Demo Day Fall 2025: Student Teams Deliver Solutions in Health, Education, AI, and More

BU Spark! closed out the Fall 2025 semester not just with projects, but with powerful solutions that offer a genuine hope for a better future by showcasing how student innovation is driving meaningful change. Demo Day, as part of the Experiential Learning Expo, brought together students, faculty, and industry partners to witness firsthand the ingenious spirit powering experiential learning across campus.

This year’s projects spanned critical areas including advanced AI, civic technology, accessibility, and sustainability, proving that for Spark! students, the end of a course is just the beginning of a solution. Dive in to explore each team and the future they are building.

🏆 Winner’s Circle

Following a full slate of presentations and audience engagement, two teams were recognized for their standout work:

LearnWyrm (formerly LinguaPlay) — Judges’ Choice Award

LearnWyrm transforms traditional class materials into quick, interactive quizzes and mini-games, giving educators an easy way to boost engagement without adding prep time. Teachers can create classes, upload materials, generate questions, build games, and track student progress — all in under a minute. Students benefit from a game-like learning experience in place of static PDFs, while educators remain fully in control of content. Designed to work across subjects and grade levels, LearnWyrm prioritizes curriculum alignment, ease of use, and student data security.

Team members: Artemios Kayas (akayas@bu.edu), Evan Jaquez (jaquevan@bu.edu), Eddie Lu (adefifp@bu.edu), Jonah Kastelic (jonahkas@bu.edu), Allison Cho (allycho@bu.edu)

Links: GitHub | Poster | Presentation | Notion Scrum Page | Product

Melanin Rx— Audience Choice Award

Melanin Rx seeks to combat the neglect and dismissal of Black women’s health concerns by developing an AI chatbot that helps users communicate more effectively with medical professionals. Drawing on reputable research studies, the platform aims to serve as a WebMD-style resource grounded in data and evidence that specifically reflects the health concerns of Black women, empowering users with more relevant and informed healthcare information.

Team members: Raniya Delil (raniya@bu.edu), Karrington Riley (kyriley@bu.edu), Ella Hain (ehain@bu.edu), Yilan Hu (lanhu@bu.edu), Yeshi Tsering (ytsering@bu.edu)

Links: GitHub | Poster | Presentation | Notion Scrum Page | Product

Innovation Program Project Gallery

In addition to the award-winning teams, Demo Day Fall 2025 featured a diverse range of student-led projects spanning education, accessibility, sustainability, and civic innovation.

Graceful AI

Graceful AI is an AI-assisted platform that enables users to design and generate their own AI agents using natural language — no coding or programming experience required.

Built using Langflow, an open-source component-based platform for agent workflows, Graceful’s assistant, Hopper, converts user ideas into functional visual flows while guiding them step-by-step through the process. For users unsure of where to begin, Hopper’s ideation feature supports brainstorming by asking targeted questions about the user’s background and problem space. Hopper can also explain how components function, identify inefficiencies or errors, and suggest improvements to better align workflows with user needs.

Team members: Owen Steck (osteck@bu.edu), Hoang Nguyen (hoangng@bu.edu), Daniel Wijaya (dswijaya@bu.edu), Dominic Laiosa (dlaiosa@bu.edu), Lucas Lotze (llotze@bu.edu)

Links: GitHub | Poster | Presentation | Notion Scrum Page | Product

fitcheck

The average American throws away approximately 81 pounds of clothing each year, and while shopping second-hand is one of the most effective ways to reduce textile waste, thrifting can be time-consuming and difficult to navigate. Fitcheck and Fitcheck.nest aim to fully digitize the in-person thrifting experience. Fitcheck allows shoppers to browse live inventories from nearby second-hand stores, making sustainable shopping more accessible for busy or selective consumers. Fitcheck.nest supports thrift store owners by streamlining inventory tagging, pricing, and tracking, creating value for both shoppers and small businesses.

