Workflow Templates

AI News Scraping System This n8n workflow automates the process of pulling in breaking AI-related headlines from curated RSS feeds, scraping their full content, and saving readable Markdown versions directly to Google Drive. Use cases include: Creating a personal newsletter curation system Automating blog post research workflows Archiving news content for later summarization or AI use How it Works Scheduled Triggers The workflow runs every 3–4 hours using multiple Schedule Trigger nodes. Each trigger targets a different news source (e.g., Google News, OpenAI Blog, Hugging Face, etc.). Fetch and Parse Feeds RSS feeds are fetched via the HTTP Request node. Items from the feed are split into individual entries using the Split Out node. Scrape Article Content Each article URL is sent to the Firecrawl API with a prompt to extract only the main content in Markdown. The scraping skips navigation, headers, footers, and ads. Convert and Save The extracted Markdown is converted into a .md file using the Convert to File node. The file is then uploaded to a Google Drive folder. Good to Know This workflow uses the Firecrawl API for web scraping. Be sure to configure a Generic HTTP Header credential with your API key. Output files are saved in Markdown format You can add more Schedule Trigger + HTTP Request pairs to extend this workflow to additional feeds. Requirements Firecrawl API account for scraping Google Drive account (OAuth2 credentials must be configured in n8n) n8n instance (self-hosted or cloud) Customization Ideas Replace or extend RSS feeds with sources relevant to your niche Load up scraped news stories into a prompt to create new content like TikToks and Reels Add a summarization step using an LLM like GPT or Claude Send the Markdown files to Notion, Slack, or a blog CMS Example Feeds | Feed Name | URL | |------------------|----------------------------------------------------------------------| | Google News (AI) | https://rss.app/feeds/v1.1/AkOariu1C7YyUUMv.json | | OpenAI Blog | https://rss.app/feeds/v1.1/xNVg2hbY14Z7Gpva.json | | Hugging Face | https://rss.app/feeds/v1.1/sgHcE2ehHQMTWhrL.json |

This workflow automates the Mark as Fulfilled action in Squarespace for each order, ensuring a seamless fulfillment process without manual intervention. How It Works This workflow retrieves all pending Squarespace orders and processes their fulfillment automatically. The workflow follows these steps: 1️⃣ Get all pending orders using the HTTP Request node (Since Squarespace does not have a n8n node) 2️⃣ Create a fulfillment request using Fulfill Order node The Filter Orders node can be used to filter valid pending order to process. Step-by-step The workflow can be run as requested or on schedule You can adjust these parameters within the Global and filter nodes: Global node for API Setting api-version** (string, required) – The current API version (see Squarespace Orders API documentation). modifiedAfter**={a-datetime} (string, conditional) – Fetch orders modified after a specific date (ISO 8601 format). modifiedBefore**={b-datetime} (string, conditional) – Fetch orders modified before a specific date (ISO 8601 format). cursor**={c} (string, conditional) – Used for pagination, cannot be combined with other filters. fulfillmentStatus**={status} (optional, enum) – Filter by fulfillment status: PENDING, FULFILLED, or CANCELED. maxPage** – Set -1 to enables infinite pagination to fetch all available orders. Filter Orders node Order Filtering – Ensures only valid orders are fulfilled, particularly useful if: You sell digital downloads or gift cards exclusively. You use third-party fulfillment services for all products. Requirements Credentials To use this workflow, you need: Squarespace API Key – Retrieve from your Squarespace settings. Who Is This For? Squarespace store owners looking to automate their fulfillment process. Merchants selling digital or personalized products who need instant fulfillment. Explore More Templates Get all orders in Squarespace to Google Sheets Convert Squarespace Profiles to Shopify Customers in Google Sheets Fetch Squarespace Blog & Event Collections to Google Sheets 👉 Check out my other n8n templates

