Workflow Templates

5 nodes92 views

Query Google Sheets/CSV data through an AI Agent using PostgreSQL

by Leonardo Grigorio

Want to see it in action? Watch the full breakdown here: 📺 Video Link Template Description This n8n workflow empowers you to query structured financial data from Google Sheets or CSV files using AI-generated SQL. Unlike traditional vector database solutions that falter with numerical queries, this template leverages PostgreSQL for efficient data storage and an AI agent to dynamically create optimized SQL queries from natural language inputs. What It Does Retrieves data from Google Sheets or CSV files Infers the data schema and builds a PostgreSQL table Populates the table with your data Uses an AI agent to translate natural language questions into SQL queries Returns precise numerical results quickly and efficiently Why Use This? No SQL knowledge required—the AI generates queries for you Bypasses the inefficiencies and costs of vector database approaches Scales effortlessly without overwhelming the language model Fully free and open-source Setup Requirements Pre-Conditions PostgreSQL Database**: A running PostgreSQL instance (no specific extensions required beyond standard installation). Google Sheets Access**: A publicly accessible or shared Google Sheet URL with structured data (e.g., financial records). Need a starting point? Use this Sample Google Sheet Template. n8n Instance**: A working n8n setup with access to the Google Drive and PostgreSQL nodes. Step-by-Step Instructions Add Your Google Sheets URL Open the "Google Drive Trigger" node. Replace the placeholder URL with your Google Sheet’s link. Verify the sheet name matches your data source. Configure PostgreSQL Update the "PostgreSQL" nodes with your database credentials (host, database, user, password). The workflow automatically creates and populates the table based on your data schema. Run the Workflow Execute the workflow manually to set up the database. Once initialized, use the AI agent by asking questions like: "How much did I sell last week?" "What were the total sales for Product X in February?" (Optional) Automate Updates Add a "Schedule Trigger" node to sync your Google Sheets data with PostgreSQL on a regular basis. How It Works Schema Detection**: The workflow analyzes your Google Sheets or CSV data to infer its structure and create an appropriate PostgreSQL table. AI-Powered Queries**: An optimized AI agent converts your natural language questions into precise SQL queries, ensuring accurate results. Efficient Retrieval**: By using PostgreSQL instead of vector-based methods, this template avoids common pitfalls like slow performance or inaccurate numerical outputs. Tips for Success Ensure your Google Sheet or CSV has consistent column headers for smooth schema detection. Test with simple questions first to verify the AI agent’s query generation. Check out the n8n Template Submission Guidelines for more best practices.

