Stories from Hack Your Summer
Hack Your Summer is a community built around learning by doing. Explore stories from students, mentors, and organizers, discover the projects taking shape this summer, and find practical insights on building, collaborating, and launching your career.
Three Projects, Three Completely Different Kinds of Work
Not every project in Hack Your Summer looks like the others. These three are from the same session, built in the same four weeks, and they have almost nothing in common except that each one started as an idea someone cared about enough to actually build.
Not every project in Hack Your Summer looks like the others. These three are from the same session, built in the same four weeks, and they have almost nothing in common except that each one started as an idea someone cared about enough to actually build.
Mapping Where Stroke Risk and Care Deserts Overlap
Every 40 seconds, someone in the United States has a stroke, and their chances of surviving and recovering well depend heavily on how quickly they can reach care. That gap between risk and access is exactly what the Stroke Burden Index was built to make visible.
Jane came in with a clear question: where do high stroke risk and poor access to care overlap worst? She posted the idea on day one, teammates joined within hours, and together the team — Jane, Cathleen, Mikko, Nitya, and Ngan — built a polished, publicly accessible site that scores all 91 counties across New York, New Jersey, and Connecticut on a combined index of stroke vulnerability and care access. The dashboard draws on data about local demographics, health risk factors, and distance from healthcare resources to surface the specific communities where public health intervention would have the highest impact.
The Stroke Burden Index main page, accessible at https://palism1.github.io/stroke-burden-index/
The finding they published is specific and striking: 12 stroke care deserts — high risk and poor access — all in rural upstate New York. The results can support public health planning, healthcare resource allocation, stroke system planning, and future research by highlighting communities where targeted interventions may have the greatest impact.
The full site includes an interactive dashboard, a plain-language methodology page, a documented data pipeline drawing on CDC, Census, CMS (Centers for Medicare & Medicaid Services), HRSA (Health Resources and Services Administration), and state stroke registries, and a reproducible automated pipeline that keeps every number traceable. This is the kind of work that takes months in a research setting. This team shipped it in four weeks, documented it thoroughly, and made it publicly available for anyone to read.
A Free Store, Made Easier to Find and Use
Cleo is an Ada Comstock Scholar at Smith College, a program for non-traditional students returning to higher education as adults, where their focus is on critical disability studies and interdisciplinary design.
Cleo’s Hack Your Summer project didn't involve code. It didn't involve a dataset. It involved walking into Redistro, a mutual aid collective and free store in their community, and asking: what would it take to make this space genuinely welcoming and accessible to everyone who needs it?
View of the interior at Redistro (photo via https://redistro.org/photo-gallery/)
The store is a real resource. But it's also hard to find on Google Maps, lacks signage, and can be difficult to navigate once you're inside. Cleo's project includes UX research through surveys and interviews with both visitors and organizers, a logo redesign for physical and digital wayfinding, exterior signage, and a full interior access map.
The plans for access mapping work alone are comprehensive: a physical map near the entrance, an audio guide with both conventional and QR code options, tactile elements, color-coded store sections with matching signage, and large-print versions of everything. Each of those is a design decision that requires thinking carefully about who the store actually serves and what barriers they face, rather than designing for a generic visitor who doesn't need any of it.
Cleo worked in Figma, ran accessibility surveys with store visitors, and coordinated directly with Redistro's organizers throughout. The project is scoped to continue well beyond the four weeks of HYS, with the program serving as the starting point for a longer-term design relationship with the organization.
Turning Litter Cleanup Into a Game
Early in the session, Ishi posted an idea for a sustainability project in our HYS Discord. Ella replied that same day, and by the end of the first week a team of four, Ishi, Ella, Trey, and Neha, had decided to build it together. Trey, a recent UNC grad in CS and Studio Art, brought UI/UX experience. Ishi, also at UNC, took the lead on the backend. The concept was simple enough to sketch on a napkin: what if picking up litter worked like Strava, with sessions, stats, streaks, and a reason to keep going?
