ReZon: A Context-Aware Personal AI Assistant Desktop Overlay by Ahmad Basyouni

 Ahmad Basyouni, Verrazzano Class of 2026, completed a major in Engineering Science

My capstone is called ReZon, a personal AI assistant that runs as a small see-through window on top of everything else on your screen. The idea is pretty simple. Instead of leaving your work, opening a chat tab, copy-pasting your code or your chart, and asking a question somewhere else, the assistant comes to you. You press one hotkey and it can see what's on your screen, figure out what app you're in, and either give you a quick answer or do something for you.

It has three modes. Trader Mode watches TradingView and warns me when I switch between stocks, reminding me of rules I set for myself, so I don't make impulsive trades. Coding Mode takes a screenshot of whatever code I'm looking at, reads it, and gives me a short summary, a possible bug, and a fix. Productivity Mode can create calendar events, send iMessages, raise GitHub issues, and make Notion tasks, but only after I click an Approve button. It never does anything on its own.

The whole thing runs on my laptop. The language model (Qwen 2.5 7B) is loaded locally through Ollama, so nothing I'm reading, writing, or trading ever leaves my computer. The system boots up with one command in about 11 seconds, and I check it before every demo with a script that runs 33 tests against all three modes.

My main conclusion was that the AI part was almost never what made things hard. Once the model was warmed up, it gave me good answers in under two seconds. What actually broke the system was the surrounding plumbing. A hardcoded calendar name that didn't exist on my Mac. A screenshot that accidentally captured the assistant's own UI. A retry loop that gave up too early after 61 tries. None of those bugs were about intelligence. They were about details. For an assistant that lives on your screen, the smart part is necessary, but the small interface decisions are what make it feel reliable.

I picked this research area because I was annoyed at myself. I'd be paper trading on TradingView and catch myself about to click Buy on something I already told myself I wouldn't trade, just because the button was sitting right there. And while coding I'd tab over to ChatGPT, paste a function, ask a question, then come back and lose my place. Both problems are the same problem. My apps don't know about my plan, so they let me forget about it. I wanted to build the thing I wished existed for me.

I expected the project to mostly be about AI. Picking the right model, prompting it cleverly. It really wasn't. The hard parts were tiny details. Getting an Electron window to actually float above Fullscreen Chrome on Mac took way more research than I expected. Making sure the screenshot didn't capture my own overlay took an entire afternoon of debugging. AppleScript for Calendar and iMessage was simple to write, but macOS permissions fight you the first few times you run it.

What was easier than I expected was the language model itself. Qwen 2.5 7B running locally was fast enough and accurate enough that I never felt limited by it. What surprised me most was how much one tiny fix mattered. I added a hardcoded fast path that fires a guaranteed sub-second toast on every ticker change, totally separate from the slower AI path. That one design choice is probably what kept my live demo from breaking on stage.

If I keep going on this, the next step is Windows support, because every friend I showed it to asked for it. After that I want to add long-term memory using a vector database, so the assistant remembers preferences across months instead of just sessions.

The biggest thing I'm taking away is that building something for yourself first is a really good way to stay motivated for a whole semester. I learned more from debugging this one project than I did in most of my classes.

Al-Noor School College Readiness & Career Exposure Program

Maiyadah Kased, Verrazzano Class of 2026, completed major in SLS

Working on this capstone project has been one of the most meaningful experiences for me, both academically and personally. Going into it, I knew I wanted to create something that would help students, especially because I had once been in their position, feeling unsure and unprepared for what comes after high school. Through the process of developing, implementing, and analyzing this program, I realized that its impact went far beyond what I originally expected.

One of the biggest things I learned is how powerful structured support and exposure can be. At the beginning of the program, many students felt overwhelmed, confused, and unsure about college and their future. Seeing the data shift from students feeling “unprepared” to “prepared and confident” showed me that these feelings weren’t permanent, they were the result of a lack of guidance and opportunities. Once students were given access to information, mentorship, and real experiences like college visits and guest speakers, their mindset completely changed. This made me understand that sometimes students don’t lack ability, they just lack access and support.