📊Data Processing

6 nodes8072 views

YouTube Comment Scraper & Analyzer with GPT-4o + Email Summary Report

by Amit Mehta

💬Communication & Collaboration

How it Works This workflow automates the collection and analysis of YouTube comments from a video and sends a summary report via email, using Google Sheets, the YouTube API, OpenAI (GPT-4o), and Gmail. Whether you're a content creator, brand manager, or social media analyst, this workflow helps you automate sentiment analysis and receive insights directly in your inbox — all triggered from a simple spreadsheet. 🎯 Use Case Ideal for: YouTubers** monitoring audience sentiment Marketing teams** analyzing campaign feedback Community managers** summarizing engagement Setup Instructions 1. Upload the Spreadsheet File name: Youtube_Video Sheet structure: | ID | Video Title | YouTube Video ID | Status | Add video IDs and set their Status as Pending 2. Configure Google Sheets Nodes Connect your Google account to: Pick Video IDs from Google Sheet Update Status on Google Sheet 3. Add API Credentials YouTube API Key** → for comment + video scraping nodes OpenAI API Key** → for analyzing comments Gmail Account** → for sending the summary email 4. Activate the Workflow Once live, the workflow will: Watch for new or updated rows in the spreadsheet Scrape comments using the YouTube API Analyze sentiment and key themes via GPT-4o Send a formatted HTML email with the summary Update the spreadsheet status to Mail sent 🔁 Workflow Logic Trigger: New/updated row in Google Sheet Retrieve: YouTube video metadata + comments Analyze: Comments using GPT-4o Email: Summary report via Gmail Update: Spreadsheet status to Mail sent 🧩 Node Descriptions | Node Name | Description | |-----------|-------------| | Pick Video IDs from Google Sheet | Watches the spreadsheet and retrieves pending video IDs | | If | Checks whether status is 'Pending' | | Limit | Restricts the number of processed rows | | Set Video Details | Prepares video info (e.g., title, channel) | | Get YouTube Video Details | Fetches metadata (title, channel, etc.) | | Get YouTube Video Comments | Pulls top-level comments using YouTube API | | Prepare Comments Data | Formats comment text for OpenAI | | AI Agent | Summarizes comments using OpenAI's GPT-4o | | Prepare HTML for Email | Converts summary into HTML for email body | | Gmail Account Configuration | Sends the email report via Gmail | | Update Status on Google Sheet | Marks the row as 'Mail sent' | 🛠️ Customization Tips Change the AI prompt for tone, length, or custom metrics Send results to Slack or Telegram instead of Gmail Export summaries to Notion, Airtable, or PDF Schedule it daily/weekly for recurring analysis 📒 Suggested Sticky Notes for Workflow | Node/Section | Sticky Note Content | |--------------|---------------------| | Pick Video IDs from Google Sheet | "Triggers on new YouTube videos in your spreadsheet" | | AI Agent | "Uses OpenAI to generate an analysis summary – customize prompt as needed" | | Gmail | "Sends summary report – you can update subject, recipients, or style" | | Update Status | "Marks video as processed to avoid duplicate runs" | 📎 Required Files | File Name | Purpose | |-----------|---------| | Youtube_Video | Google Sheet to hold YouTube video IDs and status | | Youtube_Comment_Scraper.json | Main n8n workflow export for this automation | 🧪 Testing Tips Add one test video with a valid YouTube video ID and status = Pending Monitor the workflow logs to confirm API responses Confirm summary delivery in your inbox Verify that status updates in the sheet 🏷 Suggested Tags & Categories #YouTube #OpenAI #Automation #Marketing #Email #Analytics

7 nodes856 views

Summarise MS Teams Channel Activity for Weekly Reports with AI

by Jimleuk

This n8n template lets you summarize individual team member activity on MS Teams for the past week and generates a report. For remote teams, chat is a crucial communication tool to ensure work gets done but with so many conversations happening at once and in multiple threads, ideas, information and decisions usually live in the moment and get lost just as quickly - and all together forgotten by the weekend! Using this template, this doesn't have to be the case. Have AI crawl through last week's activity, summarize all messages and replies and generate a casual and snappy report to bring the team back into focus for the current week. A project manager's dream! How it works A scheduled trigger is set to run every Monday at 6am to gather all team channel messages within the last week. Messages are grouped by user. AI analyses the raw messages and replies to pull out interesting observations and highlights. This is referred to as the individual reports. All individual reports are then combined and summarized together into what becomes the team weekly report. This allows understanding of group and similar activities. Finally, the team weekly report is posted back to the channel. The timing is important as it should be the first message of the week and ready for the team to glance over coffee. How to use Ideally works best per project and where most of the comms happens on a single channel. Avoid combining channels and instead duplicate this workflow for more channels. You may need to filter for specific team members if you want specific team updates. Customise the report to suit your organisation, team or the channel. You may prefer to be more formal if clients or external stakeholders are also present. Requirements MS Teams for chat platform OpenAI for LLM Customising this workflow If the teams channel is busy enough already, consider posting the final report to email. Pull in project metrics to include in your report. As extra context, it may be interesting to tie the messages to production performance. Use an AI Agent to query for knowledgebase or tickets relevant to the messages. This may be useful for attaching links or references to add context.

