Sana Adeel@SanaAdeel

HoloMentorX is an AI-powered contract auditing and mentoring platform built for the Qubic Track, combining the speed of Groq, intelligence of Meta’s LLaMA, and modular automation via Fetch.ai agents. It enables developers to submit smart contracts and instantly receive deep audits, vulnerability analysis, human-readable explanations, and automated tests. Our architecture supports: Groq-accelerated LLaMA inference for fast, detailed contract breakdowns. Fetch.ai-based agents to modularize tasks like auditing, testing, and summarization. A clean, React-based frontend + FastAPI backend for seamless UX. Multi-agent reasoning: multiple LLM calls work together to offer an audit decision and next action. HoloMentorX aims to solve the bottleneck of slow, expensive audits—enabling safer Web3 development for all.

MYSTICA is a dynamic AI-powered quiz app designed to engage users of all ages in an interactive learning experience. By using a free AI key with limited requests, the app generates personalized quiz questions based on the user’s age and subject preference. With each question, users are presented with multiple-choice options and immediate feedback through sound effects and playful owl images, creating a fun and educational atmosphere. The app’s goal is to provide an entertaining yet educational tool that adapts to different age groups, helping users learn while enjoying a game-like environment.

SereniMind – Your AI Companion for Calm, Clarity, and Support is a next-generation AI chatbot designed to provide a safe and supportive space for individuals experiencing mental health challenges. Unlike traditional chatbots, SereniMind remembers previous interactions, enabling users to have ongoing, context-aware conversations that feel more natural and human-like. The chatbot is powered by FastAPI (backend), React (frontend), and deepseek-r1 AI model, ensuring efficient, accurate, and empathetic responses. Users can start new conversations or continue existing ones, with each chat session being uniquely identified and stored securely. Key features include: - Context Retention: Ensures seamless back-and-forth communication. - User-Specific Conversations: Allows individuals to access past messages and continue discussions. - Fast & Secure: Optimized API responses with user authentication. - Scalability: Can be extended to support multimodal interactions (voice, image), multilingual AI, and sentiment analysis. SereniMind is not a substitute for professional help but serves as an empathetic companion that encourages self-care and emotional well-being. With future enhancements like therapist integration, sentiment tracking, and mobile accessibility, SereniMind aims to bridge the gap between AI support and human emotional needs.

Enhancing infrastructure and accessibility for healthcare and education is essential to bridging gaps in underserved regions. This project leverages AI-driven solutions to provide real-time demand scores and actionable insights for effective infrastructure planning. Using advanced machine learning models and APIs, the system helps stakeholders prioritize and optimize efforts in these sectors. For education connectivity, the system evaluates indicators like out-of-school rates, enrollment rates, and geographic data to identify regions with inadequate infrastructure. It uses Random Forest models to predict demand and recommend initiatives like building schools, establishing digital learning hubs, or allocating educational resources in high-need areas. In healthcare, the platform incorporates factors like facility type, ownership type, and population density. It assigns weighted scores to calculate demand and leverages K-Means clustering for regional analysis, combined with Gradient Boosting for accurate predictions. This helps recommend expanding networks, upgrading hospitals, or deploying telemedicine in underserved areas. The project features a user-friendly frontend visualization tool built with React and Google Maps APIs. Users can interactively select regions on a map, view demand scores, explore clusters, and access recommendations in real time. A key highlight is the LLM-based recommendation engine, which generates tailored suggestions based on real-time data. For education, it may suggest building schools or launching e-learning platforms, while for healthcare, it can recommend facility upgrades or mobile healthcare units. These recommendations adapt dynamically to evolving needs, making the platform a valuable tool for governments, NGOs, and private organizations to drive change. This system showcases the potential of AI and large language models in improving infrastructure, fostering inclusivity, and addressing challenges in global healthcare and education.