Mail'O ✉️🤖

Mail'O is a professional, AI-powered email writing assistant designed to streamline the process of drafting polished, context-aware emails. By entering a recipient's name, a brief description of the message, and selecting a desired tone, users can instantly generate high-quality email drafts. Mail'O is built with a modern React frontend and a robust Java Spring Boot backend, utilizing Spring AI to communicate with Google's Gemini models for prompt completion and content generation.

---

📸 Application Showcase

Note

The screenshots below illustrate the responsive UI, tone-switching features, and generated email drafts. Please place your actual screenshots in the docs/screenshots/ folder to activate the visual showcase.

Home Page

How It Works Page

Email Generator Page (Output)

---

✨ Features

• AI-Powered Email Generation: Formulates structured, context-aware email subjects and bodies using Google's Gemini model.
• Multiple Email Tones: Establishes context-appropriate greetings and writing styles based on the selected tone:
  • Professional: Formal, structured, business-ready language.
  • Simple & Direct: Fluff-free, clear, and concise messaging.
  • Friendly: Conversational, warm, and approachable language.
• Recipient and Context Customization: Tailors the email's greetings, style, and sign-offs dynamically based on the recipient's identity and description.
• Input Validation: Enforces parameters on both frontend fields and backend DTOs to maintain database and API integrity.
• Actionable Output: Includes one-click copy to clipboard and a pre-filled compose button to export drafts directly to Gmail.
• Responsive User Interface: Features a responsive layout with theme toggle (Light and Dark mode) using Tailwind CSS and DaisyUI.
• API Documentation: Integrates Swagger UI/OpenAPI to allow developers to interact with the endpoints directly.

---

💡 How It Works

1. User Input: The user inputs the recipient's name, selects a tone, describes the email's content (minimum 10 characters), and submits the form.
2. Frontend Validation: React validates the input lengths and formatting to prevent invalid API requests.
3. HTTP POST Request: Axios transmits the validated data in JSON format to the /api/generateMail endpoint.
4. Backend Bean Validation: Spring Boot interceptors validate the incoming request properties against Jakarta Bean Validation annotations.
5. Service Processing: The backend service layer constructs a structured instruction prompt containing the name, description, selected tone, and today's date.
6. Spring AI Chat Client: The ChatClient formats and transmits the prompt securely to the Google Gemini model.
7. AI Generation: Google Gemini analyzes the prompt and returns a tailored subject line and email body.
8. UI Rendering & Toasts: The backend returns the email payload, React updates the local states to display the split subject/body layout, and triggers a success toast notification.

---

🏗️ Architecture

graph TD
    classDef client fill:#3b82f6,stroke:#1d4ed8,stroke-width:2px,color:#fff;
    classDef server fill:#10b981,stroke:#047857,stroke-width:2px,color:#fff;
    classDef external fill:#f59e0b,stroke:#d97706,stroke-width:2px,color:#fff;

    A[React Frontend]:::client -->|Axios HTTP POST| B[Spring Boot REST API]:::server
    B -->|Jakarta Bean Validation| C[AppController]:::server
    C -->|MailRequest DTO| D[AppService]:::server
    D -->|Spring AI ChatClient| E[Google Gemini API]:::external
    E -->|Generated Email Response| D
    D -->|MailResponse DTO| C
    C -->|JSON Payload Response| A

Loading

---

🛠️ Technology Stack

Frontend

• React 19 - User interface rendering
• Vite 8 - Frontend building and local dev server
• Tailwind CSS v3 - Utility-first styling framework
• DaisyUI v4 - Tailwind-based UI components
• React Router v7 - Client-side page navigation
• Axios - HTTP client request handling
• React Hot Toast - Non-blocking system notifications
• React Icons - Vector icons library

Backend

• Java 21 - Runtime environment and compile target
• Spring Boot 4.1.1 - Main application framework
• Spring Web MVC - RESTful controller endpoints routing
• Spring AI (Google GenAI Starter v2.0.0) - Model configuration and prompt management
• Jakarta Bean Validation - DTO attribute validation
• Springdoc OpenAPI v3 (v3.0.3) - Automated Swagger documentation
• Lombok - Automatic builder, getter, and setter generation
• Maven - Build tool and dependency manager

AI Model

• Google Gemini 3.6 Flash (gemini-3.6-flash)

---

🧠 AI Integration

Mail'O leverages Google's gemini-3.6-flash model through the Spring AI framework. In the backend AppService.java class, the application compiles user input into a clean instruction prompt:

Write an email based on the following instructions:

From Name: Rajeev
Recipient Name: [toName]
Tone: [tone]
Today's Date: [currentDate]
Description of what to say: [description]

Please provide a suitable Subject line, followed by the email body. 
Address the email to the recipient provided. Use [Your Name] as a placeholder for the sender.
Do not include any extra conversational text outside of the email itself.

The model returns a plain text response containing the subject and body. The frontend parses this structure using a newline search to display the Subject and Body in separate copy-friendly fields.