📈Monitoring & Alerts

4 nodes3417 views

Split Test Different Agent Prompts with Supabase and OpenAI

by Chris Carr

Split Test Agent Prompts with Supabase and OpenAI Use Case Oftentimes, it's useful to test different settings for a large language model in production against various metrics. Split testing is a good method for doing this. What it Does This workflow randomly assigns chat sessions to one of two prompts, the baseline and the alternative. The agent will use the same prompt for all interactions in that chat session. How it Works When messages arrive, a table containing information regarding session ID and which prompt to use is checked to see if the chat already exists If it does not, the session ID is added to the table and a prompt is randomly assigned These values are then used to generate a response Setup Create a table in Supabase called split_test_sessions. It needs to have the following columns: session_id (text) and show_alternative (bool) Add your Supabase, OpenAI, and PostgreSQL credentials Modify the Define Path Values node to set the baseline and alternative prompt values. Activate the workflow and test by sending messages through n8n's inbuilt chat Experiment with different chat sessions to test see both prompts in action Next Steps Modify the workflow to test different LLM settings such as temperature Add a method to measure the efficacy of the two alternative prompts

4 nodes7699 views

Qualify Calendly Demo Requests with GPT-4 & Route to Saleshandy Sequences with Logs

by Dhruv from Saleshandy

💬Communication & Collaboration

This n8n template captures every “Request a Demo” booking in Calendly, uses OpenAI to score and qualify leads in real time, routes them into the correct Saleshandy sequence, and logs all data in Google Sheets for full GTM visibility. Use cases include: Empowering SDR teams to focus on high-value demos Providing growth marketers with reliable funnel metrics Automating triage for B2B AE teams overwhelmed by demo requests Good to know OpenAI GPT-4 calls cost based on token usage—you can expect ~1,200 tokens per lead. Calendly API rate-limits at 180 requests/min; consider batching if volume spikes. Google Sheets writes are single-threaded; high-volume users may opt for Airtable or BigQuery. How it works Capture – Webhook node listens for every new “Request a Demo” form submission in Calendly. Score – AI Agent node sends job title, company size, domain quality, and custom questions to OpenAI; returns a 1–10 score plus label (Qualified/Semi-qualified/Unqualified). Verify meeting – HTTP Request node confirms via the Calendly API that a slot was actually scheduled. Route – Switch node selects the appropriate Saleshandy sequence ID (Qualified, Nurture, Disqualify). Send – HTTP Request nodes add each prospect to the chosen Saleshandy sequence. Log – Google Sheets nodes write to three tabs (Qualified, Semi-qualified, Unqualified) with lead data, score, routing path, and timestamp. Prerequisites n8n workspace Accounts & API credentials for: Calendly OpenAI (GPT-4 or GPT-3.5) Google Sheets Saleshandy Step-by-Step Setup 1. Import the n8n Template Upload the JSON file into your n8n workspace. 2. Add Required Credentials In n8n → Credentials, add: Calendly: Personal Access Token (PAT) OpenAI: API Key Google Sheets: OAuth2 connection Saleshandy: API Key 3. Calendly Setup Go to Calendly Webhook Docs Create a Routing Form in Calendly. Generate your access token. Use Postman or any API client to: Make a POST request to create a webhook subscription. Use your n8n webhook URL in the url field. Add your Authorization token and extract the Organization ID. Paste the webhook URL into the Calendly Routing Form. 4. Set Your Saleshandy Sequences In n8n, locate the Set: Sequence IDs node. Replace the placeholder text with: Your actual Qualified Semi-qualified and Unqualified Saleshandy sequence step IDs. 5. Configure Google Sheets Create a spreadsheet with the following tabs: Qualified Semi-qualified Unqualified In n8n, connect the three Google Sheets nodes to this file. Customising this workflow Adjust scoring logic – Modify the OpenAI prompt in the AI Agent node to weight ARR, industry, or headcount differently. Refine thresholds – Change the Switch node rules for score ranges (e.g., Qualified ≥8, Semi-qualified 5–7). Swap destinations – Edit HTTP Request nodes to integrate with your CRM or email platform instead of Saleshandy. Enhance logging – Replace Google Sheets with Airtable, BigQuery, or another analytics store. Add notifications – Insert Slack or Microsoft Teams nodes after routing to alert reps instantly.

