Automated financial tracker: Telegram invoices to Notion with Gemini AI reports
Automated Financial Tracker: Telegram Invoices to Notion with AI Summaries & Reports --- Tired of manually logging every expense? Streamline your financial tracking with this powerful n8n workflow! Snap a photo of your invoice in Telegram, and let AI (powered by Google Gemini) automatically extract the details, record them in your Notion database, and even send you a quick summary. Plus, get scheduled weekly reports with charts to visualize your spending. Automate your finances, save time, and gain better insights with this easy-to-use template! Transform your expense tracking from a chore into an automated breeze. Try it out! --- Overview: This workflow revolutionizes how you track your finances by automating the entire process from invoice capture to reporting. Simply send a photo of an invoice or receipt to a designated Telegram chat, and this workflow will: Extract Data with AI: Utilize Google Gemini's capabilities to perform OCR on the image, understand the content, and extract key details like item name, quantity, price, total, date, and even attempt to categorize the expense. Store in Notion: Automatically log each extracted transaction into a structured Notion database. Instant Feedback: Send a summary of the processed transaction back to your Telegram chat. Scheduled Reporting: Generate and send a visual summary of your expenses (e.g., weekly spending by category) as a chart to your preferred Telegram chat or group. This workflow is perfect for individuals, freelancers, or small teams looking to effortlessly manage their expenses without manual data entry. Key Features & Benefits: Effortless Expense Logging: Just send a picture – no more typing! AI-Powered Data Extraction: Leverages Google Gemini for intelligent invoice processing. Centralized Data in Notion: Keep all your financial records neatly organized in a Notion database. Automated Categorization: AI helps in categorizing your expenses (e.g., Food & Beverage, Transportation). Instant Summaries: Get immediate confirmation and a summary of what was recorded. Visual Reporting: Receive scheduled charts (e.g., bar charts of spending by category) directly in Telegram. Customizable: Easily adapt the workflow to your specific needs, categories, and reporting preferences. Time-Saving: Drastically reduces the time spent on manual financial administration. How It Works (Workflow Breakdown): The workflow is divided into two main parts: Part 1: Real-time Invoice Processing & Logging (Auto Notes Transaction with Telegram and Notion database) Telegram Trigger (Telegram Trigger | When recive photo): Activates when a new photo is sent to the configured Telegram chat. Get Photo Info (Get Info Photo from telegram chat): Retrieves the details of the received photo. Get Image Info (Get Image Info): Prepares the image data. AI Data Extraction (Google Gemini Chat Model & Basic LLM Chain): The image data is sent to the Google Gemini Chat Model. A specific prompt instructs the AI to extract details (date, ID, name, quantity, price, total, category, tax) in a JSON array format and provide a summary message. The categories include Food & Beverage, Transportation, Utilities, Shopping, Healthcare, Entertainment, Housing, and Education. Parse AI Output (Parse To your object | Table): Structures the AI's JSON output for easier handling. Split Transactions (Split Out | data transaction): If an invoice contains multiple items, this node splits them into individual records. Record to Notion (Record To Notion Database): Each transaction item is added as a new page/entry in your specified Notion database, mapping fields like Name, Quantity, Price, Total, Category, Date, and Tax. Send Telegram Summary (Sendback to chat and give summarize text): The summary message generated by the AI is sent back to the original Telegram chat. Part 2: Scheduled Financial Reporting (Schedule report to send on chanel or private message) Schedule Trigger (Schedule Trigger | for send chart report): Runs at a predefined interval (e.g., every week) to generate reports. Get Recent Data from Notion (Get Recent Data from Notions): Fetches transaction data from the Notion database for a specific period (e.g., the past week). Summarize Data (Summarize Transaction Data): Aggregates the data, for example, by summing up the 'total' amount for each 'category'. Prepare Chart Data (Convert Data to JSON chart payload): Transforms the summarized data into a JSON format suitable for generating a chart (e.g., labels for categories, data for spending amounts). Generate Chart (Generate Chart): Uses the QuickChart node to create a visual chart (e.g., a bar chart) from the prepared data. Send Chart to Telegram (Send Chart Image to Group or Private Chat): Sends the generated chart image to a specified Telegram chat ID or group. Nodes Used (Key Nodes): Telegram Trigger & Telegram Node: For receiving images and sending messages/images. Google Gemini Chat Model (Langchain): For AI-powered OCR and data extraction from