Another major takeaway for me was the importance of relationships. I initially thought the most impactful parts of the program would be things like college fairs or presentations, but what stood out the most was the connection students built with counselors and alumni. Hearing from guest speakers who were once in their exact position made success feel more real and achievable. More personally, I learned how important it is for students to feel heard. There were moments during interviews that really stayed with me, especially when I saw students begin to open up and express themselves in ways they hadn’t before. That showed me that being a counselor is not just about giving advice, but about creating a space where students feel safe, understood, and supported.

I also learned a lot about research itself. Since I was both the program coordinator and the researcher, it challenged me to step back and look at my work more objectively.  Analyzing surveys, interviews, and field notes helped me see patterns and themes I wouldn’t have noticed otherwise. It made me realize how important it is to listen to student voices and use their feedback to improve programs. At the same time, I became more aware of the limitations of my study, especially since it focused on one group of students. This pushed me to think more critically about how research can be expanded and strengthened.

If I were to continue developing this project, there are several ways I would want to build on it. First, I would expand the program to include more interactive and hands-on experiences, such as career simulations or workshops that allow students to actively engage with different fields. I would also want to include a wider variety of career paths so that more students feel represented and can explore options beyond the most commonly discussed professions. In terms of research, I would expand the sample size by including multiple grade levels or even partnering other schools to see if similar results occur in different settings.

Additionally, I would place an even stronger emphasis on one-on-one support and reflection. The data showed that students benefited not just from exposure, but from having time to process what they learned and talk through their thoughts. Creating more structured opportunities for reflection could help deepen the impact of the program even further.

Overall, this project changed how I see both education and my role within it. What started as an effort to improve college readiness turned into something much bigger, a support system that helps students grow academically and emotionally. It showed me that when students are given the right tools, guidance, and environment, they can build confidence and find clarity in their future. This is something I will carry with me moving forward, and it continues to shape how I think about supporting students in meaningful ways.

 

Reimaging Student Helpdesk Communication at CSI

John Adibeli, Verrazzano Class of 2026, completed major in Mathematics and minors in Business and Design & Digital Media

This project focused on improving the student experience with the Office of Information Technology Services (OITS) at the College of Staten Island by using student feedback to identify common challenges and propose practical improvements. By using a survey, I collected responses from students about their experiences with IT support, including issues with logging into accounts, connecting to WiFi, and navigating the Help Desk website. Based on this feedback, I developed design ideas such as a simplified support interface, a clearer “Report a Problem” process, a ticket tracking feature, and a more organized FAQ section. Overall, this project highlights how listening to students can lead to more accessible and effective support systems.

What made this project especially meaningful to me was how closely it connected to my own experience. As both a student and a college assistant working within OITS, I have seen firsthand how students struggle to get the help they need, while also understanding the limitations and responsibilities on the staff side. This dual perspective is what led me to choose this topic. I wanted to work on something that not only interested me but also had the potential to make a real difference within a department I am part of.

At the beginning, I expected the capstone to feel like a typical class assignment, but it quickly became clear that it required much more independence and responsibility. Unlike other projects, I had to take initiative in designing the survey, collecting responses, analyzing the data, and consistently communicating with my mentor to stay on track. In many ways, it felt less like an assignment and more like a real-world project, which pushed me to be more accountable for my own progress.

One of the biggest challenges I faced was maintaining motivation and managing my time effectively. Balancing this project alongside my regular coursework, exams, and other responsibilities was not easy. There were times when it was difficult to stay consistent, especially when I had other academic priorities to focus on. Gathering enough data was also a challenge, and looking back, I realize I should have distributed my survey earlier to allow more time for responses. At the same time, I found parts of the process enjoyable, particularly when I was analyzing the feedback and thinking about how to translate those insights into design improvements. It was rewarding to see how real student experiences could directly shape potential solutions.

 If I had the opportunity to continue this research, I would want to take it a step further by sharing my findings with leadership within the OITS department. I would be interested in seeing how realistic these ideas are from an operational standpoint and what changes would be necessary to implement them. I would also expand the survey to include a larger group of students to strengthen the data and better represent the student population.