The app they built is called Litter Quitter, a cross-platform mobile app that gamifies community litter collection. It runs on React Native and Expo, uses GPS to track cleanup sessions in real time, lets users drop pins at pickup locations with optional photos, and accumulates points redeemable for local business coupons. On the backend, the team is building out a FastAPI service backed by PostgreSQL to handle the shift from local device storage to a shared, persistent data layer.
From napkin sketch to working prototype: early wireframes for the dashboard (left) alongside the current build (right), showing session stats, streaks, and recent walk history.
Personal stats, day streaks, community-wide impact totals, and leaderboards give users a reason to come back. The idea behind the rewards system is to loop in local businesses as partners, turning litter cleanup into something that benefits the whole neighborhood, not just the people picking things up. The team is actively working on bringing businesses on board, formulating interview questions and talking to potential users to understand what would make the partnership worthwhile on both sides.
By week three, the team had a working single-user prototype with a live map feature. Looking ahead, the team is also exploring a choropleth map that would shade neighborhoods by litter density, giving users a visual read on where cleanup efforts are needed most. The next problem was a hard one: How do you turn a working demo into a real multi-user platform with real data? That gap, from "it works on my phone" to "it works for everyone," is where a lot of apps stall out. The core of the idea is real enough to use and the team is still working through it as they continue with our second 4-week sprint.
The Stroke Burden Index, Redistro Accessibility Visioning, and Litter Quitter were all built during Hack Your Summer Session A, 2026.
Sorting It Out: Solving a Recycling Problem from Two Angles
Andrea and Abhay never formally teamed up during Hack Your Summer. They worked on separate projects, in separate tracks, with separate goals. But they were both trying to solve the same underlying problem: recycling sorting is broken, and technology should be able to fix it.
Andrea and Abhay never formally teamed up during Hack Your Summer. They worked on separate projects, in separate tracks, with separate goals. But they were both trying to solve the same underlying problem: recycling sorting is broken, and technology should be able to fix it. So they stayed in conversation throughout the program, sharing resources, comparing notes, and exploring the problem from complementary perspectives, each going deep on the parts that matched their own skills and interests.
Andrea: Teaching a Model to See Recycling
Andrea, who recently completed her Master of Science in Analytics at Georgia Tech, came in knowing she wanted to work with computer vision in an industrial setting but not yet sure how. Through conversations with Abhay, she found something she wanted to solve. The problem was specific and real: Materials Recovery Facilities (MRFs, the places that actually process the single-stream recycling you put in your bin) have to sort incoming material fast and accurately, and contamination between material types is a serious, expensive problem. She spent the first couple of weeks researching object detection models before landing on YOLO11, a fast, real-time detection architecture developed by Ultralytics well suited to high throughput conditions.
Andrea couldn't visit a MRF but she still got to know her datasets by interrogating her own recycling bin. Here her cat is helping investigate and has been classified by Andrea’s first model as “soft plastic”. (It has since been confirmed that cat is soft but not plastic.) This classification error makes sense when you look at the dataset used to fine tune the model.
Finding the right dataset took just as much effort. Ultimately she chose the ZeroWaste dataset from Boston University, built specifically to capture the extreme clutter and highly deformable objects found in real MRF environments, and augmented it with items from the TACO dataset (Trash Annotations in Context, an open image dataset of litter taken under diverse environments) to address class imbalance. She converted the ZeroWaste dataset into YOLO format with four classes (rigid plastic, cardboard, metal, and soft plastic), and fine-tuned her own YOLO11 model on it.
Then she ran it! Fifty epochs, on her own computer, over six hours of training time. The results were promising enough to make the next problem clear: she needed to speed up hyperparameter optimization, and started researching Optuna, an open-source framework for automating that search, as the next step.
