Skip to content

AudioReportsV2

An AI-powered WhatsApp assessment workflow that guides trainers through structured learner evaluations using voice notes and generates comprehensive assessment reports for skill-up program participants.

Purpose

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

This workflow appears to be designed for educational or training programs where mentors/trainers need to assess learner progress through a conversational WhatsApp interface. The system uses AI to generate assessment scenarios, collect voice feedback, and produce structured reports.

How It Works

  1. Assessment Initiation: Trainer sends "start" message to WhatsApp
  2. Scenario Generation: AI creates three learner assessment scenarios (Struggling, Progressing, Excelling)
  3. Scenario Selection: Trainer selects option A, B, or C based on their learner's situation
  4. Question Generation: AI generates targeted assessment questions based on the selected scenario
  5. Voice Response Collection: Trainer responds with voice notes containing their assessment
  6. AI Follow-up: System transcribes voice notes and asks follow-up questions if needed
  7. Report Generation: When trainer requests "generate report", AI creates a comprehensive assessment report
  8. Report Delivery: Final assessment report is sent via WhatsApp

Workflow Diagram

graph TD
    A[WhatsApp Webhook] --> B{Check Start Message}
    A --> C{Check Selection}
    A --> D{Check Response}
    A --> E{Check Report Request}

    B -->|"start"| F[Generate Scenarios]
    F --> G[Store Scenarios]
    G --> H[Send Scenarios]

    C -->|A/B/C| I[Process Selection]
    I --> J[Generate Questions]
    J --> K[Send Questions]

    D -->|Voice Note| L[Prepare Voice Note]
    L --> M[Transcribe Voice Note]
    M --> N[Generate AI Follow-up]
    N --> O[Store Transcription]
    O --> P[Update Assessment Memory]
    P --> Q[Send AI Follow-up]

    E -->|"generate report"| R[Generate Report]
    R --> S[Send Report]

Trigger

WhatsApp Webhook - Listens for incoming WhatsApp messages on the /coaching-start endpoint. The workflow responds to different message types: - Text containing "start" to begin assessment - Single letters A, B, or C for scenario selection - Voice notes for assessment responses - Text containing "generate report" for final report creation

Nodes Used

Node Type Purpose
Webhook Receives WhatsApp messages via Twilio
If (Conditional) Routes messages based on content (start, selection, voice, report)
OpenAI Generates scenarios, questions, follow-ups, and final reports
Code Processes selections and manages assessment data
Set Stores scenario and assessment data
Twilio Sends WhatsApp messages back to users

External Services & Credentials Required

OpenAI API

  • Purpose: Text generation, voice transcription
  • Credential ID: E8hkxFY5Lqqn03I5
  • Required: API key for GPT models and Whisper transcription

Twilio API

  • Purpose: WhatsApp messaging integration
  • Credential ID: 5owj9iWkYcotiAh4
  • Required: Account SID, Auth Token, WhatsApp-enabled phone number (+14155238886)

Environment Variables

No specific environment variables are configured in this workflow. All external service credentials are managed through n8n's credential system.

Data Flow

Input

  • WhatsApp messages (text and voice notes)
  • Message metadata (sender, timestamp, media URLs)

Processing

  • AI-generated assessment scenarios and questions
  • Voice note transcriptions
  • Structured assessment data storage
  • Contextual AI responses

Output

  • WhatsApp messages with scenarios, questions, and follow-ups
  • Comprehensive assessment reports
  • Stored assessment data for report generation

Error Handling

The workflow includes basic error handling: - Voice Note Processing: Checks for media presence and validates URLs - Data Retrieval: Safe parsing of stored assessment data with fallbacks - Default Values: Provides default scenarios if AI generation fails - Graceful Degradation: Uses fallback content when referenced nodes are unavailable

Known Limitations

  • WhatsApp message length limited to 1600 characters (handled by splitting messages)
  • Voice note transcription depends on audio quality and OpenAI Whisper availability
  • Assessment data is stored temporarily in workflow memory (not persistent across workflow restarts)
  • Single conversation thread - no multi-user session management
  • Currently disabled (active: false) - needs activation for production use

No related workflows identified from the provided context.

Setup Instructions

  1. Import Workflow

    • Import the JSON into your n8n instance
    • The workflow will be created in disabled state

  2. Configure Credentials

    • Set up OpenAI API credential with your API key
    • Configure Twilio credential with Account SID, Auth Token, and WhatsApp number

  3. Webhook Configuration

    • Note the webhook URL: https://your-n8n-instance.com/webhook/coaching-start
    • Configure this URL in your Twilio WhatsApp sandbox or production setup

  4. Twilio WhatsApp Setup

    • Ensure your Twilio number (+14155238886) is WhatsApp-enabled
    • Configure webhook URL in Twilio console for incoming messages

  5. Testing

    • Enable the workflow
    • Send "start" to your WhatsApp number to test scenario generation
    • Test the full flow: start → select scenario → voice responses → generate report

  6. Production Deployment

    • Update webhook URLs for production environment
    • Ensure proper error monitoring and logging
    • Consider implementing persistent storage for assessment data