invoices. Basic LLM Chain (Langchain): To interact with the language model using specific prompts. Output Parser Structured (Langchain): To structure the output from the language model. Notion Node: For reading from and writing to your Notion databases. Schedule Trigger: To automate the reporting process. Summarize Node: To aggregate data for reports. Code Node: Used here to format data for the chart. QuickChart Node: For generating charts. SplitOut Node: To process multiple items from a single invoice. Setup Instructions: Credentials: Telegram: Create a Telegram bot and get its API token. You'll also need the Chat ID where you'll send invoices and where reports should be sent. Google Gemini (PaLM) API: You'll need an API key for Google Gemini. Notion: Create a Notion integration and get the API key. Create a Notion database with properties corresponding to the data you want to save (e.g., Name (Title), Quantity (Number), Price (Number), Total (Number), Category (Select), Date (Text or Date), Tax (Number)). Share this database with your Notion integration. Configure Telegram Trigger: Add your Telegram Bot API token. When you first activate the workflow or test the trigger, send /start to your bot in the chat you want to use for sending invoices. n8n will then capture the Chat ID. Configure Google Gemini Node (Google Gemini Chat Model): Select or add your Google Gemini API credentials. Review the prompt in the Basic LLM Chain node and adjust if necessary (e.g., date format, categories). Configure Notion Nodes: Record To Notion Database: Select or add your Notion API credentials. Select your target Notion Database ID. Map the properties from the workflow (e.g., ={{ $json.name }}) to your Notion database columns. Get Recent Data from Notions: Select or add your Notion API credentials. Select your target Notion Database ID. Adjust the filter if needed (default is "past_week"). Configure Telegram Node for Reports (Send Chart Image to Group or Private Chat): Select or add your Telegram Bot API token. Enter the Chat ID for the group or private chat where you want to receive the reports. Configure Schedule Trigger (Schedule Trigger | for send chart report): Set your desired schedule (e.g., every Monday at 9 AM). Test: Send an image of an invoice to your Telegram bot and check if the data appears in Notion and if you receive a summary message. Wait for the scheduled report or manually trigger it to test the reporting functionality. --- Sticky Note Text for Your n8n Template: (These are suggestions. You would place these directly into the sticky notes within your n8n workflow editor.) Existing High-Level Sticky Notes: Auto Notes Transaction with Telegram and Notion database Schedule report to send on chanel or private message Specific Sticky Notes to Add: On Telegram Trigger | When recive photo: 📸 INVOICE INPUT 📸 Bot listens here for photos of your receipts/invoices. Ensure your Telegram Bot API token is set in credentials. Near Google Gemini Chat Model & Basic LLM Chain: 🤖 AI MAGIC HAPPENS HERE 🧠 Image is sent to Google Gemini for data extraction. Check 'Basic LLM Chain' to customize the AI prompt (e.g., categories, output format). Requires Google Gemini API credentials. On Parse To your object | Table: ✨ STRUCTURING AI DATA ✨ Converts the AI's text output into a usable JSON object. Check the schema if you modify the AI prompt significantly. On Record To Notion Database: 📝 SAVING TO NOTION 📝 Extracted transaction data is saved here. Configure with your Notion API key & Database ID. Map fields correctly to your database columns! On Sendback to chat and give summarize text: 💬 TRANSACTION SUMMARY 💬 Sends a confirmation message back to the user in Telegram with a summary of the recorded expense. On Schedule Trigger | for send chart report: 🗓️ REPORTING SCHEDULE 🗓️ Set how often you want to receive your spending report (e.g., weekly, monthly). On Get Recent Data from Notions: 📊 FETCHING DATA FOR REPORT 📊 Retrieves transactions from Notion for the report period. Default: "Past Week". Adjust filter as needed. Requires Notion API credentials & Database ID. On Summarize Transaction Data: ➕ SUMMARIZING SPENDING ➕ Aggregates your expenses, usually by category, to prepare for the chart. On Convert Data to JSON chart payload (Code Node): 🎨 PREPARING CHART DATA 🎨 This Code node formats the summarized data into the JSON structure needed by QuickChart. On Generate Chart (QuickChart Node): 📈 GENERATING VISUAL REPORT 📈 Creates the actual chart image based on your spending data. You can customize chart type (bar, pie, etc.) here. On Send Chart Image to Group or Private Chat: 📤 SENDING REPORT TO TELEGRAM 📤 Delivers the generated chart to your chosen Telegram chat/group. Set the correct Chat ID and Bot API token. General Sticky Note (Place where relevant): 🔑 CREDENTIALS NEEDED 🔑 Remember to set up API keys/tokens for: Telegram Google Gemini Notion General Sticky Note (Place where relevant): 💡 CUSTOMIZE ME! 💡 Adjust AI prompts for better accuracy. Change Notion database structure. Modify report frequency and content.