By the end of the session, Andrea was also sitting with a bigger question: what does it actually mean to learn when AI is doing the coding for you? A HYS mentor offered a response that stuck with her: you're still bringing your own knowledge and curiosity, and that's what lets you push back on the AI and ask better questions. She finished the session wanting to slow down enough to understand what her YOLO model was actually doing, not just whether or not it worked. Andrea plans to use this as an opportunity to learn how to build with AI while deepening her own skills and knowledge.
Sample image from ZeroWaste dataset, labeled by fine-tuned YOLO11 model.
Abhay: Building the Machine That Does the Sorting
Where Andrea was training a model to identify materials, Abhay was building a physical system to act on that identification. A mechanical engineering sophomore at Cal Poly San Luis Obispo specializing in mechanical design and hardware, he came in without a settled idea, so he began reflecting on problems within his own community. After experiencing the challenges of his university’s inefficient recycling system firsthand, Abhay developed the idea for AutoSort and quickly committed to bringing it to life.
His scope narrowing was deliberate and engineering-minded: instead of sorting all recyclables, he focused exclusively on aluminum and glass, the two material types with the highest recovery value in real recycling economics. The device uses sensors to identify incoming material, with an Arduino Uno translating that sensor feedback into precise movements from servo motors that physically separates it accordingly. Abhay’s comfort zone was the hardware: the circuit schematics, the mechanical design, building the physical sorting mechanism. The biggest stretch came from integrating sensors and building the machine learning model to classify incoming materials. He trained the model offline in Python on his computer before deploying it as a compact on-device classifier that could make sorting decisions in real time, the same underlying challenge Andrea was working through from the software side.
AutoSort in action. An Arduino Uno translates sensor readings into precise movements from the servo motors, allowing the prototype to identify incoming material and physically sort it in real time.
By the final weeks he had a working prototype, sensor and sorter together, distinguishing aluminum and glass from other materials in real time. The video of an apple core and a piece of aluminum foil moving through the device and getting correctly separated shows that AutoSort was a big step in the right direction toward solving the problem.
In building AutoSort, Abhay learned that the engineering process is rarely linear. Sometimes progress meant making the system work; other times, it meant finding ten new ways it could fail.
Collaboration: Another Kind of Teamwork
What makes this pair of projects notable isn't just that two people worked on similar problems. It's that they recognized the overlap early and kept learning from one another throughout the program. They stayed in conversation throughout, sharing datasets, comparing approaches, and helping each other think through decisions neither had to make alone.
They weren't a team. But taken together, their work illustrates another kind of teamwork: independent builders making each other's work better simply by building alongside one another. That's exactly the kind of connection Hack Your Summer hopes to create.
Andrea Wackerle's computer vision for recycling sorting project and Abhay Sivaraman's AutoSort prototype were developed during Hack Your Summer Session A, 2026.
An Archive Built by Many Hands
Every community has people whose stories rarely get written down. Millie set out to change that with The Living Index, a literary archive built around short portraits of everyday people. With help from two Hack Your Summer teammates, she turned the idea into a working platform. Now, anyone can contribute a story and help grow the archive.
Millie showed up to Hack Your Summer without a team and without knowing how to build a platform. She had an idea, though: a literary archive made of short portraits of ordinary people, written by the people who know them. A retired schoolteacher. A bodega owner. A bartender who remembers your order. She didn't know yet what form it would take, only that she wanted a way to preserve those kinds of stories.
She found Spencer, a recent UX design grad who was still hunting for a project of his own. A few days later, Deepi, an art history student with a strong instinct for how stories hold together structurally, joined too. None of them had worked together before.
The team came together the way most real projects do, through conversation, not assignment. Millie shaped the editorial voice and the submission process. Spencer turned it into an actual interface. Deepi thought about how the whole archive should function as a system, the kind of structural thinking her art history background was good for. Building from three different design vocabularies wasn't free. Handing off files between someone with a UX degree, a journalism/anthro major, and an art historian took some effort to sort out. But it also meant nobody had to bring everything themselves.