Team members: Chandini Toleti (toletich@bu.edu), Marcus Izumi (slime123@bu.edu), Sky Evans (skye@bu.edu), Kohki Hatori (khatori@bu.edu), Nickola Getchevski (ngetch@bu.edu)

Links: GitHub | Poster | Presentation | Notion Scrum Page | Product

GrantWareAI

Public-sector organizations — from state agencies to school districts — often struggle to identify and apply for grants, a process that is complex, time-intensive, and costly.

GrantWareAI (also referred to as GrantFinder AI) is an AI-powered platform designed to act as an “AI grants consultant.” By ingesting federal and state grant data, the platform allows users to search using natural language queries and receive ranked grant matches, plain-English summaries, eligibility checklists, and auto-generated draft application narratives. The project aims to make critical funding opportunities more accessible to communities.

Team members: Ryan Rodriguez (ryanrod@bu.edu), Janet Liu (jliuj@bu.edu), Adrian Dybacki (adybacki@bu.edu), Gabriel Levi Ramos (glevi@bu.edu)

Links: GitHub | Poster | Presentation | Notion Scrum Page | Product

Signable

Signable is a practice-focused learning hub designed to support American Sign Language (ASL) learners both in and out of the classroom.

The platform offers video vocabulary sets and note-taking tools for learning new signs, along with machine learning and computer vision technology that allows users to practice signing and receive feedback on accuracy and improvement areas. Signable incorporates a customized language model, gamified learning tools such as flashcards and matching games, and ASL-Lex — a researcher-led sign database that includes regional variations — to create a more comprehensive and engaging ASL learning experience.

Team members: Bryan Ayala (bayala@bu.edu), Ariel Diaz (adiaz13@bu.edu), Adrian Rojas (rojasa@bu.edu), Anurag Mathews (anuragm1@bu.edu), Augie Oppenheimer (augieopp@bu.edu)

Links: GitHub | Poster | Presentation | Notion Scrum Page | Product

X-Lab and Practicum Presentations

XC473 Justice Media co-Lab: Police Logs in Natick

The Natick Report is an independent, nonprofit local news publication that has served Natick, Massachusetts, since 2020. Founded to fill critical gaps in local government coverage, the publication specializes in transparency journalism, providing detailed coverage of municipal meetings, public records analysis, and accountability reporting.

The student team built an automated police transparency tool designed to transform inscrutable Natick police and arrest log PDFs into a structured, searchable database. This system enabled journalists and the public to easily see trends and explore the data, addressing the challenge that manual tracking would otherwise require prohibitive effort for a small newsroom. The team created an interface that displays arrest logs as a heat map for Natick, with the goal of creating a model replicable for small community nonprofit newsrooms across the region to enhance police transparency and community oversight.

DS488 – UX Practicum: CDS Website Redesign

The Faculty of Computing and Data Sciences is a catalyst for education, research, and innovation in computing and data science, CDS connects a plethora of liberal arts, science, and professional disciplines with its foundational fields of computer science, computer engineering, mathematics, and statistics.

The goal of this initiative is to elevate the CDS website through innovative design strategy and research, producing a prototype that feels truly outside of the box. The redesign will explore how best to communicate what makes CDS stand out, highlight the achievements of both faculty and students, and position the unit as a sophisticated, intelligent, and creative place. This effort will include a high-level redesign of the entire CDS website while also conducting a deep dive into Spark!’s integration within the site.

DS519 – SE Practicum: Anti-Displacement Tool

The BU Initiative on Cities serves as a hub for urban-related research and teaching, engaging with leaders, policymakers, and academics worldwide to work toward sustainable, just, and inclusive urban transformation.

The student team focused on modernizing the Anti-Displacement Assessment Tool (ADAT), a framework previously developed by the Initiative for the City of Louisville. The ADAT is an open-source tool that evaluates the potential displacement impact of new housing developments by accounting for specific neighborhood factors like rental prices and demographics. While the tool was already fully functional online, the team’s goal was to redesign the user-friendly interface and modernize the tech stack to allow for greater scalability. This enhancement aimed to solidify the ADAT as a replicable model for other cities seeking to implement growth plans that prioritize affordable housing and prevent the displacement of vulnerable communities.