5 nodes3 views

Stock Market Daily Digest with Bright Data Scraping & Gemini AI Email Reports

by Zacharia Kimotho

This workflow makes it easier to keep track of the stocks market and get an email with a summary of the daily highlights on what happened, key insights and trends Setup Guide Define the schedule (days, times, intervals). Replace sample stock data with your desired stock list (ticker, name, etc.) in JSON format. Split Out the fields to have a clean list of the stocks to monitor set keyword node Extracts the stock ticker from each item and sets it to the keyword property. Financial times scraper Triggers the Bright Data Datasets API to scrape financial data. Set the node as below Method: POST URL: https://api.brightdata.com/datasets/v3/trigger Query Parameters: dataset_id: Replace with your Bright Data dataset ID. include_errors: true type: discover_new discover_by: keyword Headers: Authorization: Bearer YOUR_BRIGHTDATA_API_KEY Replace with your Bright Data API key. Body: JSON, ={{ $('set keyword').all().map(item => item.json)}} Execute Once: Checked. Get progress node Checks the status of the Bright Data scraping job if complete, or running Setup: URL: https://api.brightdata.com/datasets/v3/progress/{{ $json.snapshot_id }} Headers: Authorization: Bearer YOUR_BRIGHTDATA_API_KEY Replace with your Bright Data API key. Get snapshot + data retrieves the scraped data from the Bright Data API. Pass the request as URL: https://api.brightdata.com/datasets/v3/snapshot/{{ $json.snapshot_id }} Query Parameters: format: json Headers: Authorization: Bearer YOUR_BRIGHTDATA_API_KEY Replace with your Bright Data API key. Aggregate. Combines the data from each stock item into a single object Update to sheet and add all items to This sheet. Make a copy before you can map the data create summary node generates a summary of the scraped stock data using the Google Gemini AI model and notifies you via Gmail. Setup: Prompt Type: define Text: Customize the prompt to define the AI's role, input format, tasks, output format (HTML email), and constraints. Google Sheets. Appends the scraped data to a Google Sheet. This should be set to automap so as to adjust to the results found in the request Important Notes: Remember to replace placeholder values (API keys, dataset IDs, email addresses, Google Sheet IDs) with your actual values. Review and customize the AI prompt for the "create summary" node to achieve the desired email summary output. Consider adding error handling for a more robust workflow. Monitor API usage to avoid rate limits.

📊Data Processing

4 nodes1404 views

Automated Generation of AI Advertising Photos for Product Marketing

by Julian Ivanov

How it works This workflow automates the transformation of standard product images into professional product photography featuring human models It uses AI to analyze product images, create tailored photography prompts, and generate high-quality enhanced versions Set up steps You'll need an OpenAI API key and access to gpt-image-1 (verify your organization) Set up a Google Sheets spreadsheet with columns: Image-URL, Prompt, Output Create a Google Drive folder to store the generated images Requirements: OpenAI API access (for image generation and analysis) Google Sheets and Google Drive accounts Basic product images (URLs) as input The spreadsheet must contain a column named "Image-URL" with links to the product images This workflow automatically: Reads product image URLs from your Google Sheet Downloads the images for processing Analyzes each image to understand what product it contains Creates specialized photography prompts ensuring each product is shown with a human model Generates professional product photography using OpenAI's image generation capabilities Uploads results to Google Drive and updates your spreadsheet with links Extra: You can also use the included simple image generation workflow to directly create images via prompt without product image input. This option lets you quickly generate images through the OpenAI API using just text prompts

