System Requirements Document (SRD)

Project Name: mint-ai

1. Introduction

The mint-ai project is an AI-driven mock interview web application designed to assist users in preparing for job interviews. Developed as a college project by Rudra in India, the platform aims to provide essential features for interview practice, including real-time feedback, scoring, and basic question customization. By leveraging AI technology, mint-ai offers a lightweight yet effective solution for students, professionals, and anyone preparing for interviews.

2. System Overview

The mint-ai application will simulate mock interviews using AI models to generate questions, evaluate responses, and provide feedback. The system will cater to users across various industries and experience levels, offering a streamlined interface for easy navigation. Key features include:

• AI-generated interview questions tailored to general and role-specific categories.
• Real-time scoring and feedback to help users improve their performance.
• A simple and intuitive user interface for seamless interaction.

The application will be built using modern technologies, ensuring scalability and responsiveness while maintaining simplicity for a college project scope.

3. Functional Requirements

Story Points:

• As a User, I should be able to register and log in to the platform.
• As a User, I should be able to select an interview category (e.g., technical, HR, or general).
• As a User, I should be able to start a mock interview session with AI-generated questions.
• As a User, I should receive real-time feedback and scoring based on my responses.
• As a User, I should be able to view my performance summary after completing the interview.
• As a User, I should be able to access basic question customization options (e.g., difficulty level).

4. User Personas

1. Student

• Description: College students preparing for campus placements or internships.
• Goals: Practice interview questions, improve confidence, and receive constructive feedback.

2. Professional

• Description: Working professionals seeking new job opportunities or career advancement.
• Goals: Refine interview skills, prepare for role-specific questions, and assess performance.

3. General User

• Description: Anyone preparing for interviews, regardless of industry or experience level.
• Goals: Gain exposure to interview scenarios, receive scoring, and improve responses.

5. Visuals Colors and Theme

Color Palette:

• Background: #F5F7FA (Soft Cloud White)
• Surface: #E8EDF3 (Light Steel Blue)
• Text: #2C3E50 (Deep Navy)
• Accent: #3498DB (Bright Sky Blue)
• Muted Tones: #95A5A6 (Muted Gray)

Theme:

The visual theme will be clean, professional, and approachable, reflecting the purpose of the app as a tool for interview preparation. The design will emphasize simplicity and clarity, ensuring users can focus on their practice sessions without distractions.

6. Signature Design Concept

Concept: Interactive AI Interview Room

The homepage will feature an immersive AI interview room design. Upon entering, users will see a virtual desk with a holographic AI interviewer avatar sitting across from them. The avatar will animate subtly, mimicking realistic gestures like nodding or smiling during the session.

Key elements:

• Dynamic Background: A gradient background that shifts colors based on the time of day (e.g., warm tones in the morning, cool tones at night).
• Interactive Elements: Users can click on objects in the room (e.g., a notepad for tips or a clock for session timing).
• Micro-Interactions: Buttons and icons will have hover effects, such as glowing or pulsing, to enhance engagement.
• Transitions: Smooth page transitions with fade-ins and slide animations to maintain a polished experience.

This design will make the app memorable and engaging, setting it apart from generic mock interview platforms.

7. Non-Functional Requirements

• Performance: The system should handle up to 500 concurrent users without degradation.
• Scalability: The architecture should allow for future expansion to include advanced features.
• Security: User data, including login credentials and performance summaries, must be encrypted.
• Accessibility: The platform should comply with WCAG 2.1 standards to ensure usability for all users.
• Localization: Default settings will cater to Indian users, including IST timezone and INR currency.

8. Tech Stack

Frontend:

• React for Web

Backend:

• Python
• FastAPI

Database:

• MySQL (with Alembic for migrations)

AI Models:

• GPT 5.4 for user-friendly responses
• Claude 4.6 Opas for coding-related interview questions
• Gemini 3.1 Pro for friendly and conversational feedback

AI Tools:

• Litellm for LLM Routing
• Langchain

Local Orchestration:

• Docker
• docker-compose

Server-Side Orchestration:

• Kubernetes

9. Assumptions and Constraints

Assumptions:

• Users will have basic familiarity with web applications.
• The platform will primarily target Indian users but remain accessible globally.
• The scope is limited to essential features due to its college project nature.

Constraints:

• Limited budget and resources for development.
• No advanced customization or industry-specific features.
• The system must be lightweight and easy to deploy.

10. Glossary

• AI: Artificial Intelligence, used to simulate interview scenarios and provide feedback.
• Mock Interview: A simulated interview designed to help users practice and improve their skills.
• Real-Time Feedback: Immediate evaluation and suggestions provided during the interview session.
• Scoring: Numerical assessment of user performance based on predefined criteria.
• Customization: Basic options for tailoring interview questions, such as difficulty level.