DS539 – DS Practicum: Councilor Zapata: Styrofoam Ban

Boston is trying to ban polystyrene (Styrofoam) foodware in establishments (retail and food). Similar bans or restrictions already exist in over 50 municipalities across Massachusetts. Pholystrene is a pollutant as it does not biodegrade, contributes to microplastics, and is excluded from Boston’s acceptable recyclables, and its main chemical styrene is possibly carcinogenic, posing risks to respiratory and neurological health. At the same time, enforcement and compliance require balancing environmental justice with economic equity. Small businesses need time, funding, and technical assistance to transition to alternatives. This project will support Councilor Zapata’s office in evaluating the impacts and considerations of a Styrofoam ban, specifically with a cost based focus regarding small local businesses.

DS549 – ML Practicum: Identifying Children’s “Stranger Danger” Behaviors

Identifying early risk factors for childhood anxiety is crucial, as many children maintain their anxiety into adulthood. The traditional method for assessing risk, particularly the trait of behavioral inhibition (fear and withdrawal in new situations), involved time-consuming behavioral coding by trained researchers reviewing hours of video footage. Kathy Sem, a doctoral student at the BASE Lab, sought to address this challenge by leveraging advancements in computer vision and machine learning to digitize and automate these assessment schemes.

Building on prior work, the Fall 2025 student team further improved the robustness, scalability, and accuracy of an existing web-based tool. This system analyzes video footage of children in “Stranger Danger” scenarios, using computer vision to track human movement and behavior. By automating the analysis process, the team made it possible to systematically assess risk for anxiety, significantly reducing the manual effort and specialized training previously required for this critical research.

Data Visualization: Harvard ASML: Transparency Hub

The Applied Social Media Lab (ASML) at Harvard’s Berkman Klein Center brings together technologists, researchers, and practitioners to reimagine, rebuild, and reboot social media to serve the public good. ASML is developing and maintaining the Transparency Hub, a platform that aggregates and archives public-facing documents from social media companies, such as privacy policies, terms of service, transparency reports, and community guidelines, to support public interest research and increase public understanding.

The Transparency Hub currently contains public-facing policy documents from over 300 social media companies, scraped and structured into a dataset designed for research, journalism, advocacy, and civic engagement. The Fall 2025 Spark! Data Visualization team will explore how best to present this dataset visually, creating interactive tools or dashboards that allow users to compare companies’ policies, track changes over time, and identify trends across the industry.

DS701- Tools for Data Science: CHAPA: Affordable Housing (Team B)

The Citizens’ Housing and Planning Association (CHAPA) is the non-profit umbrella organization for affordable housing and community development activities in Massachusetts, working to address the state’s extremely tight housing market where affordability and accessibility pose persistent barriers, especially for low-income households and households of color. CHAPA monitors nearly 3,000 permanently affordable homes, but key questions remained about who was applying, where they were applying from, and what systemic factors shaped these patterns.

The student team’s goal for the semester was to analyze and provide insights into these unexplored questions, focusing on geographic trends, demographic representation, and access disparities within CHAPA’s homeownership portfolio data. Specifically, the team identified where applicants lived compared to where they applied, analyzed the geographic radius of their search, and determined how these patterns differed across various demographic groups, including families, seniors, and racial groups. Furthermore, the analysis identified whether factors like marketing strategies, listing sources, or application complexity impacted applicant diversity and the overall equity of access to affordable housing.

DS701- Tools for Data Science: CAIR Media Analysis (Team B)

Council on American-Islamic Relations (CAIR) has hypothesized that there has been a decline and shift in local media coverage related to Muslim and Palestinian communities in Massachusetts since October 2023, particularly in The Boston Globe and MassLive. Prior to this date, these outlets often covered community reports and letters that elevated Muslim voices. After October 7, 2023, CAIR believes there has been reduced coverage, less representation of Muslim authorship, and framing that disproportionately favored Israel. This semester, the student team will explore and test whether these hypotheses hold true.