http://hdl.handle.net/123456789/17505 Sat, 16 May 2026 17:00:45 GMT 2026-05-16T17:00:45Z http://hdl.handle.net/123456789/20991 ALF: The Ultimate Customer Support Bot 03-135221-033 Muhammad Faizan Tahir, 03-135221-021 Muhammad Faeez Salman ALF: Modern customer support systems often struggle with delayed responses, limited scalability, and inefficiency in resolving complex queries, particularly those involving visual or contextual product-related issues. Traditional chatbots lack real-time access to dynamic databases and fail to interpret multimodal inputs like images or nuanced textual descriptions, leading to generic or inaccurate solutions[1]. This gap negatively impacts user satisfaction, increases operational costs, and strains human support teams. ALF: The Ultimate Customer Support Bot addresses these challenges by offering an intelligent, automated solution capable of processing both visual and textual inputs while integrating se amlessly with a company’s backend systems. By enabling real-time access to product catalogues, order statuses, and delivery timelines, ALF ensures precise, context-aware responses, reducing resolution time and enhancing customer experience[2]. Its significanc e lies in bridging the automation-human support divide, optimizing resource allocation, and fostering brand loyalty through instant, reliable assistance. ALF leverages advanced Large language models (LLM) to interpret user queries, whether textual (e.g., “hair oil for strong hair”) or image -based (e.g., product photos). Integrated with RESTful APIs[3], the bot fetches real-time data from the company’s product and order databases to provide accurate recommendations. A deep neural network[4] model trained on product attributes and historical customer interactions enables ALF to suggest alternatives when exact matches are unavailable. The system’s frontend, designed for web[5], features an intuitive UI with chat functionality and image-upload support. Backend integration employs cloud - based microservices for scalability, while security protocols ensure data privacy. By combining LLM, image recognition frameworks (e.g., CLIP), and API-driven database interactions[3], ALF delivers a unified, efficient support platform that automates query resolution, reduces human intervention, and elevates user engagement across digital touchpoints[6]. Dr Junaid Nasir Qureshi Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/20991 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/20992 PillGenius: AI for next level Pharmacy Automation 03-135221-011 Hafiza Asma Rasool, 03-135221-029 Rana M.Ali Zafar With life moving at a superfast pace currently, easy accessibility to credible healthcare centers as well as current medical information is at its best. There are a few requirements for such platforms that not only enable people to buy medications but also offer advice for healthcare decisions, given the rapid growth of online medical solutions. One of these initiatives of Pillgenious, a pharmacy web application driven by artificial intelligence that bridges the gap between traditional pharmacies and contemporary smart healthcare technology. The aim of Pillgenious is enabling an easy-to-use website from which customers can browse, order, purchase medicines over the internet and access immediate assistance from an artificial intelligence-powered chatbot. Key functions such as product search, individualized guidance, order tracking, payment and shipping security are also included. Additionally, Pillgenious creates alerts and news for the safe and efficient administration of medications, provides information about the real time medicine, and links people with medical specialists. Technically, it was created using a backend for safe and scalable data storage, a responsive online user interface for optimal user experience, and mongoDB for effective database management. AI integration makes it easier to intelligently respond to questions about medicine, making it even more interactive and instructive. Furthermore, Pillgenious is a healthcare partner that helps people make informed decisions in addition to being an online pharmacy. This system is also able to further medicine access, reduce use of conventional drug stores, and open a path for more improved healthcare developments based on AI in times ahead. Ms. Summaira Nosheen Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/20992 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/20988 Harvest Direct: AI-Powered Freshness &Transactions 03-135221-007 Bilal Rasheed, 03-135221-003 Abeesha Shahnawaz The "Harvest Direct" project is a mobile application aimed at transforming the agricultural marketplace by directly connecting farmers with buyers, eliminating the need for intermediaries and ensuring fairer prices for both parties. The app features an AI-powered freshness detection system, using a MobileNetV2-based machine learning model to evaluate the quality of apples based on visual attributes, such as color and texture, ensuring that consumers can make informed purchasing decisions. Designed with user accessibility in mind, the app is particularly suited for rural farmers with limited technological experience, offering an intuitive interface, a 24/7 AI chatbot for real-time assistance, and secure transactions powered by Firebase for ease of use and data security. The platform allows farmers to upload product listings, set their own prices based on product quality, and manage orders without third-party involvement, thus promoting fair trade and improved profitability. It also supports bulk orders for businesses, such as restaurants and wholesalers, providing a streamlined approach to acquiring fresh produce. This project integrates essential features such as user authentication, a real-time database, and AI-powered tools, aiming to bridge the gap between farmers and consumers, create a more efficient supply chain, reduce food waste, and support sustainable farming practices. Future developments will expand the app’s functionality to include additional produce categories, enhanced freshness detection, and more advanced AI features ensuring continued innovation in the agricultural sector. ZUNNURAIN HUSSAIN Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/20988 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/20990 Bridging Blood Donation Gaps Through AI-Powered Donor Support (RedAid) 03-135221-008 Danish Ijaz Ahmad, 03-135221-004 Ahsan Naveed The problem of blood donors is a significant issue because they are not able to access them at the right time because of the lack of a centralized system, donor awareness, and the real-time coordination between hospitals and blood banks on one side and the individuals on the other side. The situations of emergency are usually critical as the recipients experience difficulty in finding compatible donors within a short time. RedAid is a smartphone-based app that will enhance access to blood donation in Pakistan through AI. The platform matches donors with the most appropriate donors available in real-time through the use of real-time GPS tracking, AI-based donor prediction, and emergency alert mechanisms. The platform is built on Flutter that supports cross-platform and Firebase that manages the back end. RedAid also seeks to cut down drastically the time required to search donors, enhance response in case of an emergency, and motivate voluntary blood donation with awareness and available digital solutions. The project establishes the basis of the subsequent features, such as hospital integration, blood stock monitoring, and prediction of the donor behavior based on the AI. RedAid intends to develop a user-friendly, secure, and scalable blood donation ecosystem that can be used by the general population, hospitals, and blood banks as well as an emergency response team. Muhammad Zunnurain Hussain Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/20990 2026-01-01T00:00:00Z