AI Sentinel: Project EVE

Inspiration

Artificial intelligence is transforming how we learn, work, and make decisions. However, as AI becomes more powerful, it also introduces new challenges. AI can generate convincing but incorrect information, produce biased responses, and be misused for phishing, misinformation, and other harmful purposes. We asked ourselves a simple question:

What if people had an intelligent companion that helped them verify AI before trusting it?

That question inspired AI Sentinel: Project EVE—a platform designed to make AI safer, more transparent, and easier to understand for everyone.

What it does

AI Sentinel is an AI-powered platform that helps users evaluate AI-generated content before relying on it.

The platform analyzes AI responses, provides explainable Trust Scores, compares AI models, generates AI Safety Passports, stores previous safety analyses, and teaches users about responsible AI through interactive training quizzes.

At the heart of the platform is Project EVE, our explainable intelligence engine. Instead of simply labeling AI content as "safe" or "unsafe," Project EVE explains the reasoning behind each evaluation, helping users understand why an AI response may be trustworthy or require additional verification.

Our goal was not just to build another AI assistant, but to create a platform that encourages responsible AI use through transparency, education, and informed decision-making.

How we built it

We developed AI Sentinel using Google AI Studio and Gemini for AI capabilities. The frontend was built with HTML, CSS, and JavaScript, while Supabase provided authentication, database storage, and saved scan history. We used GitHub for version control and Vercel to deploy the application as a publicly accessible web app.

Throughout development, we focused on creating a clean, mobile-friendly interface that makes complex AI safety concepts simple and accessible.

Challenges we ran into

One of our biggest challenges was balancing ambition with practicality. AI safety is a broad and complex field, so we had to carefully prioritize features that would provide the most value while remaining achievable within the hackathon timeframe.

Another challenge was designing an interface that presents technical AI evaluations in a way that is understandable to users with different levels of technical knowledge. We also spent significant time refining the user experience, organizing multiple safety tools into a cohesive platform, and integrating cloud storage to preserve scan history.

Each challenge helped us improve both the technical design and the overall usability of the platform.

Accomplishments that we're proud of

We are proud of bringing multiple AI safety capabilities together into one platform instead of building a single-purpose tool.

We are especially proud of Project EVE, our explainable intelligence engine, because it focuses not only on evaluating AI responses but also on helping users understand the reasoning behind those evaluations.

We are also proud of successfully integrating AI capabilities, cloud services, authentication, saved scan history, responsive web design, and deployment into a functional public-facing prototype within the hackathon timeframe.

What we learned

This project taught us that building AI applications is about more than creating intelligent models—it is equally important to build systems that people can understand and trust.

We gained hands-on experience with AI integration, cloud databases, deployment, responsive web development, and designing explainable user experiences. More importantly, we learned how responsible AI, transparency, and user education can work together to create technology that empowers people instead of overwhelming them.

What's next for AI Sentinel: Project EVE

We plan to expand AI Sentinel with additional AI safety capabilities, richer explainability features, broader model support, enhanced collaboration tools, and more advanced educational experiences.

Our vision is to continue developing AI Sentinel into a trusted platform that helps individuals, educators, organizations, and developers confidently navigate the rapidly evolving world of artificial intelligence.

Our mission is simple: build a future where every AI decision can be understood, verified, and trusted.