This is a specific use case. The ElevenLabs guide for Cal.com bookings is comprehensive but I was having trouble with the booking API request. So I built a simple workflow to validate the request and handle the booking creation. Who's this for? You have an ElevenLabs voice agent (or other external service) booking meetings in your Cal.com account and you want more control over the book_meeting tool called by the voice agent. How's it work? Request is received by the webhook trigger node Request sent from ElevenLabs voice agent, or other source Request body contains contact info for the user with whom a meeting will be booked in Cal.com Workflow validates input data for required fields in Cal.com If validation fails, a 400 bad request response is returned If valid, meeting is booked in Cal.com api How do I use this? Create a custom tool in the ElevenLabs agent setup, and connect it to the webhook trigger in this workflow. Add authorization for security. Instruct your voice agent to call this tool after it has collected the required information from the user. Expected input structure Note: Modify this according to your needs, but be sure to reflect your changes in all following nodes. Requirements here depend on required fields in your Cal.com event type. If you have multiple event types in Cal.com with varying required fields, you'll need to handle this in this workflow, and provide appropriate instructions in your *voice agent prompt*. "body": { "attendee_name": "Some Guy", "start": "2025-07-07T13:30:00Z", "attendee_phone": "+12125551234", "attendee_timezone": "America/New_York", "eventTypeId": 123456, "attendee_email": "someguy@example.com", "attendee_company": "Example Inc", "notes": "Discovery call to find synergies." } Modifications Note: ElevenLabs doesn't handle webhook response headers or body, and only recognizes the response code. In other words, if the workflow responds with 400 Bad request that's the only info the voice agent gets back; it doesn't get back any details, eg. "User email still needed". You can modify the structure of the expected webhook request body, and then you should reflect that structure change in all following nodes in the workflow. Ie. if you change attendee_name to attendeeFirstName and attendeeLastName then you need to make this change in the following nodes that use these properties. You can also require or make optional other user data for the Cal.com event type which would reduce or increase the data the voice agent must collect from the user. You can modify the authorization of this webhook to meet your security needs. ElevenLabs has some limitations and you should be mindful of those, but it also offers a secret feature with proves useful. An improvement to this workflow could include a GET request to a CRM or other db to get info on the user interacting with the voice agent. This could reduce some of the data collection needed from the voice agent, like if you already have the user's email address, for example. I believe you can also get the user's phone number if the voice agent is set up on a dial-in interface, so then the agent wouldn't need to ask for it. This all depends on your use case. A savvy step might be prompting the voice agent to get an email, and using the email in this workflow to pull enrichment data from Apollo.io or similar ;-)

This n8n workflow tracks user engagement in a specific WhatsApp group by capturing incoming messages via a Whapi webhook. It first filters messages to ensure they come from the correct group, then identifies the message type—text, emoji reaction, voice, or image. The workflow searches for the user in an Airtable database using their WhatsApp ID and increments their message count by one. It updates the Airtable record with the new count and the date of the last interaction. This automated process helps measure user activity and supports engagement initiatives like weekly raffles or rewards. The system is flexible and can be expanded to include more message types or additional actions. Overall, it provides a seamless way to encourage and track user participation in your WhatsApp community.

Workflow Overview This workflow automates the creation and management of a custom OpenAI Assistant for a travel agency ("Travel with us"), leveraging Google Drive for document storage. How It Works 1. Create the OpenAI Assistant Node**: OpenAI Action: Creates a custom assistant named "Travel with us" Assistant using the gpt-4o-mini model. Instructions: Respond only using the provided document (e.g., agency-specific info). Stay friendly, brief, and focused on travel-related queries. Ignore irrelevant questions politely. Credentials: Requires OpenAI API key. 2. Upload Agency Document Google Drive Node**: Action: Downloads a Google Doc as a PDF. OpenAI2 Node**: Action: Uploads the PDF to OpenAI with purpose: "assistants". Output: Generates a file_id. 3. Update the Assistant with the Document OpenAI Node**: Action: Updates the assistant to include the uploaded file. 4. Chat Interaction Chat Trigger**: Activates when a message is received ("When chat message received"). OpenAI Assistant Node**: Action: Uses the updated assistant to respond to user queries. Memory: Window Buffer Memory retains chat context for coherent conversations. Set Up Steps Prepare the Document: Store your travel agency guide in Google Drive (e.g., as a Google Doc). Update the Google Drive node with your document’s ID. Configure Credentials: Google Drive: Connect via OAuth2 (googleDriveOAuth2Api). OpenAI: Add your API key to all OpenAI nodes. Customize the Assistant: Modify the instructions in the OpenAI node to reflect your agency’s needs. Ensure the document includes FAQs, policies, and travel info. Test the Workflow: Trigger manually ("Test workflow") to create the assistant and upload the file. Send a chat message (e.g., "What are your travel packages?") to test responses. Dependencies Google Drive Account**: To store and retrieve the agency document. OpenAI API Access**: For assistant creation and file uploads.

