What the rooms shipped.

Aviraj Mohanty

It provides a ready-to-use HTML5 Canvas template with a pre-configured game loop. It allows you to immediately start coding web games or visual experiments without setting up any external tools or dependencies.

“I didnt experience any surprises. However, what is typically most surprising about this specific setup is how capable vanilla JavaScript and the HTML5 Canvas API are on their own. It proves you don't need heavy engines or complex frameworks to build fluid, high-performance prototypes.”

Deepraj Singha

Introducing Artrix: Ever wished interacting with an AI felt more like talking to a friend and less like sending emails? Well, say less because I got you covered. It all started from a singular question: can a machine(ML model) react, get angry or smile at your suggestion? And while we're still figuring out where the road to AGI leads, I wanted to build something that bridges that gap, this is a early prototype powered by gemini(LLM) driven by Rive(Animations).

“It was quite challenging to build, but using Antrigravity IDE was very nice and easy to work on, and Firebase to deploy and connect the backend was very nice and easy”

Deepraj Singha

I built Arcane Mage, a fully browser-based game that uses Three.js and WebGL. 🔥 6 Procedural Elemental Abilities 🌌 9 Dynamic Biomes 👹 Smart Tactical Enemy AI 🛠️ Tech Stack: Three.js | WebGL / GLSL | JavaScript | Vite

“I built a procedural particle game system in which in which i used Antigravity for coding using Gemini's latest version, which was very helpful, and deployed it on Firebase for evaluation and easy deployment and access”

haziq farhanAI Builder Day at NYU School of Engineering · Kartik Derasari

Anatomy Atelier is an interactive 3D human anatomy and biology learning platform built for medical students, educators, and SPM Biology candidates. It combines real-time WebGL 3D organ specimens with an intelligent RAG search engine powered by Gemini API to query official syllabus textbooks. Learners can isolate organ tissues, simulate biological metrics, and ask physiological questions with instant, verified textbook citations.

“I expected RAG textbook ingestion and 3D WebGL rendering to create heavy latency, but pairing Gemini API with structured retrieval delivered instant, context-aware anatomical answers while maintaining a smooth 60fps canvas.”

Vasireddy Yasaswini

Vonage Interactive Onboarding Tutorials

“I was able to talk to Bob Marley in Italian.”

Ezgi Bilaloglu

Add Leonardo AI phone agent workshop implementation

“It was super fun to be able to change the voice, tone even accent and mood”

Ahsan Tahseen

An voice agent built on Flue framework with Vonage API for voice.

“It was nice to develop it.”

Barshat Pradhan

This project creates a telephone-based AI character that lets people call a Vonage phone number and speak with an AI acting as Leonardo da Vinci.

“How easy it has become to mage AI agent with less code using frameworks. That does the heavy lifting”

Adil Sabir Azeez

This project is a real-time voice agent that lets users dial a standard phone number to interact with a custom AI persona. Built for developers looking to integrate telephony with streaming LLM pipelines, it serves as a working boilerplate for handling bi-directional audio streams and system prompts. It's a quick way to see how standard voice APIs stack up against modern conversational AI without needing heavy infrastructure.

“I expected setting up telephony WebSockets and call state management to require heavy boilerplate. Surprisingly, Vonage’s Flue framework abstracted away all that complexity out of the box, letting me spin up a fully functional AI voice agent in just a few lines of code.”

Oley M

APO-HAL-EMS (Agnotic Policy Optimizer / Hardware Abstraction Layer For Energy Management Systems) is an architectural framework and universal governance layer designed for critical infrastructure control systems and energy management systems. ​It provides deterministic validation of automated, AI-driven, and human operator decisions before actions are committed to physical hardware or control networks.

“I thought I'd have to do more work by constantly correcting and re-checking that my prompts were being followed with accuracy throughout the build. Gemini was pretty solid and made the process so much smoother, creating much less work for me due to high precision and follow-through.”

Vaibhav ChaudhariAI Builder Day at NYU School of Engineering · Kartik Derasari

SensePath is a voice-first accessibility assistant designed for blind and low-vision users. It combines Gemini Live, multimodal vision, and Google Maps Platform to help people navigate the last few meters of a journey—finding entrances, benches, elevators, and understanding their surroundings through natural conversation. The standout feature is its ability to seamlessly switch between navigation, object finding, and immersive scene descriptions while keeping the interaction hands-free and acces

“We expected navigation to be the hardest problem, but the real challenge was making AI know when not to speak. Designing an assistant that gives timely, concise guidance without overwhelming or distracting the user turned out to be just as important as the underlying AI itself.”

Durjoy SenAI Builder Day at NYU School of Engineering · Kartik Derasari

HarmonicBlend is an AI-powered, browser-based DJ and stem mashup workstation that allows users to search any song on YouTube Music and turn it into a professional-grade remix in real time. The platform features dual interactive vinyl turntables, scrubbable waveform timelines, 3-band EQs, lowpass/highpass filter sweeps, crossfader controls, and an offline WAV exporter that lets users render and download their completed mixes directly to disk, as well as using Facebook's Demucs ML to create stems.

“Using Gemini within Google Antigravity to build this project was a leap in autonomous, agentic software engineering. Its crazy how Antigravity reasoned across full-stack boundaries, making Python Flask backends, setting up PyTorch ML pipelines, and coding complex Web Audio API DSP frontend engines, something I would need months of training and understanding to build.”