Wajeeha Ghazi@Wajeeha00

Atlas is an educational tool designed to turn any collection of unstructured documents (PDFs, PPTs, DOCs) into a structured, highly optimized, and playable learning path. By leveraging the power of AMD GPUs and advanced Large Language Models, Atlas automates the extraction of educational concepts and intelligently deduces their prerequisite relationships. The core pipeline operates in six steps: First, raw documents are parsed and chunked based on semantic boundaries rather than fixed lengths. Next, local LLMs like Gemma, running efficiently on AMD GPUs via ROCm, extract raw learning concepts from these chunks. The system then clusters and deduplicates these concepts using cosine similarity and community detection algorithms. Prerequisite relationships are inferred by evaluating pairs with high similarity and asking Fireworks AI (Llama 3) to determine the learning direction. To ensure the resulting learning path is logically sound, the backend (built with FastAPI) runs cycle detection algorithms to eliminate contradictions, producing a valid Directed Acyclic Graph (DAG). Finally, topological sorting is applied to assign hierarchical tiers (foundational vs. advanced concepts). The final output is rendered via a modern Next.js frontend as a stunning, interactive skill tree. Learners can navigate this tree, taking checkpoint quizzes generated via RAG (Retrieval-Augmented Generation) directly linked back to the source documents. Atlas essentially builds a personalized, gamified curriculum from raw files.

Long Description: BreathGuard AI addresses one of the world’s most urgent health challenges: Chronic Obstructive Pulmonary Disease (COPD), the third leading cause of death globally. Current care models often fail because they are reactive — patients only receive help once symptoms worsen. Our solution shifts the paradigm to proactive and preventive care. Using multi-agent intelligence, BreathGuard AI integrates continuous monitoring of patient vitals with environmental risk data to predict potential exacerbations before they become emergencies. Patients interact naturally with the system using voice-based symptom logging, while a personalized coaching agent guides them on daily routines such as inhaler use, breathing exercises, and activity management. In critical situations, automated alerts instantly notify caregivers or clinicians, ensuring timely response. Beyond patient care, the platform’s design supports hospitals, insurance providers, and healthcare networks with scalable AI-driven tools. By combining predictive analytics, intelligent coaching, and seamless emergency escalation, BreathGuard AI empowers patients to live more confidently while reducing hospitalizations and healthcare costs.

AI-powered PCOS Care Assistant is not just a project. It’s a mission born from my own struggle with Polycystic Ovary Syndrome (PCOS). For years, I lived with confusion, unexplained symptoms, and delayed diagnosis. Like millions of women worldwide, I kept moving from doctor to doctor without answers. PCOS is often misunderstood as “just irregular periods,” but in reality, it’s far more serious. It can affect fertility, cause weight gain, hormonal imbalance, diabetes, skin issues, emotional stress, and even future pregnancy complications. This inspired me to design a one-stop solution that makes PCOS care simple, fast, and personalized. It includes: 1. AI Chatbot for symptom analysis, personalized medicines, and diet guidance (different for teenagers, adults and pregnant women). 2. Ultrasound analysis where users upload scans, and AI highlights cyst patterns with a heatmap to instantly detect PCOS. 3. At-home lab testing, with a simple form and instructions for saliva, urine, or blood samples, collected by a lab technician at the user’s doorstep. 4. Doctor appointment booking, matching users with available doctors based on their schedule. With this assistant, women no longer have to suffer silently or wait years for answers. It provides clarity, confidence, and control , turning confusion into care and empowering women to manage PCOS with ease.

