Multi-platform AI sales agent with RAG, CRM logging & appointment booking
Multi-Platform AI Sales Agent with RAG, CRM Logging & Appointment Booking This workflow acts as a 24/7 sales agent, engaging leads across WhatsApp, Instagram, Facebook, Telegram, and your website. It intelligently transcribes audio messages, answers questions using a knowledge base, and uses modular sub-workflows to manage your CRM in Airtable and book appointments in Google Calendar. --- Who Is It For? This solution is designed for service-based businesses that require a sophisticated, multi-channel lead management and appointment booking system. Agencies, consultants, and clinics looking to automate lead qualification and booking across text and voice messages. Sales teams needing a robust system that separates CRM and calendar logic for easier management and scalability. Advanced n8n users who want a powerful, agent-based framework that can be easily customized and extended. --- Key Features & Workflow This system is composed of a parent workflow that orchestrates the conversation and calls specialized sub-workflows (agents) to perform specific tasks. Omni-Channel Engagement: Greets and converses with leads naturally on Website Chat, WhatsApp, Instagram, Facebook, and Telegram. Voice Message Transcription: Automatically transcribes incoming audio/voice notes from WhatsApp and Telegram into text, allowing the AI to understand and respond without manual intervention. RAG-Powered Intelligence: The AI agent draws answers from your dedicated PostgreSQL Knowledge Base (RAG), providing accurate information about your services, pricing, and process. A built-in tool allows you to load new knowledge documents from Google Drive. Modular CRM Agent (Sub-Workflow): When the conversation requires CRM actions (like creating a contact or updating an opportunity), the main agent calls a dedicated Airtable CRM sub-workflow to handle the task. Modular Calendar Agent (Sub-Workflow): To book appointments, the main agent calls a separate Google Calendar sub-workflow, which manages event creation, updates, and deletions. --- What You'll Need This workflow framework requires credentials for the following services: An AI provider (OpenAI is used for the main agent, transcription, and embeddings). PostgreSQL database with the pgvector extension (for RAG and chat memory). Airtable account (for the CRM sub-workflow). Google Calendar account (for the Calendar sub-workflow). Telegram Bot credentials. A Meta Developer Account (for WhatsApp, Instagram & Facebook). (Optional) Google Drive for loading knowledge documents. (Optional) Google Gemini for embeddings. --- How to Set It Up This is a modular system. You must set up the sub-workflows first. Deploy Sub-Workflows: Create two new, separate workflows using the provided templates for the CRM Agent and the Calendar Agent. Configure the credentials (Airtable, Google Calendar) within those workflows, then save and activate them. Link Sub-Workflows in Main Workflow: Return to this main workflow. In the "CRM Agent" and "Consultation Agent" tool nodes, select the new workflows you just created from the dropdown list. Configure Main Credentials: Securely add the remaining credentials (OpenAI, PostgreSQL, Telegram, and your Meta App) in this main workflow. Personalize the AI Agent: In the "Update Agent Details" node, fill in your business name, the agent's persona name, and your key services to customize the AI's personality. Load Your Knowledge (Optional): To populate the RAG database, use the manual trigger path starting with "When clicking ‘Execute workflow’" to download a document from Google Drive and insert it into your PostgreSQL vector store. Activate: Configure your channel-specific details (e.g., Phone Number ID in WhatsApp nodes), save the workflow, and activate it. --- Demo CRM Table: View on Airtable
By Vansh AroraExtract and save invoice data from Google Drive to Sheets with Dumpling AI
Who is this for? This workflow is perfect for operations teams, accountants, e-commerce businesses, or finance managers who regularly process digital invoices and need to automate data extraction and record-keeping. --- What problem is this workflow solving? Manually reading invoice PDFs, extracting relevant data, and entering it into spreadsheets is time-consuming and error-prone. This workflow automates that process—watching a Google Drive folder, extracting structured invoice data using Dumpling AI, and saving the results into Google Sheets. --- What this workflow does Watches a specific Google Drive folder for new invoices. Downloads the uploaded invoice file. Converts the file into a Base64 format. Sends the file to Dumpling AI’s extract-document endpoint with a detailed parsing prompt. Parses Dumpling AI’s JSON response using a Code node. Splits the items array into individual rows using the Split Out node. Appends each invoice item to a preformatted Google Sheet along with the full header metadata (order number, PO, addresses, etc.). --- Setup Google Drive Setup Create or select a folder in Google Drive and place the folder ID in the trigger node. Make sure your n8n Google Drive credentials are authorized for access. Google Sheets Create a Google Sheet with the following headers: Order number, Document Date, Po_number, Sold to name, Sold to address, Ship to name, Ship to address, Model, Description, Quantity, Unity price, Total price Paste the Sheet ID and sheet name (Sheet1) into the Google Sheets node. Dumpling AI Sign up at Dumpling AI Go to your account settings and generate your API key. Paste this key into the HTTP header of the Dumpling AI request node. The endpoint used is: https://app.dumplingai.com/api/v1/extract-document Prompt (already included) This prompt extracts: order number, document date, PO number, shipping/billing details, and detailed line items (model, quantity, unit price, total). --- How to customize this workflow to your needs Adjust the Google Sheet fields to fit your invoice structure. Modify the Dumpling AI prompt if your invoices have additional or different data points. Add filtering logic if you want to handle different invoice types differently. Replace Google Sheets with Airtable or a database if preferred. Use a different trigger like an email attachment if invoices come via email. ---
