GoGuard: Giving Peace of Mind to Late-Night Riders Through AI-Powered Safety
Late-night rides should end with a safe arrival—not a sense of fear.
Yet for many passengers, especially women, the experience of riding home alone—whether by car or motorcycle—still comes with a feeling of uncertainty. Traditional safety features like SOS buttons are reactive, requiring users to take conscious action in moments of stress or panic. But what if help could arrive before you even asked?
That’s the question Team INTx set out to answer with GoGuard—an AI-powered guardian designed to detect signs of danger in real time and respond intelligently, even when the passenger can’t.
Meet Team INTx
INTx is a team of passionate gamers, technologists, and problem-solvers who came together through a shared belief that technology can—and should—protect people. The team includes:
● Dharmawan Santosa – Product Lead
● Zhafira Elham Fawnia & Uttsada Jason – Developers
● Angie Febrianie – UI/UX Designer
And in case you’re wondering about the team name—yes, it’s a nod to their MBTI types (INTJ and INTP).
Introducing GoGuard: A Smart, Silent Companion for Safer Rides
GoGuard is a real-time AI safety companion embedded within the Gojek app. Its goal? To make rides feel safer without adding complexity or forcing passengers to act under stress.
Here’s how it works:
- Listens passively through your phone mic (with permission)
- Uses LLMs and voice sentiment analysis to identify distress signals—like trembling voice, high-pitched arguments, or threatening keywords
- Considers contextual data like ride time, route irregularities, and speed
-
If risk is detected, it can:
- Prompt the passenger silently
- Share live trip data with a trusted contact
- Alert Gojek’s security team—without the passenger needing to tap anything
This turns GoGuard into a proactive, AI-powered guardian that supports passengers when they’re most vulnerable.
The Tech Behind It
GoGuard’s powerful real-time intelligence is made possible by Alibaba Cloud’s AI infrastructure. Here’s what powers the system:
● Model Studio & PAI – Used to evaluate and select the most effective Qwen model for distress detection
● Qwen LLM – Handles semantic understanding of conversations and detects emotional cues
● EAS (Elastic Algorithm Service) – Enables low-latency model inference during active rides
● ECS (Elastic Compute Service) – Hosts backend services and coordinates real-time voice processing
This architecture allowed Team INTx to move fast, deploy efficiently, and build a solution that’s scalable, cost-effective, and secure.

Solving a Real Problem, Thoughtfully
What makes GoGuard different isn’t just the technology—it’s the human understanding behind it.
Instead of building another emergency button or GPS tracker, INTx focused on making help feel intuitive and invisible. GoGuard is designed for those moments when passengers might be frozen by fear, unsure how to respond, or simply hoping nothing goes wrong.
And it works for both car and motorcycle rides, with no need for extra hardware or complicated activation.
“We wanted to build something that listens, understands, and acts—especially when passengers can’t,” said Dharmawan Santosa.
A Winning Idea at the Global AI Hackathon
GoGuard was selected as the first winning projects in the Alibaba Cloud Global AI Hackathon – Indonesia. It stood out for tackling a deeply relevant issue—rider safety—using practical, well-architected AI. By transforming passive monitoring into proactive protection, it offers a glimpse of what’s possible when empathy meets innovation.
Join the Next Wave of AI Innovation
Inspired by GoGuard? We are too.
Whether you're building for health, safety, sustainability, or education, the Alibaba Cloud Global AI Hackathon is your platform to turn bold ideas into real-world solutions—just like INTx did.
🔗 Register now and build with us
Let’s create AI that truly makes life better—one ride, one person, one breakthrough at a time.
Read previous post:
GoShield: AI-Powered Passenger Safety Built for the Realities of Everyday Rides
Read next post:
Building FinTrack: An AI-Powered Tax Assistant for Freelancers Using Alibaba Cloud
-
-
Alibaba Cloud Project Hub
148 posts | 29 followers
Follow
Comments
-
-
Alibaba Cloud Project Hub
148 posts | 29 followers
Follow
Related Products
-
Token Plan
Build more, spend less. One plan, every modality.
Learn More -
Alibaba Cloud Model Studio
A one-stop generative AI platform to build intelligent applications that understand your business, based on Qwen model series such as Qwen-Max and other popular models
Learn More -
Qwen
Full-range, open-source, multimodal, and multi-functional
Learn More -
QwenWork
QwenWork is dedicated to helping employees strengthen their professional competitiveness in the AI era and to enabling enterprises to improve organizational effectiveness.
Learn More
More Posts by Alibaba Cloud Project Hub
- Aftershock: The Disaster Simulator That Grades Qwen Agent Societies
- NaLog Agronomist Agent: An Agronomist With Perfect Memory in Every Farmer's Pocket
- FORGE: The Hands-Free Voice Copilot for the Technician With Greasy Gloves
- Split Decision: Nine AI Judges, Two AI Journalists, and a Verdict You Can Verify
- Dailies: The Quality-Control Layer AI Video Was Missing
- Qwen Memory Agent: Treating Memory as a Measurable Engineering Problem
- Drama916: Cinematic Vertical Stories, Without the Crew
- ColdGuard: Is This Vaccine Safe, or Has It Already Degraded?
- Sentinel Qwen Ensemble: The Autonomous Forensic Investigator That Can't Bluff
- Tarmac: Five AI Agents Negotiate the Storm, and One Mediator Signs the Ruling