---

📁 Project Structure

Mail'O/
├── client/                 # React Frontend (Vite)
│   ├── src/
│   │   ├── components/     # Reusable UI components (Navbar, EmailForm, EmailResult, ThemeToggle)
│   │   ├── layouts/        # Layout wrappers (MainLayout)
│   │   ├── pages/          # Full page views (Home, EmailGenerator, Features, NotFound)
│   │   ├── services/       # Network API services (emailService.js)
│   │   └── main.jsx        # Frontend entry point
│   ├── package.json        # Frontend scripts and dependencies
│   └── vite.config.js      # Vite build settings
│
└── server/                 # Spring Boot Backend (Maven)
    ├── src/main/java/com/rj/mailO/
    │   ├── config/         # System configurations (CorsConfig)
    │   ├── controller/     # REST Endpoint controllers (AppController)
    │   ├── dto/            # Data Transfer Objects (MailRequest, MailResponse)
    │   └── service/        # AI prompt handling and business services (AppService)
    ├── src/main/resources/
    │   └── application.properties # Server properties and Spring AI model variables
    └── pom.xml             # Maven dependencies configuration

---

🚀 Getting Started

Prerequisites

Make sure you have the following installed on your machine:

• Node.js (v18.0.0 or higher)
• JDK 21
• Google Gemini API Key (Obtain one from Google AI Studio)

Environment Variables

Configure your credentials in the server folder. Create a .env file in server/:

GEMINI_API_KEY=your_actual_gemini_api_key_here

Warning

Security Warning: Never commit your .env file or raw API keys to Git. The project's root .gitignore file is pre-configured to ignore all .env files.

Backend Setup (Spring Boot)

1. Navigate to the server directory:

   cd server

2. Start the Spring Boot server using the Maven wrapper:
   • Windows:

     ./mvnw.cmd spring-boot:run

   • macOS/Linux:

     ./mvnw spring-boot:run

   The server will start at http://localhost:8080.

Frontend Setup (React)

1. Navigate to the client directory:

   cd client

2. Install the required packages:

   npm install

3. Launch the Vite local server:

   npm run dev

   The application will run locally at http://localhost:5173.

---

📖 Usage

1. Open the application by visiting http://localhost:5173.
2. Go to the Email Generator page.
3. Enter the Recipient Name (e.g., Hiring Manager, Support Team).
4. Enter the Email Description explaining what the email is about (minimum 10 characters).
5. Select a Tone (Professional, Simple & Direct, or Friendly).
6. Click Generate AI Email.
7. Review the subject line and body output.
8. Click Copy to copy the content to your clipboard, or Send Email to open the pre-filled message in Gmail.

---

🛡️ Validation & Error Handling

To maintain data integrity and avoid unnecessary AI API consumption, validation rules are enforced at both layers:

Validation Rules (MailRequest.java)

• toName (@NotNull): The recipient name field is required and cannot be null.
• description (@NotBlank, @Size): The description field is required and must contain between 10 and 2000 characters.
• tone (@NotNull): A valid tone parameter matching one of the ToneEnum values is required.

Error Propagation

• HTTP 400 Bad Request: If any validation rules are breached, the backend rejects the payload and returns an error array with descriptions.
• Frontend Alerts: The Axios service layer catches HTTP failures, formats nested validation constraints, and surfaces them using React Hot Toast messages and a visual error banner in the UI.

---

🔌 API Documentation

• Swagger Interactive UI: http://localhost:8080/swagger-ui/index.html
• OpenAPI Specification JSON: http://localhost:8080/v3/api-docs

Email Generation Endpoint

• Endpoint: /api/generateMail
• Method: POST
• Content-Type: application/json

Request Parameters

Field	Type	Required	Description / Constraints
toName	String	Yes	Name of the recipient
description	String	Yes	Core email context (10 to 2000 characters)
tone	String	Yes	Selected tone: PROFESSIONAL, SIMPLE, FRIENDLY

Request Payload

{
  "toName": "Support Team",
  "description": "Requesting an extension on the project deadline due to server downtime.",
  "tone": "PROFESSIONAL"
}

Response Payload (HTTP 200 OK)

{
  "result": "Subject: Request for Deadline Extension - Server Downtime\n\nDear Support Team,\n\nI hope this email finds you well. I am writing to request a short extension on the project deadline..."
}

---

🚀 Deployment

Frontend Build

To package the React frontend, navigate to the client/ directory and run:

npm run build

This generates optimized, minified production assets in the client/dist/ directory.

Backend Package

To package the Spring Boot backend into an executable JAR, navigate to the server/ directory and run:

./mvnw clean package

The standalone executable JAR will be generated under server/target/.

Production Considerations

When deploying to cloud providers:

• Configure the database or target profiles using Spring profiles (spring.profiles.active).
• Ensure that the GEMINI_API_KEY is configured as a secure system environment variable rather than hardcoded.

---

🗺️ Roadmap

• AI email generation using Google Gemini model
• Multiple email tones (Professional, Simple, Friendly)
• Jakarta Bean DTO validation and Axios error formatting
• Direct clipboard copy integration
• Responsive layout with Light/Dark mode switcher
• Email history persistence (Database integration)
• OAuth2 Authentication (Google/GitHub sign-in)
• Direct Gmail API integration (Drafting/sending without redirects)
• Multi-LLM provider support (switching between OpenAI, Anthropic, Gemini)
• RAG-based email replies using historical threads or files

---

🤝 Contributing

1. Fork the repository.
2. Create a feature branch: git checkout -b feature/your-feature-name.
3. Commit your changes: git commit -m 'Add some feature'.
4. Push to the branch: git push origin feature/your-feature-name.
5. Submit a Pull Request.

---

📄 License

No license is currently specified for this project.