
25
10
Pakistan
1 year of experience
AI enthusiast with practical experience in Generative AI, machine learning, and data analysis. I’ve worked on building AI-powered apps like chatbots and sentiment analysis tools using models like GPT and LLaMA. I enjoy solving real-world problems and exploring new ways AI can drive innovation.

𝗧𝗲𝗰𝗵𝗙𝗹𝗼𝘄 𝗔𝗜 is revolutionizing e-commerce by transforming 𝗪𝗵𝗮𝘁𝘀𝗔𝗽𝗽 into a voice-first shopping platform that works in 𝟲𝟬+ 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲𝘀. THE PROBLEM: 𝟳𝟴𝟬 𝗺𝗶𝗹𝗹𝗶𝗼𝗻 people globally are excluded from the $𝟮.𝟴 𝘁𝗿𝗶𝗹𝗹𝗶𝗼𝗻 𝗲-𝗰𝗼𝗺𝗺𝗲𝗿𝗰𝗲 market because they struggle with typing - whether due to literacy challenges, language barriers, age, or simply preferring voice communication. In emerging markets like Pakistan, Bangladesh, and Nigeria, 𝟲𝟱% 𝗼𝗳 𝘂𝘀𝗲𝗿𝘀 prefer voice over text, yet no solution exists for voice commerce. 𝗢𝗨𝗥 𝗦𝗢𝗟𝗨𝗧𝗜𝗢𝗡: TechFlow AI enables anyone to shop using WhatsApp voice messages in their native language. Customers simply send a voice note saying "I want a laptop under 50,000 rupees" in Urdu, Hindi, Bengali, or any language. Our AI, powered by 𝗚𝗣𝗧-𝟱'𝘀 revolutionary 𝟮𝟱𝟲𝗞 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 𝘄𝗶𝗻𝗱𝗼𝘄 and Whisper API, instantly understands the request, searches inventory, and responds with formatted product options in the customer's language. One voice confirmation completes the order. 𝗜𝗠𝗣𝗔𝗖𝗧 & 𝗧𝗥𝗔𝗖𝗧𝗜𝗢𝗡: Our pilot program shows stunning results - 𝟯𝟰𝟬% 𝘀𝗮𝗹𝗲𝘀 𝗶𝗻𝗰𝗿𝗲𝗮𝘀𝗲 for a Karachi electronics shop, 𝟮𝟴𝟬% 𝗺𝗼𝗿𝗲 𝗰𝘂𝘀𝘁𝗼𝗺𝗲𝗿𝘀 for a Dhaka fashion store. We're not just building a chatbot; we're democratizing commerce for 2 billion WhatsApp users, creating 2.5 million jobs, and unlocking a $500 billion market opportunity. 𝗕𝗨𝗦𝗜𝗡𝗘𝗦𝗦 𝗠𝗢𝗗𝗘𝗟: B2B SaaS charging merchants $𝟮𝟬/𝗺𝗼𝗻𝘁𝗵 𝗽𝗹𝘂𝘀 1% transaction fee. With just 1% market penetration, we reach $𝟭𝟬𝟬𝗠 ARR. The TAM is $𝟮.𝟴 𝘁𝗿𝗶𝗹𝗹𝗶𝗼𝗻 in mobile commerce, with WhatsApp commerce alone representing $𝟰𝟴𝟬 𝗯𝗶𝗹𝗹𝗶𝗼𝗻.
24 Aug 2025

DeepAgro is an AI-powered agricultural platform that transforms traditional farming with real-time crop health monitoring, pest and disease detection, climate adaptation strategies, and market insights. By leveraging AI-driven analytics, it helps farmers optimize resources, prevent losses, and increase productivity. DeepAgro offers image-based crop diagnosis, allowing farmers to detect diseases, nutrient deficiencies, and soil health issues instantly. With multilingual support and voice/image input, it ensures accessibility for all farmers. The platform provides automated alerts for extreme weather, pest outbreaks, and disease risks, enabling proactive decision-making.To address climate change impacts, DeepAgro integrates real-time climate intelligence, offering recommendations on planting schedules, irrigation, and fertilization. It also provides market-driven insights, helping farmers select profitable crops, find the best selling locations, and access government subsidies. For small-scale farmers facing resource constraints, DeepAgro generates personalized farming plans based on land, water, soil quality, and budget. Additionally, interactive visual reports, heatmaps, and predictive analytics help farmers assess risks and forecast yields effectively. By bridging the gap between traditional farming and modern AI technology, DeepAgro ensures higher yields, reduced losses, and sustainable agriculture, empowering farmers with smart, data-driven decision-making for a profitable and climate-resilient future.
16 Feb 2025

The Network Log Translator is an innovative platform aimed at demystifying common network errors for individuals with limited technical knowledge. By offering clear, layman-friendly explanations and practical troubleshooting steps, it helps users understand issues like "DNS_PROBE_FINISHED_NO_INTERNET" or "Connection Timed Out." Supporting multiple languages—including English, Urdu, Spanish, and several South African languages—this tool ensures accessibility for diverse communities. Users can input their network logs either through text or voice, making it adaptable to different preferences. The platform features predefined buttons for common errors, allowing quick access to explanations. Additionally, it integrates speech recognition technology, enabling users to speak their issues directly. Overall, the Network Log Translator empowers individuals to tackle connectivity challenges confidently, fostering greater digital literacy and self-reliance in underprivileged areas.
26 Jan 2025