DisasterRelief AI is a real-time, AI-powered platform designed to transform how humanitarian teams respond to natural disasters. Traditional disaster response systems are often delayed, fragmented, and reactive—costing precious time and lives. Our platform solves this by using artificial intelligence to detect crisis zones, assess urgent needs, and coordinate relief operations with unprecedented speed and accuracy. At the heart of DisasterRelief AI is a multi-source data engine that ingests live satellite imagery, geo-tagged social media posts, emergency alerts, and drone footage. Computer vision models (e.g., YOLOv8, UNet) analyze imagery to detect flooded zones, collapsed infrastructure, and fires. NLP models (e.g., BERT, GPT) extract distress signals and supply requests from public posts, enabling localized need detection even in communication-poor areas. This information powers a real-time dashboard that shows dynamic heatmaps, optimized aid routes, inventory status, and task coordination across multiple agencies. The platform also includes a smart logistics planner that generates safe and efficient delivery routes based on road conditions, urgency levels, and available resources. DisasterRelief AI builds a reusable knowledge graph of disaster-prone regions, infrastructure layouts, and response histories—helping organizations plan smarter for future crises. Our system has clear real-world applications: during Cyclone Idai (2019) and the Haiti Earthquake (2021), delays in response were driven by data blind spots. With DisasterRelief AI, responders could have acted faster and more precisely. DisasterRelief AI empowers responders with live intelligence and coordination—bridging the gap between chaos and action.

Our project is an AI-powered SaaS platform designed to simulate real job interviews and help candidates prepare with confidence. Users can input job titles and expertise, and the system generates tailored coding questions and scenario-based prompts. With the help of Vapi AI, the platform conducts interactive voice interviews, mimicking real recruiter interactions. After each session, users receive detailed feedback on their answers, problem-solving approach, and communication skills. The platform also allows users to set daily goals and track their progress, ensuring consistent preparation. This solution is especially beneficial for students, professionals switching careers, or anyone aiming for competitive roles in the tech industry.

Xía is your AI-powered cofounder, designed to accelerate the early stages of launching a startup. It helps non-technical founders bring their ideas to life by generating product plans, investor emails, competitor analyses, and structured task lists — all through a simple, chat-based interface. With Xía, users can go from idea to execution without needing a team of experts. Whether you're drafting your MVP roadmap or crafting a pitch to investors, Xía provides intelligent suggestions tailored to your startup’s vision. Our goal is to empower solo entrepreneurs to launch faster, smarter, and with confidence — all from a single platform.

🌎 Hybrid Hackathon | 💻 Online Build: 3–8 November 2026 | On-site Phase: 8 November 2026 📍 On-site Venue: Pierpont Place 163 W Pierpont Ave, Salt Lake City, UT 84101, USA ✨ Please note that travel and accommodation are not covered.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.

⏱️ Design, build, and deploy trustless AI trading agents. 📅 March 30 – April 12, 2026 🌐 Build AI trading agents that execute strategies using ERC-8004 or Kraken CLI. 🤝 Build solo or in teams to create autonomous trading, risk, yield, or protection agents. 💰 $55,000 prize pool, allocated and shared via Surge and Kraken. Your team should have registered project at early.surge.xyz in order to be eligible for the prize. Get access in your team profile or our discord 🔑 Access to early.surge.xyz If prompted for login credentials, use: • Username: admin • Password: JBRv2xWG7AzwVrLz88

Join our $1,000,000+ startup challenge series powered by Surge 📌 This announcement outlines the launch of a Global Human+AI Exchange — aligning universities, global cities, talent networks, and industry to accelerate human-centered AI innovation, technology transfer, and economic growth. 👉 Read more here ⏱️ 8 days to turn your idea, or existing product, into an investable demo. 📅 February 6 - 15, 2026 • Feb 6 - 14 (Online Phase) - Collaborate and build online with developers and AI innovators from around the world. All projects must be submitted by the end of the online phase on February 14th. 🕙 Doors open at 10:00 AM, first come, first served. • Feb 14 (On‑site Build Day) - Selected participants will be invited to an exclusive in‑person session to refine their projects and connect directly with mentors. • Feb 15 (On‑site Demos & Awards) - Live pitching sessions to a panel of judges and ecosystem partners, followed by the official winner announcement. 🌟 Get feedback from startup mentors and technical experts. 📍 On-site Venue (Feb 14–15): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📲 Real-time on-site updates (SF) For real-time announcements and information during the on-site portion (Feb 14–15), join the LabLab SF Chapter WhatsApp group: 👉 Join the WhatsApp group 🤝 Join solo or with a team. New founders and existing startups are welcome. 🏆 $1,000,000+ in credits, token prizes, perks and funding opportunity. 📍 On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Apply now to build, validate, and pitch with purpose.