content, and generating unique contributions for each article using an AI model. The contributions are then posted to a Slack channel and a NocoDB database for record-keeping. The workflow is triggered weekly to ensure new articles are continuously collected and responded to. Who is this for? This workflow is designed for professionals, marketers, and content creators looking to boost their LinkedIn presence by regularly engaging with LinkedIn advice articles. It’s especially useful for those who want to be seen as a "thought leader" or "top voice" in their niche by contributing relevant and unique advice to trending topics. What problem is this workflow solving? Manually searching for relevant LinkedIn articles, reading through them, and crafting thoughtful contributions can be time-consuming. This workflow solves that by automating the process of finding new articles, extracting key content, and generating AI-powered contributions. It helps users stay consistently active on LinkedIn, contributing value to trending discussions. What this workflow does Triggers Weekly: The workflow is set to run every Monday at 8:00 AM. Search Google for LinkedIn Advice Articles: Uses a predefined Google search URL to find the latest LinkedIn advice articles based on the user's area of expertise. Extract LinkedIn Article Links: A code node extracts all LinkedIn advice article links from the search results. Retrieve Article Content: For each article link, the workflow retrieves the HTML content and extracts the article title, topics, and existing contributions. Generate AI-Powered Contributions: The workflow sends the extracted article content to an AI model, which generates unique, helpful advice for each topic within the article. Post to Slack & NocoDB: The AI-generated contributions, along with the article links, are posted to a designated Slack channel and stored in a NocoDB database for future reference. Setup Google Search URL: Update the Google search URL with the relevant LinkedIn advice query for your field (e.g., "site:linkedin.com/advice 'marketing automation'"). Slack Integration: Connect your Slack account and specify the Slack channel where you want the contributions to be posted. NocoDB Integration: Set up your NocoDB project to store the generated contributions along with the article titles and links. How to customize this workflow Change Search Terms**: Modify the Google search URL to focus on a different LinkedIn topic or expertise area. Adjust Trigger Frequency**: The workflow is set to run weekly, but you can adjust the frequency by changing the schedule trigger. Enhance Contribution Quality**: Customize the AI model's prompt to generate contributions that align with your brand voice or content strategy. Workflow Summary This workflow helps users maintain a consistent presence on LinkedIn by automating the discovery of new advice articles and generating unique contributions using AI. It is ideal for professionals who want to engage with LinkedIn content regularly without spending too much time manually searching and drafting responses.

This n8n template is one of a 3-part series exploring use-cases for clustering vector embeddings: Survey Insights Customer Insights Community Insights This template demonstrates the Customer Insights scenario where Trustpilot reviews can be quickly grouped by similarity and an AI agent can generate insights on those groupings. With this workflow, marketers can save days and even weeks of work breaking down their own or competitor reviews and identify frequently mentioned positives and negatives. Sample Output: https://docs.google.com/spreadsheets/d/e/2PACX-1vQ6ipJnXWXgr5wlUJnhioNpeYrxaIpsRYZCwN3C-fFXumkbh9TAsA_JzE0kbv7DcGAVIP7az0L46_2P/pubhtml How it works Trustpilot reviews are scraped for a particular company using the HTTP request node. Reviews are then inserted into a Qdrant collection carefully tagged with the question and Trustpilot metadata. Reviews are fetched and put through a clustering algorithm using the Python Code node. The Qdrant points are returned in clustered groups. Each group is looped to fetch the payloads of the points and feed them to the AI agent to summarise and generate insights for. The resulting insights and raw responses are then saved to the Google Spreadsheet for further analysis by the marketer. Requirements Qdrant Vectorstore for storing embeddings. OpenAI account for embeddings and LLM. Customising the Template Adjust clustering parameters which make sense for your data. Consider expanding date range of reviews for insights over common intervals: 3mth, 6mth and YTD.

This n8n workflow is designed for security monitoring and incident response when suspicious login events are detected. It can be initiated either manually from within the n8n UI for testing or automatically triggered by a webhook when a new login event occurs. The workflow first extracts relevant data from the incoming webhook payload, including the IP address, user agent, timestamp, URL, and user ID. It then splits into three parallel processing paths. In the first path, it queries GreyNoise's Community API to retrieve information about the investigated IP address. Depending on the classification and trust level received from GreyNoise, the alert is given a High, Medium, or Low priority. This priority is assigned based on the best practices documentation from GreyNoise on how to apply their data to analysis. Once a priority is assigned, a message is sent to a Slack channel to notify users about the alert. The second path involves fetching geolocation data about the IP address using IP-API's Geolocation API and merging it with data from the UserParser node. This data is then combined with the data obtained from GreyNoise. In the third path, the UserParser node queries the Userparser IP address and user agent lookup API to obtain information about the user's IP and user agent. This data is merged with the IP-API data and GreyNoise data. The workflow then checks if the IP address is considered an unknown threat by examining both the noise and riot fields from GreyNoise. If it is considered an unknown threat, the workflow proceeds to retrieve the last 10 login records for the same user from a Postgres database. If there are any discrepancies in the login information, indicating a new location or device/browser, the user is informed via email. Potential issues when setting up this workflow include ensuring that credentials are correctly entered for GreyNoise and UserParser nodes, and addressing any discrepancies in the data sources that could lead to false positives or negatives in threat detection. Additionally, the usage of hardcoded API keys should be replaced with credentials for security and flexibility. Thorough testing and validation with sample data are crucial to ensure the workflow performs as expected and aligns with security incident response procedures.