By Rizqi Pratama RamadhaniRespond to inbound leads with personalized videos using Heygen AI and GPT-4
🎥 AI-Powered Inbound Sales Rep Video Agent – Auto-Respond to Leads with Personalized Videos Description: This workflow helps you instantly respond to inbound leads with a hyper-personalized video and email—fully automated using n8n, Heygen API, and OpenAI. Watch the step-by-step Tutorial Build here: https://www.youtube.com/@Automatewithmarc When a visitor submits a form on your website, this AI agent dynamically: Creates a video script tailored to the lead's input using an AI prompt agent Generates a video using the Heygen API with a branded avatar Crafts a contextual follow-up email embedding the video Sends it to the lead’s inbox with a call-to-action This is ideal for: Marketing agencies looking to impress new prospects Sales teams aiming to boost inbound conversions Founders and freelancers building trust through instant video touchpoints 📥 How It Works: Form Trigger Captures user inputs like name, email, business URL, and marketing pain points. AI Video Prompt Agent Uses LangChain + OpenAI to write a short, personalized script (e.g., “Hey this is Jason from Purple Unicorn Marketing...”). Video Generation (Heygen API) Triggers a video using a selected avatar and voice style. Video Status & Wait Logic Monitors the video generation status until completed. Get Final Video URL & Thumbnail Retrieves the finished video and prepares for embedding. Email Writer (GPT-4) Generates an HTML-based outreach email including the lead's info and embedded video thumbnail with a booking link. Email Delivery (Gmail Node) Sends the full message to the inbound lead automatically. ⚙️ Tools & Integrations: n8n (self-hosted or cloud) Heygen API – for video generation LangChain + OpenAI GPT-4 – for script writing and email creation Gmail Node – for automated outreach delivery 🔧 Setup Instructions: Heygen API Key Create a Heygen account and retrieve your API key. Set it up as a credential in n8n (httpHeaderAuth). OpenAI Key Add your OpenAI API key under OpenAI credentials. Gmail OAuth2 Connect your Gmail account using OAuth2 for sending emails. Customize the Prompt Modify the system message in the LangChain Agent node to reflect your brand tone or CTA. Calendly Link Update the call-to-action links in both the video prompt and email generator nodes with your real booking URL. 💡 Use Cases: Automating welcome sequences for new signups Personalized video lead responses for agencies AI-driven inbound sales agent for bootstrapped startups
By Automate With MarcAutomate email marketing campaigns with NocoDB & Brevo
Description🔍 This n8n workflow is a complete marketing automation system that connects to your CDP (Customer Data Platform), selects which flows to send, and delivers personalized emails using Brevo. It's modular and extensible — you can also add SMS, push notifications, Telegram messages, or other channels. To build a full marketing automation system, you need four key components: Workflow Automation – using n8n (this workflow) CDP – store and manage user data (e.g., NocoDB, Metabase, Power BI, etc.) Database – track transactions, templates, and send statuses (e.g., NocoDB) BI / Analytics – monitor performance by flows, journeys, and sent events This workflow represents the Workflow Automation layer. You can connect it to your own data stack or use the included example databases (cdp-ecrm, n8n-templates-ecrm, and n8n-transaction-ecrm) to get started quickly. 👤 Who’s it for? Growth & CRM teams managing user engagement flows Ecommerce marketers running time-sensitive email journeys Marketing automation pros using low-code CRM stacks Data teams building custom campaign triggers from CDPs ✅ Features 🔁 Two modular flows: "Insert user_id" and "Sending Email" 🧠 Select flow using flow_id from templates in NocoDB ✏️ Insert user data into n8n-transaction-ecrm with processing status 🔍 Filter duplicate users by user_id to avoid over-sending 📧 Validate email fields and flag disposables 📨 Send personalized emails using Brevo template parameters 📊 Track delivery with sentresult, sentat, and status updates 🕒 Runs every 30 minutes via schedule trigger 🛠 How to Use Set your flow In the Setup Flow node, change the flow_id to match a row in your n8n-templates-ecrm table. Prepare your tables in NocoDB cdp-ecrm: contains users (userid, email, firstname, phone_number) n8n-templates-ecrm: contains flows with metadata n8n-transaction-ecrm: stores and updates user send status Configure credentials NocoDB API Token Brevo (Sendinblue) API Key Trigger the flows Run “Insert user_id” manually or on a schedule to prepare users “Sending Email” runs automatically every 30 minutes 📌 Notes Disposable email domains are filtered using regex Status: 0-processing → just inserted 1-sending → ready to send 2-sent → email sent successfully 3-no-email → missing email address 4-disposal-email → disposable or banned email Easily duplicate the "Insert user_id" flow to add more campaigns