Who is it for? This workflow is perfect for marketers, sales teams, agencies, and local businesses who want to save time by automating lead generation from Google Maps. It’s ideal for real estate agencies, restaurants, service providers, and any local niche that needs a clean database of fresh contacts, including emails, websites, and phone numbers. ✅ Prerequisites Before starting, make sure you have: Apify account** → to scrape Google Maps data OpenAI API key** → for GPT-4 email extraction Airtable account & base** → for structured lead storage Gmail account with OAuth** → to send personalized outreach emails Your Airtable base should have these columns: | Title | Street | Website | Phone Number | Email | URL | |-------------------------|-------------------------|--------------------|-----------------|------------------------|----------------------| | Paris Real Estate Agency| 10 Rue de Rivoli, Paris | https://agency.fr | +33 1 23 45 67 | contact@agency.fr | maps.google.com/... | 🏡 Example Use Case To keep things clear, we’ll use real estate agencies in Paris as an example. But you can replace this with restaurants, plumbers, lawyers, or even hamster trainers (you never know). 🔄 How the workflow works Scrape Google Maps leads with Apify Clean & structure the data (name, phone, website) Visit each website & extract emails with GPT-4 Save all leads into Airtable Automatically send a personalized email via Gmail This works for any industry, keyword, or location. Step 1 – Scraping Google Maps with Apify Start simply: Open your n8n workflow and choose the trigger: “Execute Workflow” (manual trigger). Add an HTTP Request node (POST method). Now, head over to Apify Google Maps Extractor. Fill in the fields according to your needs: Keyword: e.g., "real estate agency" (or restaurant, plumber...) Location: "Paris, France" Number of results: 50 (or more) Optional: filters (with/without a website, by categories…) Click Run to test the scraper. Then click API → select API endpoints tab. Choose “Run Actor synchronously and get dataset items”. Copy the URL, go back to n8n, and paste it into your HTTP Request node (URL field). Then enable: Body Content Type → JSON Specify Body Using JSON Go back to Apify, click the JSON tab, copy everything, and paste it into the JSON field of your HTTP Request. If you now run your workflow, you'll get a nice structured table filled with Google Maps data. Pretty magical already—but we're just getting started! Step 2 – Cleaning Things Up (Edit Fields) Raw data is cool, but messy. Add an Edit Fields node next, using Manual Mapping mode. Here’s what you keep (copy-paste friendly): Title → {{ $json.title }} Address → {{ $json.address }} Website → {{ $json.website }} Phone → {{ $json.phone }} URL → {{ $json.url }} Now, you have a clean, readable table ready to use. Step 3 – Handling Each Contact Individually (Loop Over Items) Next, we process each contact one by one. Add the Loop Over Items node: Set Batch Size to 20 or more, depending on your needs. This node is simple but crucial to avoid traffic jams in the automation. Step 4 – Isolating Websites (Edit Fields again) Add another Edit Fields node (Manual Mapping). This time, keep just: Website → {{ $json.website }} We've isolated the websites for the next step: scraping them one by one. Step 5 – Scraping Each Website (HTTP Request) Now, we send our little robot to visit each website automatically. Add another HTTP Request node: Method: GET URL: {{ $json.website }} (from the previous node) This returns the raw HTML content of each site. Yes, it's ugly, but we won't handle it manually. We'll leave the next step to AI! Step 6 – Extracting Emails with ChatGPT We now use OpenAI (Message a Model) to politely ask GPT to extract only relevant emails. Configure as follows: Model: GPT-4-1-mini or higher Operation: Message a Model Simplify Output: ON Prompt to copy-paste: Look at this website content and extract only the email I can contact this business. In your output, provide only the email and nothing else. Ideally, this email should be of the business owner, so if you have 2 or more options, try for the most authoritative one. If you don't find any email, output 'Null'. Exemplary output of yours: name@examplewebsite.com {{ $json.data }} ChatGPT will kindly return the perfect email address (or 'Null' if none is found). Step 7 – Neatly Store Everything in Airtable Almost done! Add an Airtable → Create Record node. Fill your Airtable fields like this: | Airtable Field | Content | n8n Variable | | ------------------ | ------------------------------- | ------------------------------------------ | | Title | Business name | {{ $('Edit Fields').item.json.Title }} | | Street | Full address | {{ $('Edit Fields').item.json.Address }} | | Website | Website URL | {{ $('Edit Fields').item.json.Website }} | | Phone Number | Phone number | {{ $('Edit Fields').item.json.Phone }} | | Email | Email retrieved by the AI agent | {{ $json.message.content }} | | URL | Google Maps link | {{ $('Edit Fields').item.json.URL }} | Now, you have a tidy Airtable database filled with fresh leads, ready for action. Step 8 – Automated Email via Gmail (The Final Touch) To finalize the workflow, add a Gmail → Send Email node after your Airtable node. Here’s how to configure this node using the data pulled directly from your Airtable base (from the previous step): Recipient (To): Retrieve the email stored in Airtable ({{ $json.fields.Email }}). Subject: Use the company name stored in Airtable ({{ $json.fields.Title }}) to personalize the subject line. Body: You can include several fields directly from Airtable, such as: Company name: {{ $json.fields.Title }} Website URL: {{ $json.fields.Website }} Phone number: {{ $json.fields["Phone Number"] }} Link to the Google Maps listing: {{ $json.fields.URL }} All of this data is available in Airtable because it was automatically inserted in the previous step (Step 7). This ensures that each email sent is fully personalized and based on clear, reliable, and structured information.

