AI sales agent: WhatsApp, FB, IG, OpenAI, Airtable, Supabase auto-booking

7637 views

2/3/2026

Vision AI Slack Automation Image Analysis Google Gemini

This workflow automates multi-channel AI-driven sales engagement for lead qualification, service information delivery, and consultation booking. It integrates WhatsApp, Facebook Messenger, Instagram DM, and an n8n chat interface with a backend CRM (Airtable), a knowledge base (Supabase), and conversational AI (OpenAI), all orchestrated by n8n.

Tools & Services Used

Messaging Platforms: WhatsApp, Facebook Messenger, Instagram DM, n8n Built-in Chat

AI Core & Processing: OpenAI (GPT-4o for main agent logic, Whisper for audio transcription)

CRM & Data Management: Airtable (for initial WhatsApp lead lookup, lead form submissions, and as the backend for the crmAgent sub-workflow operations)

Knowledge Base: Supabase (Vector Store for technical_and_sales_knowledge tool)

Chat Memory: PostgreSQL (for the main AI Agent's conversation history)

Orchestration & Automation: n8n (Self-hosted, utilizing Langchain community nodes)

Calendar Service: Integrated via the calendarAgent sub-workflow

CRM Service: Integrated via the crmAgent sub-workflow (interacting with Airtable)

Workflow Overview

This automation performs the following steps:

Trigger: A new interaction is initiated through one of the following channels:

A new message is received via the WhatsApp Trigger.

A new message is received via the Facebook Trigger (Webhook).

A new message is received via the Instagram Trigger (Webhook).

A new message is received via the n8n Chat Trigger.

Alternatively, a new lead is submitted via the Airtable Form Submitted Webhook.

Channel-Specific Ingestion & Pre-processing:

For WhatsApp:

The system attempts to find an existing lead in Airtable using the sender's phone number.

Incoming messages are routed by the Handle Message Types switch:

Text messages are passed to the Edit Fields - chat1 node to prepare input for the AI Agent, including any found lead information.

Audio messages are processed: the WhatsApp Business Cloud node gets the media URL, the HTTP Request node downloads the audio, OpenAI transcribes it to text, and Edit Fields - chat2 prepares this transcribed text and lead information for the AI Agent.

Unsupported message types trigger the Reply To User1 node to send a notification that the message type cannot be processed.

For Facebook Messenger:

The system responds to webhook verification (Respond to Webhook - facebook get) and acknowledges new messages (Respond to Webhook - facebook post).

The If is not echo - facebook node filters out messages sent by the page.

The Sales Agent Demo - typing_on node sends a typing indicator.

The Edit Fields - facebook node prepares the message text, sender ID, and Facebook-specific context for the AI Agent.

For Instagram DM:

The system responds to webhook verification (Respond to Webhook - instagram get) and acknowledges new messages (Respond to Webhook - instagram post).

The If is not echo - instagram node filters out messages sent by the business account.

The Edit Fields - instagram node prepares the message text, sender ID, and Instagram-specific context for the AI Agent.

For n8n Chat:

The Edit Fields - chat node prepares the user's input and session information for the AI Agent.

Input Aggregation for AI Agent:

Processed data from all active messaging channels (WhatsApp text/audio, Facebook, Instagram, n8n Chat) is funneled through the No Operation, do nothing node to the main AI Agent.

AI Sales Conversation & Tool Utilization:

The AI Agent (using OpenAI Chat Model - GPT-4o, and Postgres Chat Memory) engages the user according to its system prompt, aiming to qualify them for Paint Protection Film (PPF), Ceramic Coating, or Window Tint.

The AI Agent uses the technical_and_sales_knowledge tool (which queries the Demo Supabase vector store via Embeddings OpenAI and OpenAI Chat Model1) to provide service details and answer questions.

The AI Agent uses the crmAgent tool (a sub-workflow) to log contact details (Name, Email, service interest) and update opportunity statuses in Airtable.

The AI Agent uses the calendarAgent tool (a sub-workflow) to book consultation appointments once preferred dates/times are provided. This occurs after contact details are logged in the CRM.

Response Delivery:

The AI Agent's final textual response is passed to the Switch node.

