Muhammad Zubair Zafar@zubair480

Electric Safe is a fully on-device Android application that guides industrial electricians through the Lockout/Tagout (LOTO) safety procedure using a Vision-Language Model (VLM) running on the Qualcomm Hexagon NPU via ExecuTorch and QNN. How it works — 5-screen state machine: Start — Dark industrial UI with a single "Start Session" button and a model selector (SmolVLM 500M / InternVL3 1B). Add Documents — Import equipment manuals via the SAF PDF picker or use the bundled PowerFlex 753 VFD manual. PDFs are processed on-device using PDFBox with regex-based fault code extraction. Live AI Session — Push-to-talk speech input (offline, EXTRA_PREFER_OFFLINE) and on-device TTS. Upload a photo of the VFD fault display; the VLM reads the fault code (e.g. F071 OC1) and matches it to the manual's meaning. A live NPU: X ms latency readout shows real inference time. Guided LOTO — Four camera-gated verification steps: Breaker B-201 OFF, Breaker B-205 OFF, Lock & Tag applied, MCC Cabinet open. Each step requires the VLM to verify the correct breaker identity and state (OFF/ON) with a minimum 0.70 confidence threshold. Identity mismatches trigger a red "WORK BLOCKED" card with expected vs detected values. Permit — Generates a timestamped LOTO evidence PDF on-device using android.graphics.pdf.PdfDocument, embeds captured photos, and allows sharing via FileProvider. Architecture: Single-activity MVVM with state-machine navigation (no NavController). The CaptureDetectionSource interface abstracts detection — mock mode (clickable demo) and real VLM inference drive the exact same code path. Model files are side-loaded via adb push to external storage (industrial MDM pattern), falling back to bundled assets. Privacy: No INTERNET permission declared. Camera capture, VLM inference, PDF generation, speech recognition, and TTS all run locally on the Snapdragon Galaxy S25 Ultra. Nothing leaves the device.

Agentic Audit is a proactive, multi-agent compliance monitoring system designed for enterprise organizations. Instead of relying on manual searches or reactive LLM prompts, our platform utilizes an asynchronous Python backend to continuously monitor highly regulated portals, such as the SEC or EU data privacy boards. By leveraging Bright Data's Web Unlocker and Scraping Browser, our system successfully bypasses the geo-blocks and heavy JavaScript barriers that typically block standard bots, allowing us to reliably capture raw regulatory text and timestamped screenshot evidence. Once our monitoring engine detects a change via SHA-256 hash comparisons, it triggers a multi-agent AI swarm. These agents analyze the text diffs, strip away the legal jargon, and map the updated regulations directly against internal company controls. The final output is delivered to a React dashboard where compliance officers can view a side-by-side comparison of the AI's risk assessment and the verified Bright Data screenshot. The system goes beyond basic summarization by providing actionable, auto-generated engineering tickets for immediate remediation, turning raw web data into operational enterprise security.

Navi is a cutting-edge, AI-powered learning tool that is designed to adapt to your unique needs and learning style. Whether you're a student looking to improve your grades, a professional looking to develop new skills, or simply someone who wants to learn something new, Navi can help you achieve your goals. With access to a vast library of indexed Truth Data stored in Vector Datastore and powered by OpenAI's GPTurbo API, Navi offers a one-of-a-kind personalized learning experience. This means that the more you use Navi, the more it learns about your individual needs and preferences, and the better it can adapt to your unique learning style. This not only makes learning more engaging and effective but also helps to build your confidence and self-esteem. One of the great things about Navi is its flexibility. Whether you prefer to learn on the go or in the comfort of your own home, Navi can be accessed from anywhere, at any time. This means that you can fit your learning around your busy schedule and never miss a beat. With Navi, learning has never been more convenient or accessible. Overall, Navi is a revolutionary learning tool that offers a one-of-a-kind personalized learning experience. Whether you're a student, professional, or lifelong learner, Navi can help you achieve your goals and reach your full potential. Can you input this text instead

It is a web application that is designed to generate code using AI21 API. It uses flask at it's backend and HTML,CSS,js,bootstrap on its frontend.

🌉 On-site Only Hackathon | 📅 June 27–28, 2026 | 📍 San Francisco, CA This is an in-person hackathon in San Francisco for selected participants. Capacity is limited to 150 people, teams must include 3–5 members, and there is no online or hybrid participation. Build real-time AI apps that run directly on Snapdragon-powered mobile devices using ExecuTorch. Selected teams will get Samsung Galaxy S25 Ultra devices on-site for building, testing, and live demos. 📍 On-site Venue (June 27–28): The Web Data Loft by Bright Data 625 2nd St, San Francisco, CA 📱 Samsung Galaxy S25 Ultra devices provided on-site for selected teams 🧠 Learn from Qualcomm and Meta experts through workshops, mentorship, and hands-on support 🏆 Prizes include Meta Quest 3 headsets, Ray-Ban Meta AI Glasses, and post-event project support 🧑‍💻 Apply now to build the future of on-device AI with ExecuTorch and Snapdragon. Once pre-approved, you will receive further instructions on how to complete the acceptance process. Application deadline: June 17, 2026, at 11:59 PM PDT.

🌍 Hybrid Hackathon | 💻 Online Build: May 25–30,2026 | 📍 SF Onsite Finale: May 30–31,2026 We’ve unlocked the web for your AI. Now build what wasn’t possible before. Build AI agents with live web data, then join the SF onsite finale at Bright Data’s new Web Data Loft. 🚀 The onsite experience will take place during the opening of Bright Data’s new SF space, The Web Data Loft. 📍 On-site Venue (May 30–31): The Web Data Loft 625 2nd St, San Francisco, CA 🏆 $18,300 cash prize + Bright Data AI Startup Program opportunities 🍕 Free food, drinks, networking, workshops, mentorship, and live demos 🎁 Onsite attendees are automatically entered into a live giveaway for 4 × $100 Amazon gift cards. 🧑‍💻 Apply now to build AI agents powered by real-time web access.

In this hybrid hackathon powered by Arc, developers will build the next generation of payment systems using AI + Arc with USDC. Explore a world where AI agents can understand natural language, automate financial actions, and move money with precision. From DeFi to digital content and real-world assets, this is your chance to shape the future of intelligent finance. 📅 October 27 – November 9, 2025 • Oct 27 – Nov 8 (Online Phase) – Collaborate and build with developers and AI innovators from around the world. All projects must be submitted by end of day on November 8. • Nov 8 (New York City – On-site Build Day) – Selected participants will be invited to an exclusive in-person session to refine their projects and connect directly. • Nov 9 (New York City – Live pitching & Awards) – Live pitching sessions to a panel of judges and investors, followed by the official winner announcement. 📍 On-site Venue (Nov 8–9): Babe Ruth Room, Jay Conference Chelsea 159 West 25th Street, New York City, USA 🧠 Get guidance from blockchain and AI experts throughout the event. 🤝 Go solo or team up — it's your flow. 🏆Compete for $10,000 in USDC prizes. 📍 On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑🏻‍💻 Secure your spot now — sign up before the Kick-Off Stream!