By Nima SalimiGenerate and auto-publish LinkedIn posts with GPT-4 text and AI images
How it works This workflow automates LinkedIn posting for businesses and personal brands. It starts with a form where you submit your post idea. Then: Message Model (OpenAI) generates the LinkedIn post text in a professional and engaging style. Image Generation (OpenAI) creates a custom visual to match the post idea and brand style. LinkedIn Node publishes the text + image directly to your LinkedIn account. This way, you can go from idea → AI-written post → branded visual → live LinkedIn content, all in one automated flow. Setup steps Connect your Form Trigger (or replace with Google Forms/Typeform/Notion etc. if you prefer). Configure OpenAI credentials for text and image generation. Adjust the AI prompts with your own details: [business name], [founder name], [brand colors], [tone of voice]. Connect your LinkedIn account in the final node. Requirements OpenAI API key (for text + image generation) LinkedIn account with API access n8n instance (self-hosted or cloud)
By RodrigoFinancial reporting AI: concise SEC 10-K/10-Q briefs via OpenRouter + Perplexity
Why skim 10-K/10-Q by hand when AI can extract what matters in minutes? Who is this for? Sales engineers, solution architects, founders, product/strategy teams, analysts, and BD reps who need fast, consistent briefs on public companies—plus a mapping to a chosen vendor’s solutions. Use case Problem: SEC filings are dense. Manually summarizing financials, spotting initiatives, and aligning them to a vendor’s offerings is slow, error-prone, and often missed by busy teams. Use Case: An n8n workflow that takes a company name / URL / ticker, analyzes the latest 10-Q/10-K with Perplexity “Deep Research” (via OpenRouter), extracts a concise financial overview and top 4–5 initiatives (tech, cost, revenue), then maps them to one vendor’s solutions (e.g., Microsoft, Google, T-Mobile) and outputs a clean brief. What this workflow does Trigger: “When chat message received” (or webhook) accepts name / URL / ticker + target vendor. AI Agent: Chat Model (OpenRouter) orchestrates the prompt and formatting. Tool: Perplexity Deep Research performs retrieval over the latest 10-K/10-Q and recent references. Output: Creates a Google Drive document from the generated text (title, summary, initiatives, vendor-solution matches, suggested contacts). (Optional) Append a row to Google Sheets for tracking companies, initiatives, and match scores. Prerequisites n8n (Cloud or self-hosted). Credentials in n8n: OpenRouter API key (with access to Perplexity’s Deep Research model). Google Drive (and Google Sheets, if you add the sheet step). Setup Import the workflow JSON into n8n. Open Credentials → connect OpenRouter and Google Drive. In the AI Agent node: Set Chat Model to your OpenRouter model. Set Tool to Perplexity’s Deep Research endpoint. Paste the provided prompt that(example): Summarize the key financial highlights and list the key strategic initiatives from Office Depot's most recent quarterly report. The company's URL is https://www.officedepot.com and its stock symbol is ODP. After gathering this information, compare Office Depot's initiatives with the solutions offered by T-Mobile for Business (URL: https://www.t-mobile.com/business, stock symbol: TMUS). Finally, provide specific recommendations on T-Mobile solutions that can help Office Depot achieve its initiatives. Explain how each recommended solution would help. Present the final response with clear headings for each section. How to customize it for your needs Ticker/Name disambiguation: Add a guardrail step that confirms the exchange + CIK before analysis. EDGAR fetch (advanced): Pull the exact 10-K/10-Q document/link and pass it to the model for grounded citations. Multi-vendor mapping: Loop over a list (e.g., Microsoft, Google Cloud, AWS) and produce a comparison table. Contact enrichment: Add your preferred enrichment step to suggest roles (IT, Network, Data, Finance). Scoring: Compute initiative ↔ solution fit scores and prioritize must-explore actions. Alerts: Send the brief to Slack/Telegram/Email for your team. Troubleshooting Wrong company matched? Add a pre-check that resolves ticker → legal name and require confirmation. Generic web summary? Tighten the prompt: “Use the latest 10-Q/10-K; cite sections; list initiatives with evidence.” Empty Drive file? Verify the AI Agent’s {{$json}} mappings flow into the Drive node’s content. No citations? Require bullet-level references; if missing, loop once with a “citations-only” follow-up prompt. Why Use This Template? Turn hours of filing review into a repeatable, shareable brief. You’ll get: A clean financial snapshot, The company’s top initiatives, A vendor-aligned solution map you can act on immediately—great for prospecting, QBRs, and strategic planning. Expected Outcome: Need Assistance? For setup guidance, customization, or business inquiries, Email: phoenixaiagentsolutions@gmail.com
By Ashish Kumar Swain