The Switch node routes the response to the appropriate node for delivery on the original channel:

Reply To User for WhatsApp.

Facebook Graph API - Sales Agent Demo for Facebook Messenger.

Instagram Graph API - smb.sales.agent.demo for Instagram DM.

Output - chat for the n8n Chat interface.

Airtable Form Submission Processing (Separate Branch):

When the Airtable Form Submitted webhook receives data, the Airtable node fetches the full record.

The Create Contact node creates a new contact in the Airtable 'Contacts' table.

The Edit Fields - form node prepares data for a notification.

The WhatsApp Business Cloud2 node sends a templated WhatsApp message to the lead, confirming their form submission.

AI Sales Agent for WhatsApp, Facebook, Instagram with OpenAI, Airtable, Supabase, and Auto-Booking

This n8n workflow creates a sophisticated AI sales agent that can interact with customers across multiple messaging platforms (WhatsApp, Facebook, Instagram), leverage AI for intelligent responses, store data in Airtable and Supabase, and potentially facilitate auto-booking. It acts as a central hub for managing customer conversations and automating sales processes.

What it does

This workflow automates the following key steps:

Receives Chat Messages: Listens for incoming chat messages from various platforms (WhatsApp, Facebook, Instagram) via a central Chat Trigger.
Processes Messages with AI Agent: Routes the received message to an AI Agent powered by OpenAI's chat model.
Manages Conversational Memory: Utilizes Postgres Chat Memory to maintain context and history for ongoing conversations, allowing the AI to provide more relevant responses.
Accesses External Knowledge: Employs a Supabase Vector Store and an Answer questions with a vector store tool to provide the AI agent with access to a knowledge base for answering specific queries.
Performs Actions via n8n Workflows: The AI Agent can call other n8n workflows (via the Call n8n Workflow Tool) to perform specific actions, such as:
- Updating Airtable: Interacts with Airtable, likely to log conversations, update customer information, or manage booking details.
- Making HTTP Requests: Executes custom API calls, which could be used for integrating with booking systems, CRM, or other services.
- Sending WhatsApp Messages: Responds to customers directly on WhatsApp using the WhatsApp Business Cloud node.
- Sending Facebook/Instagram Messages: Responds to customers on Facebook or Instagram via the Facebook Graph API node.
Conditional Logic: Uses If and Switch nodes to implement conditional logic, allowing the workflow to branch based on message content, AI decisions, or other criteria.
Responds to Webhooks: The Respond to Webhook node is likely used to acknowledge receipt of messages or send final responses back to the originating platform if not handled directly by a messaging node.
Data Transformation: The Edit Fields (Set) node is used to manipulate and format data as it flows through the workflow.

Prerequisites/Requirements

To use this workflow, you will need accounts and API keys for the following services:

n8n: Your n8n instance (self-hosted or cloud).
WhatsApp Business Cloud API: For sending and receiving WhatsApp messages.
Facebook Graph API: For sending and receiving Facebook Messenger and Instagram messages.
OpenAI API Key: For the OpenAI Chat Model and Embeddings OpenAI (used by the AI Agent).
Airtable Account: For data storage and management.
Supabase Account: For the Supabase Vector Store and Postgres Chat Memory. You'll need a PostgreSQL database configured for chat memory and a vector store for knowledge retrieval.

Setup/Usage

Import the Workflow: Download the JSON content and import it into your n8n instance.
Configure Credentials:
- Set up credentials for WhatsApp Business Cloud, Facebook Graph API, OpenAI, Airtable, and Supabase within n8n.
Configure Trigger Nodes:
- Chat Trigger: Configure this node to listen for messages from your desired platforms (WhatsApp, Facebook, Instagram). This might involve setting up webhooks in your messaging platform accounts to point to n8n.
- WhatsApp Trigger: Ensure this is correctly configured to receive incoming WhatsApp messages.
Configure AI Agent:
- AI Agent: Configure the AI Agent node with your OpenAI credentials and specify the language model to use (e.g., OpenAI Chat Model).
- Postgres Chat Memory: Configure this node to connect to your Supabase PostgreSQL database for storing chat history.
- Supabase Vector Store: Configure this node to connect to your Supabase instance and point to your vector store table for knowledge retrieval.
- Call n8n Workflow Tool: If the AI agent is intended to call other n8n workflows, ensure these sub-workflows are created and properly exposed as tools for the AI agent to use.
Configure Action Nodes:
- Airtable: Configure the Airtable node with your base and table IDs for data interaction.
- HTTP Request: Adjust the URLs, headers, and body for any external API calls.
- WhatsApp Business Cloud / Facebook Graph API: Ensure these nodes are configured to send messages back to the correct recipients.
Activate the Workflow: Once all credentials and nodes are configured, activate the workflow to start processing messages.