This workflow sends a OpenAI GPT reply when an email is received from specific email recipients. It then saves the initial email and the GPT response to an automatically generated Google spreadsheet. Subsequent GPT responses will be added to the same spreadsheet. Additionally, when feedback is given for any of the GPT responses, it will be recorded to the spreasheet, which can then be used later to fine-tune the GPT model. Prerequisites OpenAI credentials Google credentials How it works This workflow is essentially a two-in-one workflow. It triggers off from two different nodes and have very different functionality from each trigger. The flow triggered from On email received node is as follows: Triggers off on the On email received node. Extract the email body from the email. Generate a response from the email body using the OpenAI node. Reply to the email sender using the Send reply to recipient node. A feedback link is also included in the email body which will trigger the On feedback given node. This is used to fine-tune the GPT model. Save the email body and OpenAI response to a Google Sheet. If a sheet does not exist, it will be created. The flow triggered from On feedback given node is as follows: Triggers off when a feedback link is clicked in the emailed GPT response. The feedback, either positive or negative, for that specific GPT response is then recorded to the Google Sheet.

Who this is for This template is for everyone that wants to download their n8n Cloud invoices automatically as a PDF instead of downloading them manually. How it works This workflow checks your Gmail inbox for new n8n invoice emails from n8n's payment provider Paddle. Once it finds something, it converts the URL into a PDF using pdflayer and saves it in Google Drive. Setup Setup your Gmail and Google Drive credentials Create a free account at https://pdflayer.com/ Insert your pdflayer API key into the Setup node Insert the URL to the wanted drive folder into the setup node (make sure to remove everything after the ?) How to adjust it to your need Instead of saving the PDF in Google drive, you could also save it in your local system, any other storage provider or send the PDF automatically to the right person in your company.

Who might benfit from this workflow? Everyone organizing him/herself by using a notion database for tasks but losing track on some important tasks having a deadline. The weekly reminder helps you to not forget about your notion tasks. How it works: The workflow fetches all your notion tasks from a desired database but the closed ones It generates a html template for each tasks containing a headline and a short list of key data (prio, status deadline, tags) It creates two groups based on the deadline date if a task is already overdue or not It generates a complete html email containing both groups and some sugar around them It sends the email to your desired email It uses Pushover to send you a push notification to your phone It is scheduled by the beginning of each week How to set it up: Fill out the "Set Workflow vars" node with your data Connect your notion account and select the database your tasks are stored at define the status filters to the ones you are using for your tasks Setup your email server to enable the email node to deliver your html email Create a Pushover account and setup the authentication for the Pushover node Adjust the last html node to change email style for your desire How to customize this workflow for your needs? You might adjust the filtering of the notion fetch node to filter for other statuses than provided in the example. You apply your custom design to the html email You could remove the filter which is filtering for tasks having a deadline and just send yourself a reminder for all tasks You need help implementing this or any other n8n workflow? Feel free to contact me via LinkedIn or my business website. You want to start using n8n? Use this link to register for n8n (This is an affiliate link)

This n8n template combines an AI agent with n8n's multi-page forms to create a novel interaction which allows automated question-and-answer sessions. One of the more obvious use-cases of this interaction is what I'm calling the AI interviewer. You can read the full post here: https://community.n8n.io/t/build-your-own-ai-interview-agents-with-n8n-forms/62312 Live demo here: https://jimleuk.app.n8n.cloud/form/driving-lessons-survey How it works A form trigger is used to start the interview and a new session is created in redis to capture the transcript. An AI agent is then tasked to ask questions to the user regarding the topic of the interview. This is setup as a loop so the questions never stop unless the user wishes to end the interview. Each answer is recorded in our session set up earlier between questions. When the user requests to end the interview we break the loop and show the interview completion screen. Finally, the session is then saved in a Google Sheet which can then be shared with team members and for the purpose of data analysis. How to use You'll need to be on a n8n instance that is accessible to your target audience. Not technical enough to setup your own server? Try out n8n cloud and instantly deploy template! Remember to activate the workflow so the form trigger is published and available for users to use. Requirements Groq LLM for AI agent. Feel free to swap this out for any other LLM. Redis(-compatible) storage for capturing sessions Customising this workflow The next step would be adding tools! AI interviews with knowledge retrieval could definitely open up other possibilities. Eg. An onboarding wizard generating questions by pulling facts from internal knowledgebase.

How it works: The workflow starts by sending a request to a website to retrieve its HTML content. It then parses the HTML extracting the relevant information The extracted data is storted and converted into a CSV file. The CSV file is attached to an email and sent to your specified address. The data is simultaneously saved to both Google Sheets and Microsoft Excel for further analysis or use. Set-up steps: Change the website to scrape in the "Fetch website content" node Configure Microsoft Azure credentials with Microsoft Graph permissions (required for the Save to Microsoft Excel 365 node) Configure Google Cloud credentials with access to Google Drive, Google Sheets and Gmail APIs (the latter is required for the Send CSV via e-mail node).