By the end of two weeks, they'd already shipped an MVP version of The Living Index, a website where anyone can submit a portrait of someone in their life, have it reviewed, and see it published to a permanent map. Along the way, the sharpest question they got wasn't about design. It was about who owns a portrait once someone else writes it. That's the kind of question a project only earns once it looks real, and the team took it seriously, folding it into how they thought about editorial review from then on.
The Living Index home page, where you can access the live archive.
Overnight, Millie didn't become a programmer, Spencer didn't become a journalist, and Deepi didn't become a UX designer. That was never the plan! But they built The Living Index anyway, together, with each doing the part only they could do.
The first portrait submitted by Millie on The Living Index, now available to read here.
Want to Get Involved?
If there's someone in your community whose story deserves to be remembered, a neighbor, coworker, family member, or familiar face from your block, The Living Index wants to hear about them. You don't need to be a writer. You just need to be someone who's paying attention. The site includes a simple submission template to help you get started.
The living Index is also looking for collaborators with experience in social media, storytelling and publishing, illustration and design, web or product development, and legal or consent advising. It's an early-stage project with plenty of opportunities to help shape what comes next, including future plans for audio storytelling.
To contribute, get in touch through The Living Index website or email Millie at emileepolzin@gmail.com. If you're an early-stage investor interested in supporting the project, she'd love to hear from you too.
The Living Index is open. Come share who matters to you.
Mind the Gap: A Transit Project in Progress
A graduate student interested in climate and urban systems, Sasha arrived at Hack Your Summer with three project ideas. After getting feedback from the community, she narrowed her focus to one city she knows well: Tampa.
That decision became the foundation for a sophisticated transit equity dashboard, and a lesson in why the best projects often begin by thinking smaller.
Sasha Patil didn't spend her first week at Hack Your Summer building. She spent it figuring out what was worth building.
A graduate student interested in climate and urban systems, Sasha arrived with three ideas and posted them in the HYS Discord looking for feedback. The advice she got back was simple: stop thinking about the whole country. Pick one place.
She chose Tampa. It wasn't a random decision. Sasha lives in the area, and she wanted to build something that could be useful to the people and communities she already knew.
As she dug into the data, the project evolved. Instead of asking where extreme heat would hit hardest, she found herself asking a different question: where do people most need public transit, and where is it falling short?
The result was the Tampa Mobility Gap Explorer, an interactive dashboard designed to help City of Tampa and Hillsborough County planners visualize gaps in transit access.
The dashboard's main view displays a Transit Gap Score from 0–100 for every census tract, combining factors like household vehicle ownership, disability rates, income, and proximity to bus stops. Planners can also explore each underlying layer individually.
The Explorer layers a transit system map with information about the people who are most likely to rely on it, including age, income, disability status, and household vehicle ownership. It also highlights major employment centers to identify neighborhoods where better transit could have the biggest impact on connecting residents to jobs.
Here, the dashboard highlights neighborhoods where poverty rates are high but transit access is limited. The color-coded map helps planners quickly identify areas with the greatest transportation gaps.
Behind the scenes, Sasha combined multiple public datasets into a single interactive tool and developed a Transit Gap Score to identify places where high community need, nearby jobs, and limited transit overlap. The result is more than a map. It's a way to help planners prioritize where future transit investments could make the biggest difference. The platform also features an Infrastructure Scenario Simulator that lets planners test potential improvements and see how neighborhood accessibility changes.
The Infrastructure Scenario Simulator lets planners select a neighborhood and test a proposed transit investment. The dashboard estimates outcomes such as newly accessible jobs and improvements in neighborhood walkability.
Just as importantly, Sasha documented the work the way professional teams do. Her GitHub repository includes the underlying census and transit datasets, a modular Python pipeline with clearly separated processing steps, and the deployed interactive dashboard. By sharing the full workflow, Sasha makes it easy for others to understand how the project was built, reproduce the results of her analyses, and build on her work. The repository tells the story behind the dashboard, making it a much stronger portfolio piece than a finished visualization alone.
