by Milan Vasarhelyi - SmoothWork
Video Introduction Want to automate your inbox or need a custom workflow? π Book a Call | π¬ DM me on Linkedin What This Workflow Does This workflow creates an AI-powered chatbot that answers natural language questions about your QuickBooks data in real-time. Users can interact with a public chat interface to query customer information, balances, invoices, and other accounting data without needing to navigate the QuickBooks interface directly. The AI agent uses OpenAI's language model to understand questions and automatically retrieves the relevant data from QuickBooks. Key Features Natural Language Interface**: Ask questions like "How many customers do we have?" or "What's the total balance across all customers?" and get instant answers Public Chat URL**: Share a link with team members or stakeholders so they can access QuickBooks insights without direct system access Customizable Data Access**: Configure the QuickBooks tool to retrieve different resources (customers, invoices, expenses, bills, etc.) based on your needs Common Use Cases Enable non-accounting staff to get quick answers about customer data Provide executives with on-demand financial insights without training them on QuickBooks Create a self-service interface for sales teams to check customer balances Build internal support bots that can answer accounting questions Setup Requirements QuickBooks Developer Account: Register at developer.intuit.com and create a new app with Accounting permissions Credentials: Configure QuickBooks OAuth2 API credentials (Client ID, Client Secret, and Redirect URI from the Intuit Developer dashboard) and OpenAI API credentials Environment: Start with Sandbox mode for testing, then switch to Production after getting your app approved by Intuit Tool Configuration: The QuickBooks tool is pre-configured to retrieve all customer data, but you can modify the operation and filters to access different QuickBooks resources based on your requirements
by Rodrigo
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 β AI-written post β branded visual β 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 AI/ML API | D1m7asis
π¬ GPT-5 Powered Telegram Bot β AI/ML API + n8n This n8n workflow lets users chat with GPT-5 directly in Telegram. It simulates typing for a natural UX, sends messages to GPT-5 via AI/ML API, and replies back in the same chat. Optionally, each interaction can be logged in Google Sheets. π Features π© Telegram-based chat input π¬ Typing indicator before reply π§ High-quality AI responses via openai/gpt-5-chat-latest (AI/ML API) π€ Replies sent back in Telegram with formatting π Optional logging to Google Sheets π Secure credential handling in n8n π Setup Guide 1. π² Create Telegram Bot Open @BotFather Use /newbot, choose name + username Save the API token 2. π Set Up Credentials in n8n Telegram API: paste the BotFather token AI/ML API: create a key from aimlapi.com (Optional) Google Sheets: connect via OAuth2/Service Account 3. π Prepare Google Sheet (optional logging) Name: e.g., GPT5 Bot Logs Sheet: Sheet1 Columns: user_id | date | query | response 4. π§ Configure Workflow Import the JSON into n8n Attach your credentials to the Telegram + AI/ML API nodes (Optional) update Google Sheets node with Sheet ID βοΈ Flow Summary | Node | Function | | ------------------------------- | -------------------------------------- | | π© Receive Telegram Message | Trigger on user message | | π¬ Simulate Typing | Sends "typingβ¦" action to Telegram | | π§ Process with GPT-5 | Calls AI/ML API with message text | | π€ Send Response to Telegram | Replies back to user with model output | | π Log Interaction (optional) | Appends log row to Google Sheets | π‘ Example User Flow User sends: Whatβs the capital of Japan? Bot replies after "typingβ¦": The capital of Japan is Tokyo. Conversation continues naturally. π§ͺ Testing Use a test chat with your bot Trigger via /execute workflow (not βExecute Nodeβ) Add Set or Console nodes for debugging π Resources π AI/ML API Docs π€ GPT-5 Models
by System Admin
No description available
by System Admin
Tagged with: , , , ,
by System Admin
No description available
by System Admin
No description available
by System Admin
No description available
by System Admin
No description available
by System Admin
No description available
by System Admin
Tagged with: , , , ,
by System Admin
No description available