This workflow provides a robust framework for building an interactive AI sales agent. You will likely need to customize the AI agent's prompt, the tools it can use, and the specific logic within the If and Switch nodes to match your exact sales processes and customer interaction requirements.

Related Templates

Track competitor SEO keywords with Decodo + GPT-4.1-mini + Google Sheets

This workflow automates competitor keyword research using OpenAI LLM and Decodo for intelligent web scraping. Who this is for SEO specialists, content strategists, and growth marketers who want to automate keyword research and competitive intelligence. Marketing analysts managing multiple clients or websites who need consistent SEO tracking without manual data pulls. Agencies or automation engineers using Google Sheets as an SEO data dashboard for keyword monitoring and reporting. What problem this workflow solves Tracking competitor keywords manually is slow and inconsistent. Most SEO tools provide limited API access or lack contextual keyword analysis. This workflow solves that by: Automatically scraping any competitor’s webpage with Decodo. Using OpenAI GPT-4.1-mini to interpret keyword intent, density, and semantic focus. Storing structured keyword insights directly in Google Sheets for ongoing tracking and trend analysis. What this workflow does Trigger — Manually start the workflow or schedule it to run periodically. Input Setup — Define the website URL and target country (e.g., https://dev.to, france). Data Scraping (Decodo) — Fetch competitor web content and metadata. Keyword Analysis (OpenAI GPT-4.1-mini) Extract primary and secondary keywords. Identify focus topics and semantic entities. Generate a keyword density summary and SEO strength score. Recommend optimization and internal linking opportunities. Data Structuring — Clean and convert GPT output into JSON format. Data Storage (Google Sheets) — Append structured keyword data to a Google Sheet for long-term tracking. Setup Prerequisites If you are new to Decode, please signup on this link visit.decodo.com n8n account with workflow editor access Decodo API credentials OpenAI API key Google Sheets account connected via OAuth2 Make sure to install the Decodo Community node. Create a Google Sheet Add columns for: primarykeywords, seostrengthscore, keyworddensity_summary, etc. Share with your n8n Google account. Connect Credentials Add credentials for: Decodo API credentials - You need to register, login and obtain the Basic Authentication Token via Decodo Dashboard OpenAI API (for GPT-4o-mini) Google Sheets OAuth2 Configure Input Fields Edit the “Set Input Fields” node to set your target site and region. Run the Workflow Click Execute Workflow in n8n. View structured results in your connected Google Sheet. How to customize this workflow Track Multiple Competitors → Use a Google Sheet or CSV list of URLs; loop through them using the Split In Batches node. Add Language Detection → Add a Gemini or GPT node before keyword analysis to detect content language and adjust prompts. Enhance the SEO Report → Expand the GPT prompt to include backlink insights, metadata optimization, or readability checks. Integrate Visualization → Connect your Google Sheet to Looker Studio for SEO performance dashboards. Schedule Auto-Runs → Use the Cron Node to run weekly or monthly for competitor keyword refreshes. Summary This workflow automates competitor keyword research using: Decodo for intelligent web scraping OpenAI GPT-4.1-mini for keyword and SEO analysis Google Sheets for live tracking and reporting It’s a complete AI-powered SEO intelligence pipeline ideal for teams that want actionable insights on keyword gaps, optimization opportunities, and content focus trends, without relying on expensive SEO SaaS tools.