Like many Hack Your Summer projects, this one changed shape as Sasha learned more about the problem she wanted to solve. Sasha shared rough ideas before she had anything built, accepted feedback that meant narrowing her scope, and let the project become something different from what she originally imagined.
That's often what building looks like. The best projects don't always begin with the perfect idea. They get better because you're willing to ask for feedback, change direction, and focus on solving one real problem for one real community.
The Tampa Mobility Gap Explorer is still evolving, but it's already a great example of starting small to solve a meaningful problem. Rather than trying to improve transportation everywhere, Sasha focused on one city she knows well, and built something that could make a real difference there.
Interested in building something for your own community? Registration for Hack Your Summer Session 2 closes Friday July 10 at midnight Pacific. We'd love to see what you can build.
The Right Teammate Can Change Your Project
When Mateo joined Hack Your Summer, he wasn't looking for something to build from scratch. He was looking for an engineering problem.
A day later, he found Nathan.
When Mateo joined Hack Your Summer, he wasn't looking for something to build from scratch. He was looking for an engineering problem.
A PhD student at the University of Illinois Urbana-Champaign studying aerospace engineering, Mateo spends most of his time thinking about 3D printing, composite materials, and manufacturing. When introductions started in the Hack Your Summer Discord, he posted exactly that. If anyone was building something that needed engineering or fabrication, he'd love to help.
A day later, he found Nathan.
Nathan, an undergraduate studying computer science, had already been developing “ClickSafe”, a personal emergency alert device inspired by products like Life Alert but designed for much smaller communities. Instead of automatically contacting emergency services, ClickSafe lets the wearer alert the people most likely to help first, whether that's family members, trusted friends, or campus security.
Nathan already had the electronics, wireless communication, and an early prototype. What he didn't have was a product enclosure someone would actually want to carry.
Left: Nathan's prototype esp32 board for transmitter mounted on battery. Right: The other side of the battery with charging port and transmitter.
Mateo immediately saw where he could contribute.
Rather than building another software feature, he offered to redesign the physical housing. They jumped on a video call, talked through the hardware, and naturally divided the work. Nathan focused on the electronics, networking, and embedded software. Mateo took ownership of the enclosure, refining the CAD model and preparing it for 3D printing.
Mateo’s CAD model of physical enclosure for ClickSafe.
It's an easy detail to overlook, but it's one that shows up on real engineering teams all the time. Not every collaborator joins at the beginning. Sometimes the most valuable contribution is recognizing where someone else's project needs your particular expertise.
The project is still evolving. Nathan continues refining the networking architecture while Mateo iterates on the printed enclosure, fixing design issues, adjusting the model, and turning digital designs into physical prototypes that can actually be held, tested, and improved.
That cycle is the reality of hardware development. You don't just write code and press run. Every iteration means redesigning parts, waiting on a printer, testing the fit, discovering the next problem, and printing again.
Mateo showing a 3D printing of the ClickSafe enclosure.
As the first Hack Your Summer cohort wraps up, ClickSafe is becoming something neither student would have built alone. Nathan's idea now has a purpose-built physical form, and Mateo found exactly the kind of engineering challenge he was hoping to tackle when he joined the program.
If you're wondering whether you need to arrive with the perfect idea, or whether your skills fit someone else's project, ClickSafe offers a different perspective. Some of the best collaborations begin with a simple conversation. Sometimes the most valuable thing you build during Hack Your Summer isn't your own idea. It's the missing piece that helps someone else's come to life.
Think you'd rather join an existing project than start from scratch? Or maybe you're still looking for the right idea or teammates?
That's exactly what the next Hack Your Summer cohort is for.
Registration for Session 2 closes soon! If you're curious about building something real this summer, now's the time to sign up!