Rupsha Debnath@rupsha_debnath_366
1
Events attended
1
Submissions made
India
1 year of experience
About me
I’ve been building with AI mainly through personal and college-side projects where I combine frontend development with AI APIs to solve real problems. Most of my work has been focused on creating practical AI-powered web apps rather than just experimenting with prompts. One project I worked on was an AI-based volunteer coordination platform where I designed the frontend and integrated AI features to help manage task flow, communication, and organization in a smarter way. I also explored healthcare-related AI concepts through a project called “Onco AI,” where I experimented with AI-assisted workflows and user-focused interfaces. Apart from that, I regularly use AI tools for: UI/UX prototyping and rapid development Prompt engineering and response optimization Building futuristic responsive web interfaces Automating workflows and generating structured outputs Debugging and improving code efficiency I’m comfortable working with tools like ChatGPT APIs, modern frontend frameworks, and AI-assisted development workflows. Most of my learning has been hands-on — testing ideas, refining prompts, improving outputs, and turning concepts into usable products. I enjoy building projects where AI actually improves user experience instead of being added just for hype.
🤓 Latest Submissions
AegisNexus AI
AegisNexus AI is a production-style AI governance and adversarial defense platform designed to secure modern AI systems against prompt injection attacks, unsafe instructions, policy violations, and malicious agent behavior. The project combines a FastAPI backend with a cinematic React frontend to create a live operational command center for AI security monitoring and governance simulation. The backend architecture was built with modular FastAPI services and includes: • Real-time prompt threat analysis • Governance guardrails for prompt inspection • Policy enforcement engine • SQLite persistence and audit logging • Telemetry streaming using WebSockets • Threat scoring and response recommendations • Gemini API integration with fallback heuristic analysis • Attack simulation endpoints for testing AI resilience The frontend was designed as a futuristic AI defense interface featuring: • Interactive adversarial simulation sandbox • Real-time telemetry monitoring • Threat visualization dashboards • Incident containment indicators • Live risk score analysis • Dynamic governance metrics • Responsive cyberpunk-inspired UI with Framer Motion animations Users can enter prompts into the simulator to test how the governance engine reacts to malicious or unsafe instructions. The platform evaluates the prompt, assigns a threat level, calculates a risk score, and recommends actions such as BLOCK, REVIEW, or ALLOW. Example attacks include: • Prompt injection attempts • Instruction override attacks • Credential extraction attempts • Jailbreak prompts • Policy bypass requests AegisNexus AI was created to demonstrate how future AI systems can include transparent governance layers, safety orchestration, and adversarial monitoring before deploying autonomous agents into real-world environments.
19 May 2026