"EduNexus 2.0" is an AI-powered educational platform that integrates IBM Watson Assistant's conversational AI with personalized learning tools to create an adaptive, intelligent learning environment. The platform offers a tailored experience to meet individual student needs. Powered by IBM Watson Granite Model , it provides real-time, context-aware support, utilizing natural language processing (NLP) to offer precise assistance for complex academic queries. Key features include a Personalized Learning Assistant that Customizes learning plans, an AI Coding Mentor for expert coding support, and a Smart Document Summarizer that simplifies complex content. The Interactive Study Planner helps students create personalized study schedules, while Real-Time Q&A offers instant academic support. Mental Health Support ensures students maintain well-being, and Multi-Language Support breaks down language barriers. EduNexus 2.0 also generates AI Study Resources, such as personalized materials and practice tests, along with Lecture Summaries that condense lengthy lectures for easier review. By combining IBM Watson’s conversational intelligence with adaptive learning algorithms, EduNexus 2.0 creates an intuitive, responsive ecosystem that enhances academic and technical skill development, supports mental wellness, and optimizes learning outcomes for students.
18 Nov 2024

Government websites serve as sources of information and services related to public affairs, playing an essential role in connecting citizens with government institutions, but they are notorious for their complexity and lack of user-friendly design. The vast amount of information available on these sites can make it incredibly difficult to find what you're looking for. We created GovEase to make navigating government websites easier for users. All the user has to do to use GovEase is choose a language, choose a country, and input the government service or benefit they are looking for. The system will then find the documents and information that are responsive to the user's inquiry. GovEase can be used by native English speakers and people with limited English proficiency who speak Spanish, Hindi, French, Urdu, or German, because the results can be translated into one of these languages. GovEase searches any country's government websites to find government documents and information with ease. The tech stack we used for our project is Llama 3.2 (LLM), Browserless, Groq, Streamlit, Python, and LangDetect. Browserless does a search on Google based on the user's query. The search finds the top websites and gets the document links which is then given to LLama 3.2 which structuralizes the search results (output and links). LangDetect is a library that detects the language that the user wants and translates the results into the language the user wants. We are using Llama 3.2 from the Groq API key as the hosting platform and the front end deployment is hosted by Streamlit.
11 Nov 2024

TeleGuide is an advanced AI assistant specifically designed for the telecommunications industry. Built on cutting-edge AI models like Llama 3.2, TeleGuide helps users efficiently handle various telecom-related tasks. Whether it’s analyzing regulatory documents, contracts, or customer inquiries, the app delivers detailed insights and actionable data. TeleGuide goes beyond text-based queries by offering image analysis as well. Users can upload satellite imagery or equipment photos for inspection and get a comprehensive analysis, all integrated with TelecomAI for enhanced accuracy and speed. With TeleGuide, telecom professionals have a versatile tool to streamline their work, making data processing and interpretation more efficient than ever.
20 Oct 2024

Period Care is a holistic health platform designed to support individuals throughout their entire menstrual cycle, not just during their period. Our app offers personalized health insights, food recommendations, and emotional well-being tips tailored to each phase of the cycle. Users can track their periods, mood swings, and sleep patterns, helping them better understand their bodies. Additionally, the app provides easy access to nearby stores for purchasing pills or pads and allows users to book appointments with gynecologists. By focusing on both menstrual and non-menstrual phases, Period Care empowers users to take control of their health and well-being year-round.
13 Oct 2024

Today’s litigators are expected to quickly make well-informed decisions and develop strong strategies and a big-picture perspective. To accomplish these goals in shorter time frames, we present Legal Buddy to streamline the document review and analysis process. Legal Buddy gives attorneys more time for strategic planning by providing a report with an overview of the case, a liability analysis, a case analysis, applicable laws and defenses, damages, and recommendations for the case. The attorney (user) can upload medical records or summaries, witness statements, deposition transcripts or summaries, pleadings, and other legal documents, notes, or summaries and the system will use Upstage's Document OCR to extract text from the documents. Then, the Llama model summarizes all the text and the text is given to the OpenAI's o1 LLM to generate a liability analysis and report. Additionally, we stored a data set of U.S. case law on MongoDB using LlamaIndex and enabled a vector search to find the relevant cases for the case analysis feature. The system matches information from our specific case from the uploaded documents with other cases from the data set of U.S. case law. OpenAI's o1 reasoning is used to generate case analysis and the case analysis is included in the report. There is currently a resource limit on the length of the documents that can be uploaded and the amount of cases that can be stored, so for now we are uploading summaries of legal documents instead of the actual documents and the data set we are storing is a sub-set (about 500 cases) of the entire U.S. case law data set. We would like to have more processing and storage functionality, but that just wasn't feasible for this hackathon. For the future, we would like the user to interact with live data from a data source (i.e. Westlaw, LexisNexis) instead of a data set. We would also like the user to query case information through a chat interface.
11 Oct 2024

EduNexus is a cutting-edge AI-powered platform that brings together key academic tools into one integrated solution, offering personalized support tailored to each student’s needs. Using IBM watsonx.ai’s advanced generative AI, EduNexus provides a range of features designed to enhance the educational experience: • Personalized Learning Materials: EduNexus customizes content based on a student’s learning style and progress, ensuring that each student receives material suited to their individual needs. • Real-Time Coding Assistance: The platform offers immediate feedback on coding tasks, helps debug code, and explains complex coding concepts, making programming easier to understand. • Document Summarization: EduNexus uses AI to create concise summaries of textbooks and academic papers, helping students grasp essential information quickly and efficiently. • Interactive Study Planning: It generates personalized study schedules that adapt as students progress, helping them manage their time and workload effectively. • Custom Study Resources: The platform creates practice exams and revision materials tailored to a student’s current knowledge and learning needs. Powered by the Granite-3b-code-base model, EduNexus uses few-shot learning to adapt dynamically, providing relevant and high-quality content with minimal input. This approach ensures a seamless and efficient learning experience. EduNexus aims to transform education by boosting student engagement and easing educators' workloads, with plans for future expansion to further enhance its impact on the global education landscape.
26 Aug 2024