Overview A comprehensive educational workflow that demonstrates practical JavaScript usage in n8n's Code node through real-world business scenarios. Perfect for learning data manipulation, transformation, and automation patterns that you can immediately apply to client projects. What This Template Teaches: Data Filtering & Transformation - Filter employees by age, calculate bonuses, format contact information Statistical Analysis - Generate team statistics, averages, role distributions, and KPIs Multi-Format Export - Create CSV files, email lists, and API-ready payloads from raw data n8n Best Practices - Proper JSON handling, return formats, and data flow patterns How It Works: Manual Trigger starts the workflow with sample employee data Set Sample Data provides realistic business data (employees with roles, salaries, ages) Three Code Node Examples process the same data differently: Filter & Transform: Creates adult employee list with calculated bonuses Calculate Stats: Generates comprehensive team analytics and reports Format for Export: Prepares data for external systems (APIs, emails, CSV) Key Learning Points: Access input data using items[0].json.propertyName Return proper n8n format with [{ json: data }] structure Use JSON.parse() for string-to-object conversion Apply JavaScript array methods (filter, map, reduce) for data processing Handle multiple output scenarios and data aggregation Perfect For: n8n beginners learning Code node fundamentals Developers transitioning to n8n automation Client demos showing data processing capabilities Team training and onboarding sessions Foundation for building custom business automation workflows Business Use Cases: Transform this template for lead qualification, customer segmentation, report generation, data enrichment, and API integrations. Each Code node pattern can be adapted for different industries and automation needs.

This workflow will take a timer entry from Clockify and submit it to a matching ticket in Syncro. It saves the time entry ID from Clockify and the time entry ID from Syncro into a Google Sheets. Then, it will check if a match already exists from a previous update and will update the same time entry if the description or time is changed in Clockify. There is a Set node with the name and Syncro IDs of technicians. If you have multiple technicians with the same name, this won't work for you. Likewise, if the name in Clockify doesn't exactly match what you put in the Set, it won't work. You also need to setup a webhook in Clockify set to trigger on "Time entry updated (anyone)" and pointed at your workflow. Configured this way, you can start and stop time entries at will and it won't do anything until you change the description. > This workflow is part of an MSP collection, The original can be found here: https://github.com/bionemesis/n8nsyncro

Who this template is for This template is for everyone who needs to work with XML data a lot and wants to convert it to JSON instead. Use case Many products still work with XML files as their main language. Unfortunately, not every software still supports XML, as many switched to more modern storing languages such as JSON. This workflow is designed to handle the conversion of XML data to JSON format via a webhook call, with error handling and Slack notifications integrated into the process. How this workflow works Triggering the workflow: This workflow initiates upon receiving an HTTP POST request at the webhook endpoint specified in the "POST" node. The endpoint, designated as , can be accessed externally by sending a POST request to that URL. Data routing and processing: Upon receiving the POST request, the Switch node routes the workflow's path based on conditions determined by the content type of the incoming data or any encountered errors. The Extract From File and Edit Fields (Set) nodes manage XML input processing, adapting their actions according to the data's content type. XML to JSON conversion: The XML data extracted from the input is passed through the "XML" node, which performs the conversion process, transforming it into JSON format. Response handling: If the XML-to-JSON conversion is successful, a success response is sent back with a status of "OK" and the converted JSON data. If there are any errors during the XML-to-JSON conversion process, an error response is sent back with a status of "error" and an error message. Error handling: in case of an error during processing, the workflow sends a notification to a Slack channel designated for error reporting. Set up steps Set up your own in the Webhook node. While building or testing a workflow, use a test webhook URL. When your workflow is ready, switch to using the production webhook URL. Set credentials for Slack.

