Connecting MCS Studies with Modern AI Technologies

Studying MCS has changed the way I look at computer science. Before this, most of my learning was focused on building applications and improving myself as a full stack developer. I worked with frontend, backend, databases, APIs, authentication, and deployment. I learned how to use technologies like React, Laravel, Node.js, Python, and Supabase to build complete web applications.

But after joining MCS, I started looking at technology from a deeper point of view.

Now I do not only ask, “How can I build this feature?” I also ask, “Why does this system work this way?” and “How can this be improved?” This small change in thinking has made my learning more interesting.

MCS is helping me connect my practical development experience with stronger computer science concepts. Subjects related to algorithms, data, research, system design, and intelligent systems feel more meaningful when I compare them with the real applications I have worked on.

For me, this is where modern AI technologies become interesting.

From Building Applications to Understanding Intelligence

As a full stack developer, I already understand how normal web applications work. A user sends a request, the backend processes it, the database stores or returns data, and the frontend displays the result. This flow is familiar to me.

But AI-powered applications work a little differently.

They do not only store and return data. They can understand language, generate responses, summarize information, suggest ideas, and sometimes assist users in decision-making. Generative AI especially has made this more visible because it can work with text, code, documents, and other types of content.

This made me realize that the future of software is not only about forms, dashboards, and CRUD operations. Applications are slowly becoming more interactive, more helpful, and more intelligent.

As someone who already works with web technologies, I feel that learning AI is a natural next step for me.

Why MCS Makes AI More Meaningful for Me

If I had started learning AI only from tools, I might have focused only on using prompts or APIs. But because I am studying MCS, I feel more interested in the concepts behind those tools.

I want to understand how models learn from data, how they generate output, why they sometimes make mistakes, and how we can design better systems around them.

For example, when I use an AI chatbot, I do not only see it as a chat interface. I start thinking about the complete system behind it. What model is being used? Where is the data coming from? How is the prompt structured? How can the answer be made more accurate? How should user data be handled? What happens if the AI gives a wrong answer?

These questions make AI more serious and more interesting for me.

MCS gives me the academic environment to think about these questions, while my full stack development background gives me the practical skills to build and test real applications.

The New Question I Keep Asking Myself

One question I keep asking myself is:

Can I build applications that are not only functional, but also intelligent enough to support users in a better way?

This question feels important to me.

A normal application can show data. But an AI-powered application can explain that data.

A normal search feature can match keywords. But an AI-powered search system can understand meaning.

A normal dashboard can display charts. But an AI-powered dashboard can help users understand what those charts actually mean.

A normal document system can store files. But an AI-powered document assistant can help users summarize, search, and understand those files faster.

This is the kind of thinking that makes me more interested in modern AI technologies.

I do not want to learn AI just to say that I know AI. I want to learn how it can be connected with real problems and real applications.

Connecting AI with My Full Stack Skills

One thing I have understood is that AI alone is not enough to build a complete product.

Even if the main feature is powered by AI, the application still needs a proper frontend, backend, database, authentication, API integration, error handling, security, and deployment. This is where my full stack background becomes useful.

For example, if I build an AI document assistant, I still need to create the upload system, store the files, extract text, connect the AI model, display the result, and manage users.

If I build an AI chatbot, I still need to design the chat interface, save conversation history, manage API calls, handle loading states, and make the response feel natural to the user.

If I build an AI-based content tool, I still need to think about user experience, prompt design, editing options, saved drafts, and performance.

So for me, AI is not separate from web development. It extends web development.

It gives full stack applications a new layer of intelligence.

A Concept That Really Caught My Attention

One concept that I find very interesting is Retrieval-Augmented Generation, also called RAG.

The idea is simple but powerful. Instead of depending only on what an AI model already knows, we can connect it with external data, such as documents, websites, notes, or a knowledge base. Then the AI can generate answers based on that specific information.

This caught my attention because it feels very practical.

Many real-world applications need answers from private or updated data. For example, a company may want an AI assistant that answers questions from its own documents. A college may want a student support assistant trained on notices, syllabus, and rules. A developer may want an AI assistant that can search project documentation and explain code structure.

This kind of system connects AI with actual data, and that makes it more useful.

As a developer, I can imagine building this type of application using my existing skills: frontend for the user interface, backend for APIs, database for storage, and AI integration for intelligent responses.

Learning AI with Responsibility

Another thing I am starting to understand is that AI should not be used blindly.

AI can be powerful, but it can also make mistakes. It may generate wrong information, biased answers, or responses that sound correct but are not actually accurate. Because of this, developers need to think carefully while building AI-powered systems.

This is where deeper understanding becomes important.

It is not enough to connect an API and display the answer. We need to think about accuracy, privacy, user trust, and limitations. We need to ask whether the answer should be verified, whether the user should see the source, and whether the AI should be allowed to make certain decisions.

As I continue my MCS studies, I want to understand these parts more seriously. I believe responsible AI development will become an important skill for developers in the coming years.

What I Want to Explore Next

My current goal is to keep learning AI step by step and connect it with projects.

I want to explore generative AI, large language models, prompt engineering, embeddings, vector databases, RAG, and AI agents. I also want to understand how these concepts can be used in real applications instead of learning them only in theory.

Some project ideas I want to try are:

• AI chatbot for a personal website

• AI assistant for documents and PDFs

• Smart search system for blogs or notes

• AI-powered resume or portfolio assistant

• Content generation tool for developers

• Dashboard that explains data in simple language

These ideas match both my academic journey and my experience as a full stack developer.

My Direction Going Forward

At this stage, I feel that MCS and AI are helping me grow in a new direction.

Full stack development gave me the ability to build applications. MCS is helping me think more deeply about computer science. Modern AI technologies are showing me how software can become more intelligent and useful.

I know I still have a lot to learn. AI is a large field, and it is changing very fast. But I feel motivated because I can connect it with what I already know.

For me, the goal is not to leave full stack development and move completely into AI. The goal is to combine both.

I want to become the kind of developer who can build complete web applications and also add intelligent features that solve real problems.

This journey is still at an early stage, but it feels meaningful. I am learning not only how to use modern AI tools, but also how to think about them, question them, and build with them responsibly.

That is what makes this phase of my learning exciting.