.png&w=256&q=75)
Hamna Shahid@hamnashahid48042292
2
Events attended
2
Submissions made
Pakistan
1 year of experience
About me
I am an aspiring AI enthusiast with a growing interest in artificial intelligence, Python, and technology. I enjoy learning new skills through hands-on projects and hackathons. Currently, I am building my first AI projects while contributing to research, documentation, and project coordination. My goal is to continuously improve my technical skills, collaborate with talented teams, and eventually build impactful AI solutions and startups.
🤝 Top Collaborators
.png&w=640&q=75)
.png&w=640&q=75)
🤓 Latest Submissions
LectureAI
LectureAI helps university and college students turn recorded lecture audio into organized, exam-ready study material — automatically, without writing a single note by hand. A student logs in, selects or creates a subject (like "Programming Fundamentals" or "Calculus"), and uploads a lecture recording. The audio is transcribed using Speechmatics' Melia 1 model, which is purpose-built for multilingual, code-switched speech — meaning it accurately handles lectures spoken in English, Urdu, or a natural mix of both, common in many classrooms. The resulting transcript, always in English, is then processed by four specialized AI agents powered by Claude Sonnet 5: a Summarizer that captures the lecture's main topics and flow, a Key Concepts Extractor that pulls out important terms, definitions, and formulas as a cheat-sheet, a Confusion Highlighter that flags unclear or rushed parts of the lecture with simplified explanations, and a Memory/Continuity Checker that compares the lecture to the student's most recent previous lecture in the same subject, showing exactly how the two connect and clearly displaying that previous lecture's date. Each agent produces its own downloadable PDF, giving students four focused, ready-to-use study documents per lecture. Every student's data is kept private through Google OAuth authentication and Supabase's row-level security, and lectures are organized by subject so the Continuity Checker always compares against the correct prior lecture. Built entirely on native.builder, LectureAI integrates two AI Factory hackathon technology partners: Speechmatics for transcription and AI/ML API (Claude Sonnet 5) for the four content agents — turning a genuinely time-consuming student problem into a fully automated, exam-ready workflow.
10 Aug 2026
CareLoop - Catching Caregiver Burnout Early
Family caregivers looking after aging parents or sick relatives often don't notice their own burnout until it's already a crisis. There's rarely time to reflect, and by the time exhaustion becomes visible to others, the caregiver has usually been struggling alone for a while. CareLoop was built to catch that decline earlier, fitting into a caregiver's day instead of adding another task to it. The idea is simple: a caregiver writes or speaks a short journal entry about their day, the way they'd say it out loud to a friend. CareLoop reads that entry and reflects back what it notices across five areas that tend to surface first in burnout: sleep loss, isolation, resentment, physical strain, and emotional exhaustion. Each entry is scored gently, not clinically, and saved so the caregiver sees a trend over time rather than one isolated bad day. When strain builds, CareLoop surfaces relevant support, like local respite care, caregiver support groups, or counseling, matched to whatever's showing up most. Under the hood, a FastAPI backend scores each entry using an AI model (Gemini, or Fireworks hosting Gemma), with a free rule-based fallback so the app still works without an API key. Entries are stored simply in a local JSON file, so the data pipeline stays transparent. The frontend is a single, custom-designed interface built to feel calm and human rather than clinical, with a signature trend line that reads more like a gentle pulse than a corporate dashboard. Voice input is supported too, so caregivers can speak an entry instead of typing when they're too tired to write. The whole app is containerized with Docker, backend and frontend as separate services tied together with Docker Compose, ready to run on AMD Developer Cloud infrastructure.
13 Jul 2026