Who this template is for This template is for developers, content creators, or application builders who want to integrate an AI-powered text-to-image generation service into their applications or systems via an API endpoint. Use case Creating a secure API endpoint that converts text prompts into AI-generated images, with built-in content moderation to prevent inappropriate content generation. This can be used for creative applications, content creation tools, prototyping interfaces, or any system that needs on-demand image generation. How this workflow works Receives text prompt through a webhook endpoint Filters the prompt for inappropriate content using AI moderation Submits valid prompts to the Fal.ai Flux image generation service Polls for completion status and retrieves the generated image when ready Returns the image results in a structured JSON format to the client Set up steps Create a Fal.ai account and obtain API credentials Configure the HTTP Header Auth credentials with your Fal.ai API key Set up an OpenAI API key for the content moderation component Deploy the workflow and note the webhook URL for your API endpoint Test the endpoint by sending a POST request with a JSON body containing a "prompt" field

🚀 Automate News Discovery & Publishing with GPT-4, Google Search API & Slack 🎯 Overview Automated content publishing system that discovers industry news, transforms it into original articles using GPT-4, and publishes across multiple channels with SEO optimization and intelligent duplicate prevention. ✨ Key Features 🤖 Smart Query Generation** - AI agent generates unique search queries while checking Google Sheets to avoid duplicates 🔍 News Discovery** - Uses Google Custom Search API to find recent articles (last 7 days) 🧠 Content Intelligence** - Processes search results and skips anti-bot protected sites automatically 📝 GPT-4 Article Generation** - Creates professional, SEO-optimized news articles in Reuters/Bloomberg style 📢 Multi-Channel Publishing** - Publishes to CMS with automatic Slack notifications 📊 Comprehensive Tracking** - Logs all activity to Google Sheets for analytics and duplicate prevention 🔄 How It Works ⏰ Scheduled Trigger runs every 8 hours to maintain consistent content flow 🤖 AI Agent generates targeted search queries for your niche while checking historical data 🔍 Google Search finds recent articles and extracts metadata (title, snippet, source) 🛡️ Smart Content Handler bypasses sites with anti-bot protection, using search snippets instead ⚡ GPT-4 Processing transforms snippets into comprehensive 2000+ word articles with proper formatting 🚀 Publishing Pipeline formats content for CMS with SEO metadata and publishes automatically 📱 Notification System sends detailed Slack updates with article metrics 📈 Activity Logging tracks all published content to prevent future duplicates 🔧 Setup Requirements 📋 Prerequisites Google Custom Search API key and Search Engine ID OpenAI GPT-4 API access Google account for tracking spreadsheet Slack workspace for notifications CMS or website with API endpoint for publishing 🛠️ Step-by-Step Setup Step 1: 🔎 Google Custom Search Configuration Go to Google Custom Search Engine Create a new search engine Configure to search the entire web Copy your Search Engine ID (cx parameter) Get your API key from Google Cloud Console Step 2: 📊 Google Sheets Template Setup Create a Google Sheet with these required columns: Column A:** timestamp - ISO date format (YYYY-MM-DD HH:MM:SS) Column B:** query - The search query used Column C:** title - Published article title Column D:** url - Published article URL Column E:** status - Publication status (success/failed) Column F:** word_count - Final article word count Template URL: Copy this Google Sheets template Step 3: 🔑 Credential Configuration Set up the following credentials in n8n: 📊 Google Sheets API - OAuth2 connection to your Google account 🤖 OpenAI API - Your GPT-4 API key 📱 Slack Webhook - Webhook URL for your notification channel 🔍 Custom Search API - Your Google Custom Search API key Step 4: ⚙️ Workflow Customization Modify these key parameters to fit your needs: 🎯 Search Topic:** Edit the AI agent prompt to focus on your industry ⏰ Publishing Schedule:** Adjust the cron trigger (default: every 8 hours) 📝 Article Length:** Modify GPT-4 prompt for different word counts 🌐 CMS Endpoint:** Update the publishing node with your website's API 🎨 Customization Options 🎯 Content Targeting Modify the AI agent's search query generation to focus on specific industries Adjust date restrictions (currently set to last 7 days) Change the number of search results processed per run ✍️ Article Style Customize GPT-4 prompts for different writing styles (formal, casual, technical) Adjust article length requirements Modify SEO optimization parameters 📡 Publishing Channels Add additional CMS endpoints for multi-site publishing Configure different notification channels (Discord, Teams, etc.) Set up social media auto-posting integration 💡 Use Cases 📰 Automated news websites 📝 Industry blog content generation 🔍 SEO content pipeline automation 📊 News aggregation and republishing 📈 Content marketing automation 🛠️ Technical Notes Workflow includes error handling for anti-bot protection Duplicate prevention through Google Sheets tracking Rate limiting considerations for API usage Automatic retry logic for failed requests 🆘 Support For setup assistance or customization help, refer to the workflow's internal documentation nodes or contact the template creator.

