http://hdl.handle.net/123456789/10321 2026-07-16T21:13:35Z http://hdl.handle.net/123456789/21340 Verbally – An AI-Powered Companion for Mastering English Ayesha Mushtaq Khan, 01-131222-010; Muhammad Saad Jamil, 01-131222-023 In today’s digital age, English learning remains a fragmented process, requiring students to rely on a variety of online courses and applications to develop different language skills. However, these solutions often lack clear feedback and structured learning paths, limiting their effectiveness in providing an adaptive learning experience. This project proposes Verbally, an AI-based English learning system designed to transform traditional e-learning platforms from simple content delivery tools into intelligent systems capable of assessment and personalized feedback. The key objective of the project is to create an easy to use, complete, scalable, and self-paced. It should be able to test a learner's skills in all of the core English skills, such as vocabulary, grammar, listening, speaking, writing. The framework is constructed based on a robust three-tier client-server model. React is used to create the front end, which is deployed into Vercel, the backend is constructed using NestJS and run on Railway. Aiven is used to manage PostgreSQL database. In accent based speech assessment module, it uses Deepgram Speech to Text and the Montreal Forced Aligner to provide precise, phoneme level and accent aware feedback. It utilizes the Google Gemini API, which is a generative AI model, to automatically create lesson content, writing prompts and test questions. The common European Framework of Reference of Languages is utilized in the platform to put students to A1-C2 proficiency levels. A Level-Up module allows learners to advance to the next level by taking combined vocabulary, grammar, writing and speech tests. A hybrid python microservice architecture is used for speech scoring pipeline, which uses a lot of processing power. The system also has a real-time messaging feature, and it allows learners to be socially connected. The system aims with response times under a second, 99 percent up-time and capability to service at least 100 number of concurrent users dependent on its beta. This demonstrates that it is a suitable and practical alternative to discontinuous English learning solutions Supervised by Dr. Kashif Sultan 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/21339 Multi-Agent AI System for Automated Software Development Aden Javed, 01-131222-006; Zohaib Shafqat, 01-131222-052 In this project, AIMARES (M.A.I.S. for Automating Software Development) is proposed. This unique system is responsible for automated creation of user stories that have a very high level of detail, specific regulations, API designs, and so on. Such requirements are demanded from engineers in order to start software development. Usually, there are initial problem statements when new projects arise. However, engineers need software specifications which often leads to miscommunication and waste of time spent on translation of general ideas into specific software needs. In order to solve this issue, AIMARES was created with the help of another approach than the standard AI prompt one. The work of the tool is based on the deterministic multi-agent pipeline. This mechanism receives a generic specification of a project and transforms it into highly structured software specifications. In this regard, Next.js serves as an interface while FastAPI back-end executes the algorithm of this transformation process. Moreover, AIMARES relies on DDA and RAG (FAISS) mechanisms to make prompts more specific. The process comprises various steps, including the assessment of the project's environment, business logic modeling, describing its UI/UX, planning the development cycle, validation of results, and producing a final package. In general, all the agents generate a complete set of outputs, which includes user stories, a complete Software Requirements Specification (SRS) document, non-functional requirements, APIs, traceability matrices, and quality reports. The final product is condensed into one downloadable package. The architecture incorporates sophisticated features, which ensure the stability and efficiency of the operation, such as the ability to save the current state, playbacks, resume operations, debugging with rich logs, and manifest-driven data processing. We evaluated the performance of our solution through testing it on a hospital management software platform. The task included processing complex issues, such as patient registration, emergency operations, diagnosis, pharmacy, and billing procedures. To summarize, the output demonstrates that artificial intelligence performs significantly better in acquiring software requirements in a structured and traceable workflow rather than being a simple text generator Supervised by Dr. Awais Majeed 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/21341 Vid-AI Faiza Alam Warraich, 01-131222-016; Asad E Bukhari, 01-131222-045 VidAI is an intelligent, cross-platform web and mobile application designed to revolutionize the way Pakistani couples plan their weddings. With the cultural significance and logistical complexity of Pakistani weddings which typically span multiple ceremonies such as Nikah, Mehndi, Baraat, and Walima couples face significant challenges in discovering trustworthy vendors, managing multi-event budgets, and coordinating services across cities. Traditional wedding planning in Pakistan relies heavily on word-of-mouth referrals and manual coordination, which are time-consuming, inconsistent, and lack transparency. Existing digital solutions fail to address the cultural specificity of Pakistani weddings and offer no intelligent assistance for planning decisions. The main motivation behind developing this system was to create an affordable, accessible, and AI-powered platform that bridges the gap between scattered vendor markets and the modern couple's need for a unified, intelligent wedding planning experience. In VidAI, users can register as customers or vendors and interact through dedicated portals. Customers can browse and search verified vendors by category, city, and price range, create bookings with conflict detection, manage multi-event budgets, communicate with vendors in real time, and make secure online payments. The system features a dual AI engine: a conversational AI assistant trained with Pakistani wedding domain knowledge helps users with planning queries, while a structured AI module generates personalized vendor recommendations ranked by budget proximity, automated budget plans with per-event cost breakdowns, and AI-crafted wedding invitation content with image generation. Vendors can manage their profiles, packages, and portfolios, accept or reject bookings, view analytics dashboards, and chat with customers. An Admin portal provides vendor verification, user management, booking oversight, report moderation, and system health monitoring. A React Native mobile app delivers full customer feature parity for on-the-go access, including push notifications for real-time updates. Supervised by Dr. Kashif Sulan 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/21338 Skill Select AI Raja Ramish Tahir, 01-131222-040; Yashal Naeem, 01-131222-049 SkillSelectAI is an AI-powered recruitment platform developed to automate and optimize the hiring process. Traditional recruitment procedures are often slow and inefficient because of manual CV screening, delays in interview scheduling, and difficulties in evaluating candidates accurately. Moreover, recruitment information is commonly spread across different platforms, making candidate management challenging for recruiters and HR teams. To solve these issues, SkillSelectAI provides an intelligent recruitment solution that automates resume screening, candidate-job matching, interview scheduling, and AI-assisted candidate evaluation. The platform is designed to improve recruitment efficiency, reduce manual workload, and enable faster and more effective hiring decisions. SkillSelectAI offers recruiters a centralized system for managing job postings, candidates, and interview workflows. The platform uses Natural Language Processing (NLP) techniques for resume parsing and intelligent candidate-role matching based on skills, qualifications, and job requirements. It also supports template-based interview questions customized for specific job roles, along with asynchronous voice and video interviews that provide flexibility for both recruiters and applicants. The system further functions as an AI-powered evaluation platform that integrates web-based interfaces, backend data management, and intelligent processing services to support automated assessment workflows. It analyzes multimodal inputs including speech, text, tone, and visual behavioral cues to generate structured evaluations and recruitment insights. Advanced technologies such as Natural Language Processing, speech recognition, and behavioral analysis are utilized to interpret candidate responses and interactions effectively. In addition, the platform automatically stores and organizes interview recordings, assessment reports, and generated evaluation results for future access and review. By combining multimedia analysis with centralized data management, SkillSelectAI enables scalable, consistent, and data-driven decision-making across recruitment and candidate evaluation processes. Supervised by Ma’am Rafia Hassan 2026-01-01T00:00:00Z