By YangAutomate email management with OpenAI classification, Gmail drafts & Slack alerts
What it does This workflow automatically processes incoming emails with intelligent AI classification, creating draft responses and sending Slack notifications based on email content. How it works Monitors emails with the 'AI-Agent' label AI classification into categories: Inquiry, Support, Newsletter, Action Item Adds appropriate labels to emails automatically Creates draft replies for Support and Inquiry emails Sends Slack notifications for Action Items and Newsletter summaries Setup Requirements Gmail OAuth2 credentials configured OpenAI API credentials (or other AI provider) Slack OAuth2 credentials (if notifications desired) Gmail labels created (see setup instructions below) How to customize Modify classification categories in the AI Agent Adjust label mappings in the Parse Classification node Customize draft response templates Configure different Slack channels for different email types
By Fabian ZNTLAi-powered multi-stage web search and research suite
Description: The closest definition to this workflow is a cheaper Modular Version of Perplexity online API empowered by LLM models that outperform the Perplexity Lama Model. This flow provides a seamless way to conduct detailed web searches, extract data, and generate insightful reports based on real-time information. It provides a webhook-based flow that gets any search question and reports back the results via a multi-level web search analysis and domain-specific emulation of an agent to deliver an unbiased expert report. This Flow is Ideal for market research, competitive analysis, or any scenario where actionable, structured insights are needed. A more complete, step-by-step guide is provided within the workflow, ensuring you have all the details to set up and customize each component. This tool is designed to function similarly to Perplexity by performing semantic search, reranking, and follow-up queries. However, it offers a unique advantage—complete customization at every stage. Modify any part of the process, from query refinement to data extraction, allowing you to tailor the workflow to your specific needs. Key Features: AI-Powered Query Generation and Expert Emulation: Uses Google Gemini to transform user queries into expert-level searches, providing accurate and context-aware results. Dual-Stage Semantic Search with Intelligent Reranking: Performs an initial search, reranks results, and refines the query based on findings to conduct a second, more targeted search. Top-Result Data Extraction: Extracts content from the top three results of each search, capturing relevant insights from six total sources. Customizable API Options: Pre-configured with free APIs (Google Gemini, DuckDuckGo, and Article Extraction APIs) but easily adaptable to other APIs if preferred. Automated, Insightful Reporting: Synthesizes data into a cohesive report, providing expert-level insights tailored to the user’s query. Instructions for API Setup: This workflow is designed to work with free-tier APIs, offering a cost-effective way to retrieve high-quality data. Here’s how to set up each API, with detailed instructions included in the workflow: Google Gemini API (for Query Generation and Analysis): Visit Google AI Studio and log in. Create a free API key under "Get API Key" → "Create API Key in New Project." The free tier includes up to 15 requests per minute, 1 million tokens per minute, and up to 1,500 requests per day. Brave Search API (for Web Search): To attain the free web search API tier from Brave, follow these steps: Visit api.search.brave.com Create an account Subscribe to the free plan (no charge) Navigate to the API Keys section Generate an API key. For the subscription type, choose "Free". Article Extraction API (for Content Extraction): Register on RapidAPI.com and subscribe to the Article Extraction API. The free plan allows up to 300 extractions per month. Enter your API key in each of the 6 extraction nodes for content retrieval. Alternative: In the workflow, we have provided the full instructions on how to replace the current flow with alternative API Keys and provided suggestions such as Scraper Tech API. Additional Tip: To use other APIs, you can generate a cURL request in RapidAPI’s playground, and then paste it into the HTTP Request node in n8n. This approach streamlines integration by automatically filling in headers and request details. Why Choose This Workflow? The Intelligent Online Web Researcher offers an all-in-one solution for complex, customizable online research. Unlike other tools that provide automated semantic search, this workflow is fully modifiable, allowing you to tailor each step, from the initial query and reranking to data extraction and reporting. With built-in instructions and a structure that’s easy to adapt, it’s ideal for commercial applications that require real-time, high-quality insights. Tags: Online Research, Web Search, Market Analysis, Web Search Automation, Data Extraction, Semantic Search, API Integration, Competitive Intelligence, Business Intelligence, Real-Time Reporting, Web Scrape, Data Crawler, Perplexity
By Mind-Front