By Ranjan Dailata

161

Generate song lyrics and music from text prompts using OpenAI and Fal.ai Minimax

Spark your creativity instantly in any chat—turn a simple prompt like "heartbreak ballad" into original, full-length lyrics and a professional AI-generated music track, all without leaving your conversation. 📋 What This Template Does This chat-triggered workflow harnesses AI to generate detailed, genre-matched song lyrics (at least 600 characters) from user messages, then queues them for music synthesis via Fal.ai's minimax-music model. It polls asynchronously until the track is ready, delivering lyrics and audio URL back in chat. Crafts original, structured lyrics with verses, choruses, and bridges using OpenAI Submits to Fal.ai for melody, instrumentation, and vocals aligned to the style Handles long-running generations with smart looping and status checks Returns complete song package (lyrics + audio link) for seamless sharing 🔧 Prerequisites n8n account (self-hosted or cloud with chat integration enabled) OpenAI account with API access for GPT models Fal.ai account for AI music generation 🔑 Required Credentials OpenAI API Setup Go to platform.openai.com → API keys (sidebar) Click "Create new secret key" → Name it (e.g., "n8n Songwriter") Copy the key and add to n8n as "OpenAI API" credential type Test by sending a simple chat completion request Fal.ai HTTP Header Auth Setup Sign up at fal.ai → Dashboard → API Keys Generate a new API key → Copy it In n8n, create "HTTP Header Auth" credential: Name="Fal.ai", Header Name="Authorization", Header Value="Key [Your API Key]" Test with a simple GET to their queue endpoint (e.g., /status) ⚙️ Configuration Steps Import the workflow JSON into your n8n instance Assign OpenAI API credentials to the "OpenAI Chat Model" node Assign Fal.ai HTTP Header Auth to the "Generate Music Track", "Check Generation Status", and "Fetch Final Result" nodes Activate the workflow—chat trigger will appear in your n8n chat interface Test by messaging: "Create an upbeat pop song about road trips" 🎯 Use Cases Content Creators: YouTubers generating custom jingles for videos on the fly, streamlining production from idea to audio export Educators: Music teachers using chat prompts to create era-specific folk tunes for classroom discussions, fostering interactive learning Gift Personalization: Friends crafting anniversary R&B tracks from shared memories via quick chats, delivering emotional audio surprises Artist Brainstorming: Songwriters prototyping hip-hop beats in real-time during sessions, accelerating collaboration and iteration ⚠️ Troubleshooting Invalid JSON from AI Agent: Ensure the system prompt stresses valid JSON; test the agent standalone with a sample query Music Generation Fails (401/403): Verify Fal.ai API key has minimax-music access; check usage quotas in dashboard Status Polling Loops Indefinitely: Bump wait time to 45-60s for complex tracks; inspect fal.ai queue logs for bottlenecks Lyrics Under 600 Characters: Tweak agent prompt to enforce fuller structures like [V1][C][V2][B][C]; verify output length in executions

By Daniel Nkencho

601

Automate invoice processing with OCR, GPT-4 & Salesforce opportunity creation

PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive ➜ Download PDF ➜ OCR text ➜ AI normalize to JSON ➜ Upsert Buyer (Account) ➜ Create Opportunity ➜ Map Products ➜ Create OLI via Composite API ➜ Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content → the parsed JSON (ensure it’s an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id ➜ build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total ➜ per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger → Download File From Google Download File From Google → Extract from File → Update File to One Drive Extract from File → Message a model Message a model → Create or update an account Create or update an account → Create an opportunity Create an opportunity → Build SOQL Build SOQL → Query PricebookEntries Query PricebookEntries → Code in JavaScript Code in JavaScript → Create Opportunity Line Items --- Quick setup checklist 🔐 Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. 📂 IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) 🧠 AI Prompt: Use the strict system prompt; jsonOutput = true. 🧾 Field mappings: Buyer tax id/name → Account upsert fields Invoice code/date/amount → Opportunity fields Product name must equal your Product2.ProductCode in SF. ✅ Test: Drop a sample PDF → verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep “Return only a JSON array” as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields don’t support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your org’s domain or use the Salesforce node’s Bulk Upsert for simplicity.

By Le Nguyen

942