Overall, this experience is something I take pride in completing. It challenged me in ways that went beyond a typical assignment and helped me develop stronger time management and organizational skills. More importantly, it showed me how research and design can be used together to solve real problems. This project made me think differently about how students interact with campus services and how even small improvements can have a meaningful impact. It is an experience that I will carry with me moving forward, both academically and professionally.

Tea Colored Minds: An in-depth Evaluation on The God of Small Things and Transgressive Love in India’s Caste System

Jillian Handley, Verrazzano Class of 2026, completed major in English Literature 

For my thesis, I examined the structure of India’s caste system and how it shapes and forms everyday life, creating tight restrictions on love. I think what primarily motivated this research was my infatuation with the concept of love. It can be found everywhere, within anyone, and lingers for years. It can be shown and represented in so many ways, and everyone deserves that invisible bond that trails amongst us all. It is such a mundane topic, but it impacts us in so many ways, and it's a common ground we can all relate to in one way or another. Almost everyone I am surrounded by has had either a great love, a tragic love, a first one, or even a doomed love.

Arundhati Roy took everything I wanted to focus on and compiled it into an intricate work of art that remains extremely relevant to this day. In her work, she draws on her experience living in India and the effects of caste, post-colonialism, and family dynamics leading up to tragedy and altering lives.

When I went into this paper, I was excited because I had never quite done something like this before. Despite being an English major, I haven’t had to complete something of this caliber. When I was a sophomore, I took a class with Professor Ray, and on the first day, he asked us, “Do you know the caste system?”, and went into great detail about the social system in the country, making for a well-informed conversation throughout the semester. Although we had spoken about it throughout the course, it still didn’t make the topic any less daunting. For me, focusing on love and family bonds was the bridge I needed to feel most at ease with during the conversation.

I found more things to be more hard than easy when working on this, but I feel that is expected and maybe even more appreciated. I love feeling challenged, but I also like adding to conversations, and I was able to do exactly that in my research. I don’t think I’ll ever speak about temporal hybridity or the bildungsroman the way I do now, but who knows!

If I were to ever expand on this topic, I would need something that can provide a new avenue of perspective to enhance the work rather than sounding like I’m repeating the same four sentences. But from my work, I am leaving with the importance of childhood experiences in shaping lives. Prejudice is taught, not born. Love is truly the greatest risk taken and the most rewarding, despite all odds.

Dietary Factors Impact on Oral Microbiome

Emily Eisler-Grynsztajn, Verrazzano Class of 2026, complete major in Biology and minor in Psychology

I chose the focus of my capstone to be the relationship between diet and the oral microbiome. I have always been interested in health, and I never really took the time to realize how much what we eat can affect oral health beyond just cavities. Getting to learn that the things we consume can influence bacteria in the mouth, and even connect to overall health, made me want to explore it further. This topic felt relevant because diet is something people have the ability to control, and understanding its impact could help prevent not only oral diseases, but systemic ones as well.

At the very start of this project, I expected it to mainly focus on basic nutrition and dental hygiene. However, the research ended up being much more complex than I thought. I learned that different dietary patterns, like high-sugar diets versus plant-based or Mediterranean diets, can significantly change the diversity of bacteria in the mouth. For instance, high sugar intake promotes harmful bacteria and reduces microbial diversity. On the other hand, plant-based and Mediterranean diets support beneficial bacteria and reduce inflammation. I did not expect the connection between the oral microbiome and overall health, including diseases like diabetes and cardiovascular conditions, to be so strong.

One of the most challenging parts of this project was organizing all the scientific information and making it understandable. A good amount of the studies had complex terminology, especially when learning about microbial diversity, metabolism, and research methods. Something else that was difficult initially was understanding the methodology, like the two-phase design with both observational and experimental research. To make it easier to follow on my part, I broke it down. The easiest part of the project was connecting the research to real-life examples, especially our choices in diet, because it made the topic feel more relatable.