6 nodes3718 views

Analyze Search Intent for Keywords with Google Scraping, Bright Data, and Gemini AI

by Zacharia Kimotho

What it does This workflow scrapes the top 10 pages on SERP and conducts an in-depth analysis of the keyword intent for each ranking keyword, saving the information to a Google Sheet for further analysis. How does this workflow work? We add our keywords and country code to a Google sheet that we need to monitor and research on Run the system Scrape the top 10 pages Analyze the intents of the top 10 and update to a Google sheet Technical Setup Make a copy of this G sheet Add your desired keywords to the Google sheet Map keyword and country code Update the Zone name to match your zone on Bright Data Run the scraper Upon successful scraping, we run an intent classifier to determine the intents for each ranking page and update the G sheet. Setting up the Serp Scraper in Bright Data On Bright Data, go to the Proxies & Scraping tab Under SERP API, create a new zone Give it a suitable name and description. The default is serp_api Add this to your account Add your credentials as a header credential

4 nodes2 views

Extract & Analyze Brand Content with Bright Data and Google Gemini

by Ranjan Dailata

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 Perists the response to disk Setup Sign up at Bright Data. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. 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. A Google Gemini API key (or access through Vertex AI or proxy). Update the Set URL and Bright Data Zone for setting the brand content URL and the Bright Data Zone name. 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.

📊Data Processing

5 nodes407 views

TechCrunch AI Article Scraper & Classifier with GPT-4.1-nano to Sheets & Telegram

by Mujahid Kabae

How it works This workflow scrapes the latest Artificial Intelligence articles from TechCrunch, then processes and classifies the content using OpenAI and LangChain nodes. The final result is saved to Google Sheets and sent as a summary to a Telegram group. Workflow Logic: Trigger: Schedules daily at 6AM Bangkok time. Scraper: Extracts URLs and publish dates from TechCrunch's AI category. Filter: Only continues if the article is from yesterday (to avoid duplication). Content Fetch: Downloads and extracts article body text. AI Agent: Summarizes the article in Thai. Scores it using strict journalism criteria (max 100). Categorizes the news into one of 9 predefined categories. Output: Saves all structured data to Google Sheets. Sends a summary to a Telegram group. Set up steps 🕒 Estimated setup time: 10–15 minutes Connect your credentials: Google Sheets (OAuth2) Telegram OpenAI account (via LangChain model) Update the Telegram chatId and Google Sheets documentId/sheetName values. Deploy and activate the workflow. It runs daily without manual intervention.

8 nodes4 views

Build a RAG System for PDF Documents with Google Drive, Unstructured, and OpenAI

by Tomas Lubertino

This template monitors a Google Drive folder, converts PDF documents into clean text chunks with Unstructured, generates OpenAI embeddings, and upserts vectors into Pinecone. It’s a practical, production-ready starting point for Retrieval-Augmented Generation (RAG) that you can plug into a chatbot, semantic search, or internal knowledge tools. How it works 1) Google Drive Trigger detects new files in a selected folder and downloads them. 2) The files are sent to Unstructured where they are split into smaller pieces (chunks). 3) The chunks are prepared to be sent to OpenAI where they are converted into vectors (embeddings). 4) The embeddings are recombined with their original data and the payload is prepared for upsert into the Pinecone index. Set up steps 1) In Pinecone, create an index with 1536 dimensions and configure it for text-embedding-3-small. 2) Copy the host url and paste it on the 'Pinecone Upsert' node. It should look something like this: https://{your-index-name}.pinecone.io/vectors/upsert. 3) Add Google Drive, OpenAI and Pinecone credentials in n8n. 4) Point the trigger to your ingest folder (you can use this article for demo). 5) Click the 'Open chat' button and enter the following: Which Git provider do the authors use?

📝Content Management