Project Info

Winner

[MLH] Best Use of ElevenLabs; [Sponsor - Windborne] Best Use of Windborne API

SlugRoute

Inspiration

UC Santa Cruz is famous for its beautiful but unpredictable terrain. A sunny afternoon at Science Hill can quickly become a foggy, wind-swept walk by the time you reach Porter. We noticed that traditional navigation apps are climate-blind. They optimize only for distance and time, not for comfort, safety, or environmental conditions. SlugRoute was created to give students a weather-intelligent navigation companion that understands campus microclimates the same way Slugs do.

What it does

SlugRoute is an AI-powered campus navigation system that redesigns how students move through campus by integrating real-time atmospheric data. Instead of selecting routes based purely on distance, SlugRoute evaluates environmental exposure, physical effort, and weather comfort to recommend smarter paths. Users can prioritize faster travel, lower wind exposure, or more comfortable walking conditions depending on their needs.

How we built it

We focused on a performance-first architecture to maintain smooth real-time responsiveness. The frontend was built using Next.js 16 with Turbopack for fast builds and Framer Motion for fluid UI animations. For intelligence, we integrated Gemini 2.0 Flash to deliver rapid route analysis while using OpenAI GPT-3.5 as a fallback layer to maintain reliability. ElevenLabs was used to generate natural voice guidance that enables hands-free navigation. Windborne Systems provided high-resolution atmospheric data, while Mapbox enabled custom campus geospatial overlays. Auth0 was implemented to handle secure authentication for campus users.

Challenges we ran into

One of our biggest technical challenges was synchronizing real-time wind data with complex campus path geometries. Translating environmental conditions into accurate effort and comfort scores required building a custom scoring model. We also encountered deployment challenges related to managing authentication callbacks across dynamic Vercel environments. Additionally, coordinating real-time AI voice feedback required building logic to prevent overlapping audio during rapid navigation updates.

Accomplishments we're proud of

We are especially proud of the UI and experience quality achieved across devices. Creating a layout that feels polished on desktop while remaining intuitive on mobile was a major design milestone. From a technical perspective, successfully chaining Gemini’s reasoning output with ElevenLabs voice synthesis enabled a fully autonomous voice-guided navigation experience, which felt like a step toward next-generation spatial computing.

What we learned

SlugRoute became a masterclass in system orchestration. We learned that impactful AI systems are built through thoughtful integration of sensors, real-time data pipelines, cloud infrastructure, and user interfaces. The project strengthened our understanding of production deployment workflows, environment variable management, authentication configuration, and AI-to-voice pipelines.

What's next

Our roadmap includes expanding SlugRoute into augmented reality navigation by projecting wind-sheltered routes directly onto the user’s camera feed. We also plan to introduce predictive crowd modeling using historical campus traffic patterns to help students avoid peak congestion. Another major feature in development is group routing, which will calculate optimal shared meeting points and synchronize routes for multiple users simultaneously.

This is a Next.js project bootstrapped with create-next-app.

Getting Started

First, run the development server:

npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev

Open http://localhost:3000 with your browser to see the result.

You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.

This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.

Learn More

To learn more about Next.js, take a look at the following resources:

Next.js Documentation - learn about Next.js features and API.
Learn Next.js - an interactive Next.js tutorial.

You can check out the Next.js GitHub repository - your feedback and contributions are welcome!

Deploy on Vercel

The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.

Check out our Next.js deployment documentation for more details.

Analysis

Compare with all teams

View

Metric

Deepak-karani
8

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only

CSSIn code
Google GeminiIn code
Next.jsIn code
OpenAIIn code
ReactIn code
Tailwind CSSIn code
TypeScriptIn code
JavaScriptClaimed
Node.jsClaimed
PythonClaimed
VercelClaimed

7 of 11 appear in the indexed code. 4 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

112 KB

Source files

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.