AWS Builder Center
Building AnvikshAI: Creating a Personalized Learning Platform with AWS EC2 and S3

Building AnvikshAI: Creating a Personalized Learning Platform with AWS EC2 and S3

Discover how I built AnvikshAI, an AI-powered personalized learning and career alignment platform designed to help learners overcome information overload. In this blog, I share the technical architecture, AI-assisted learning roadmap generation, and my practical experience using Amazon EC2 for cloud deployment and Amazon S3 for object storage. I also discuss the challenges I faced, lessons learned, and how AWS services supported the development of a scalable EdTech solution.

Building AnvikshAI: Creating a Personalized Learning Platform with AWS EC2 and S3

Introduction

The internet has made learning resources more accessible than ever. Today, students can find programming tutorials, documentation, courses, and educational videos on almost any topic. However, having access to more resources does not always make learning easier.
One of the challenges I have observed is that learners often struggle with deciding what to study, where to begin, and how to organize their learning journey. They may spend more time searching for resources than actually learning.
This problem inspired me to build AnvikshAI, an AI-powered personalized learning and career alignment platform. The goal is to help learners turn a skill or career objective into a structured learning journey with actionable milestones.
In this blog, I will explain the motivation behind AnvikshAI, its technical architecture, how I used Amazon EC2 and Amazon S3, and the lessons I learned while working on the project.

1. The Problem: Too Much Information, Not Enough Direction

When someone wants to learn a new skill, the first step is often to search online. This can lead to a large number of tutorials, courses, videos, and articles.
Although these resources are valuable, learners can face several difficulties:
  • Finding a suitable starting point based on their current knowledge.
  • Organizing learning resources in the correct sequence.
  • Dividing a large learning goal into manageable daily tasks.
  • Tracking progress and identifying areas that need more practice.
  • Understanding how a skill relates to career opportunities.
AnvikshAI was designed around the idea that learning should not only provide information but also help learners organize and apply that information.

2. Introducing AnvikshAI

AnvikshAI is a learning platform that uses AI-assisted roadmap generation to help users organize their learning goals into structured plans.
A learner can select a topic or skill they want to develop. The platform is designed to help generate a learning roadmap based on the learner's goals, current knowledge, and available time.
The core concept is:
Personalized Structured Content + Smart Feedback + Career Guidance
The platform focuses on four main principles:
  1. Personalization and structure: Organizing learning around the learner's goals and existing knowledge.
  1. Adaptive learning: Supporting progress tracking, practice, and adjustments to the learning journey.
  1. Content curation: Helping learners discover and organize existing educational resources.
  1. Career-skill integration: Connecting skill development with practical career objectives.
The aim is to make self-learning more organized and actionable.

3. Technology Stack

I used a modern full-stack technology stack to develop AnvikshAI.
Component
Technology
Frontend
React.js
UI
Material Tailwind, Tailwind CSS, ShadCN UI
Backend
FastAPI, Python
Additional backend
Node.js
Database
MongoDB
AI
DeepSeek local model
Cloud compute
Amazon EC2
Object storage
Amazon S3
The architecture was organized into modular components to make development and future improvements easier.
React was used to build the user interface, while FastAPI and Python handled backend and AI-related functionality. MongoDB was used for application data, and the AI layer supported the generation of personalized learning roadmaps.

4. Using AI to Organize Learning

One of the central components of AnvikshAI is AI-assisted learning roadmap generation.
Instead of providing a learner with an unstructured list of resources, the platform is designed to organize learning into a sequence of topics and milestones.
For example, a learner interested in backend development could receive a roadmap that includes:
  • Programming fundamentals.
  • HTTP and API concepts.
  • Backend framework fundamentals.
  • Database integration.
  • Authentication and security.
  • Practical projects and revision.
The roadmap concept is intended to help learners understand what they should focus on at each stage.
AnvikshAI uses a DeepSeek model as part of its AI approach. The model supports the generation of learning-related content and roadmap structures. The actual quality of a generated roadmap still depends on the model, prompts, validation, and the learning requirements provided by the user.
This project helped me understand that integrating an AI model into an application involves more than simply sending a prompt and displaying the response. The surrounding application needs to organize the input, handle the output, and provide a useful experience for the learner.

5. Application Architecture

The application follows a modular architecture with separate frontend, backend, AI, database, and cloud infrastructure components.
The general request flow is:
Learner → React Frontend → Backend API → AI Processing → Database / Response → Learner
The frontend is responsible for user interaction and displaying the learning experience. The backend handles API requests and application logic. The AI component supports roadmap-related processing, while MongoDB stores application data.
The cloud infrastructure provides an environment for running application services and managing resources.
This separation helps make the application easier to maintain and provides a foundation for future improvements.