Personal Finance AI Agent – Telegram Bot (n8n Workflow) A fully automated Telegram-based personal finance tracker that: Accepts receipts as images, PDFs, or plain text Uses Google Gemini Vision for OCR & intelligent extraction Logs every expense into Google Sheets Stores receipt images/PDFs in Google Drive Answers natural-language spending questions ("How much did I spend on food last month?", "Compare this month vs last month", etc.) Built entirely with n8n – 100% self-hostable, no-code/low-code. How It Works (Overview) You send a message to your Telegram bot → Photo of a receipt, PDF, or just text like "Nov 10 – 2500 NGN – Uber" Switch node detects the message type: Photo → Branch 0 Document (PDF/other) → Branch 1 Pure text → Branch 2 (goes straight to query agent) Receipt Processing Path (Images & PDFs) Files downloaded from Telegram → uploaded to Google Drive ("Monthly receipts" folder) Images → OCR with Gemini Vision PDFs → native PDF text extraction Extracted text + Drive link → merged → sent to Gemini AI Agent AI extracts: Date (YYYY-MM-DD) • Amount (NGN) • Description • Category (food, transportation, subscriptions, takeouts, entertainment, gift, electricity, repairs, other stuffs) Clean JSON → appended to Google Sheets → friendly confirmation sent back Spending Query Path (Text questions) Second AI Agent with access to the live Google Sheet + calculator + memory Answers anything: totals, breakdowns, comparisons, trends, percentages… Live Google Sheet (Template) You can make a copy of the exact sheet the bot uses: https://docs.google.com/spreadsheets/d/1kwWJquPpwL9vt9U06a4f4phXq5jZjaGazvh2V69FGoc/edit?usp=sharing Just click File → Make a copy and use your copy’s ID in the workflow. Setup Steps (Step-by-Step) Prerequisites n8n instance (cloud or self-hosted) Telegram bot (created via @BotFather) Google account 1. Create Telegram Bot Message @BotFather → /newbot Copy the bot token In n8n → Credentials → New Telegram API credential → paste token 2. Google Setup Make a copy of the sheet above → Copy the new spreadsheet ID from the URL Create a Google Drive folder called "Monthly receipts" (or any name) → copy folder ID Enable Gemini API in Google Cloud (or use your existing key) In n8n create these credentials: Google Sheets OAuth2 API Google Drive OAuth2 API Google Gemini (PaLM) API 3. Import Workflow Copy the full JSON from the original file n8n → Workflows → Import → paste → Import 4. Update IDs & Credentials After import, configure these nodes: | Node | What to Change | |-----------------------------------|-----------------------------------------------------| | Telegram Trigger + all Telegram nodes | Your Telegram credential | | Google Sheets nodes | Your Google Sheets credential + new Sheet ID | | Google Drive "Upload file" nodes | Paste your "Monthly receipts" folder ID | | Gemini nodes | Your Gemini credential | | AI Agent & AI Agent1 | Verify model, memory, tools are connected | 5. Activate & Test Click Activate Start chatting with your bot on Telegram Test commands Send a photo/PDF receipt Type: How much did I spend last month? Type: Show me food spending this month vs last month You’ll get instant replies and see new rows appear in your sheet! Features Zero manual entry ever again Works with handwritten receipts Smart categorization Natural-language spending insights All data stays 100% in your Google account Completely private & self-hostable NGN-native (Naira) Never track expenses manually again!