Course WhatsApp Copy

An AI-powered WhatsApp chatbot that delivers structured educational content through conversational interactions. This workflow processes incoming WhatsApp messages (text and audio), transcribes voice messages, and provides personalized course instruction using OpenAI's language models with memory persistence.

Purpose

No business context provided yet — add a context.md to enrich this documentation.

How It Works

1. Message Reception: Receives WhatsApp messages via Twilio webhook, supporting both text and audio formats
2. Message Processing: Routes messages based on type - audio messages are downloaded and transcribed using OpenAI's Whisper, while text messages are processed directly
3. Content Preparation: Normalizes all messages into a standard text format for the AI agent
4. Reset Detection: Checks if the user sent "reset" to clear conversation memory
5. AI Instruction: Uses an OpenAI-powered agent with conversation memory to provide educational guidance, accessing course content through a specialized tool
6. Response Delivery: Sends the AI's response back to the user via WhatsApp

The workflow also includes a separate process that periodically downloads and processes course content from Google Drive, parsing PDF files into structured lesson formats.

Mermaid Diagram

graph TD
    A[Webhook] --> B[Switch]
    B -->|audio| C[HTTP Request]
    B -->|text| D[Edit Fields1]
    C --> E[Transcribe a recording]
    E --> F[Edit Fields]
    F --> G[Edit Fields2]
    D --> G
    G --> H[If]
    G --> I[Main agent]
    H -->|reset| J[Delete Messages1]
    I --> K[Send an SMS/MMS/WhatsApp message]
    L[OpenAI Chat Model] -.->|language model| I
    M[Simple Memory] -.->|memory| I
    N[Leadership_course_agent] -.->|tool| I
    O[Schedule Trigger] --> P[HTTP Request1]
    P --> Q[Extract from File]
    Q --> R[Code]
    S[When clicking 'Execute workflow'] --> T[Delete Messages]
    T --> U[insert Messages1]
    M -.->|memory| T
    M -.->|memory| U
    M -.->|memory| J

Trigger

• Primary: Webhook endpoint that receives POST requests from Twilio when WhatsApp messages are sent to the configured number
• Secondary: Schedule trigger for periodic course content updates
• Manual: Manual trigger for testing memory management functions

Nodes Used

Node Type	Purpose
Webhook	Receives incoming WhatsApp messages from Twilio
Switch	Routes messages based on type (audio vs text)
HTTP Request	Downloads audio files and course content
OpenAI (Transcribe)	Converts audio messages to text using Whisper
Edit Fields	Normalizes message data into consistent format
If	Checks for reset command to clear memory
AI Agent	Main conversational AI powered by OpenAI
OpenAI Chat Model	Language model for generating responses
Memory (Buffer Window)	Maintains conversation context per user
Tool Workflow	Accesses course content through external workflow
Twilio	Sends WhatsApp responses back to users
Extract from File	Parses PDF course content
Code	Processes and structures lesson data
Memory Manager	Manages conversation memory (delete/insert)

External Services & Credentials Required

Twilio

• Purpose: WhatsApp message handling (receive and send)
• Credentials:
  • Account SID
  • Auth Token
  • WhatsApp-enabled phone number
• Used in: Webhook reception and message sending

OpenAI

• Purpose: Audio transcription and conversational AI
• Credentials:
  • API Key with access to Whisper and GPT models
• Used in: Audio transcription and chat responses

Google Drive

• Purpose: Course content storage and retrieval
• Requirements: Public access to course PDF files
• Used in: Periodic content updates

Environment Variables

No explicit environment variables are defined in this workflow. All configuration is handled through n8n credentials and node parameters.

Data Flow

Input

• WhatsApp Messages: Text or audio messages from users
• Message Metadata: Sender ID, message type, timestamps
• Audio Files: Voice messages in supported formats

Processing

• Text Extraction: Audio transcription or direct text processing
• Context Management: User-specific conversation memory
• Course Content: Structured lesson data from PDF files

Output

• WhatsApp Responses: Educational content and interactive guidance
• Memory Updates: Persistent conversation context
• Structured Lessons: Parsed course content for agent use

Error Handling

The workflow includes basic error handling through: - Message Type Routing: Graceful handling of different message formats - Conditional Processing: Reset command detection and memory management - Tool Integration: Fallback behavior when course content is unavailable

No explicit error nodes are present, so errors would follow n8n's default error handling behavior.

Known Limitations

• Audio transcription depends on OpenAI service availability
• Course content updates require manual PDF uploads to Google Drive
• Memory is limited to 15 message window per user
• No explicit error recovery for failed API calls
• Workflow is currently inactive (active: false)

Related Workflows

• CourseContentAgent (ID: I32PCLSspW3b6umC): Provides structured course content and lesson management

Setup Instructions

1. Import Workflow: Import the JSON into your n8n instance

2. Configure Credentials:

   • Set up Twilio API credentials with WhatsApp capabilities
   • Configure OpenAI API credentials with GPT and Whisper access
   • Ensure HTTP Basic Auth for Twilio media downloads

3. Set Up Webhook:

   • Note the webhook URL from the Webhook node
   • Configure Twilio WhatsApp webhook to point to this URL

4. Configure Course Content:

   • Upload course PDF to Google Drive with public access
   • Update the Google Drive URL in the HTTP Request1 node
   • Ensure the CourseContentAgent workflow is available

5. Test Setup:

   • Use the manual trigger to test memory management
   • Send test messages to your WhatsApp number
   • Verify audio transcription and text responses

6. Activate Workflow: Set the workflow to active to begin processing messages

7. Monitor Performance: Check execution logs for any credential or API issues