6. Deploying Application Services with Amazon EC2

Why I used Amazon EC2

Amazon EC2 provides cloud-based virtual servers that can be configured to run application workloads.
For AnvikshAI, I used EC2 as part of the application's cloud deployment. It provided an environment for running backend and application-related services.
Working with EC2 gave me experience with the practical aspects of cloud deployment, including:
  • Working with a remote server environment.
  • Preparing the runtime for application services.
  • Managing application dependencies.
  • Understanding the relationship between a local development environment and a deployed application.
For a full-stack AI application, the deployment environment needs to support the requirements of the backend and AI components. EC2 provides the flexibility to configure the server environment according to those requirements.

What I learned from EC2

One of the important lessons I learned is that developing an application locally and deploying it to a cloud server are different tasks.
A working local application still requires appropriate configuration, dependency management, and operational considerations when it is deployed.
This experience helped me better understand the practical side of backend deployment and cloud infrastructure.

7. Using Amazon S3 for Object Storage

Amazon S3 is an object storage service that can be used to store and manage files and other objects.
I used Amazon S3 as part of the storage infrastructure for AnvikshAI.
Separating object storage from the application compute environment provides a useful architectural approach. It allows application files and resources to be managed through a dedicated storage service rather than relying exclusively on the local filesystem of the application server.

What I learned from S3

Working with S3 helped me understand the role of cloud storage in application architecture.
Some of the concepts I considered while working with storage included:
  • Organizing stored objects.
  • Understanding storage access permissions.
  • Separating application compute from object storage.
  • Considering how storage requirements can change as an application grows.
S3 is particularly useful as an architectural component when an application needs to manage files or other stored resources independently of its compute environment.

8. Challenges During Development

Building an AI-powered learning platform involves several challenges beyond implementing the user interface.

Challenge 1: Converting learning goals into useful roadmaps

A learning roadmap needs to be relevant to the learner's starting point and objective. Generating a sequence of topics is not sufficient if the order is unclear or the content does not match the learner's requirements.
This motivated me to focus on personalization, structure, and the organization of learning milestones.

Challenge 2: Integrating AI into a practical application

An AI model needs to be integrated with application logic, user inputs, and the overall product experience.
The challenge is not only generating a response but also designing how that response can support an actual workflow.
This project helped me think about AI as one component of a larger software system rather than as an isolated feature.

Challenge 3: Understanding cloud deployment

Moving from local development to a cloud environment introduced practical considerations involving server configuration, application dependencies, and storage.
Working with EC2 and S3 helped me gain experience with the infrastructure side of building a web application.

9. What I Would Improve in the Future

AnvikshAI is a foundation for a larger learning platform, and there are several areas I would like to improve.

Better roadmap validation

Generated roadmaps should be evaluated for logical sequencing, relevance, and suitability for the learner's current knowledge.

More adaptive learning

The platform could use quiz results, completed tasks, and learning progress to adjust future recommendations.

Improved content curation

A stronger content discovery and validation system could help learners find relevant resources while reducing irrelevant or low-quality recommendations.

Career-oriented learning insights

The platform could connect learning roadmaps with job requirements and skill trends, helping learners understand the practical applications of the skills they are developing.

More scalable infrastructure

As usage increases, the application architecture could be improved through better service separation, monitoring, and infrastructure optimization.
These improvements would require additional design, testing, and evaluation.

10. My Experience with AWS

Working with Amazon EC2 and Amazon S3 helped me understand how cloud services support application development.
EC2 gave me practical experience with cloud-based application hosting, while S3 helped me understand object storage and the separation of storage from compute resources.
One of the key lessons I took from the project is that building a product involves more than writing code. Application architecture, deployment, resource management, and maintainability are also important parts of software engineering.
I also learned that cloud services should be selected based on the actual requirements of the application. Understanding what a service provides is important, but knowing how to integrate and manage it within a complete system is equally valuable.

11. Conclusion

AnvikshAI started with a simple idea: help learners move from information overload to structured, actionable learning.
By combining AI-assisted roadmap generation, learning organization, and career alignment, the project explores how technology can support more personalized self-learning experiences.
The development process gave me an opportunity to work across frontend development, backend APIs, AI integration, databases, and cloud infrastructure.
Using Amazon EC2 and Amazon S3 helped me gain practical experience with deploying application services and working with cloud storage.
I see AnvikshAI as a foundation for further experimentation in AI-powered education. My future focus is to improve roadmap quality, make learning more adaptive, and build a platform that helps learners develop skills with greater clarity and direction.
The goal is not just to help learners find more information, but to help them understand what to learn, how to learn it, and how to move forward.
Any opinions in this article are those of the individual author and may not reflect the opinions of AWS.
Enjoyed reading this content? Let the author know!

Your likes, comments, shares, and saves help creators reach more builders.

Loading recommendations

Loading article