Frontend final year project ideas
Frontend final year project ideas from the free Sefism library, each scoped for a single semester with a suggested stack and deliverables.
- 300 project ideas
Ideas and guidance, not finished projects
These are project ideas and scoping guidance, published free for students to use as a starting point. I do not build, write, or sell final-year projects, and I do not complete coursework for anyone. Take an idea, make it yours, and build it.
84 ideas · page 1 of 4
Multi-Agent Literature Review Assistant with Verified Citations for Students
Students writing a literature review often get chatbot answers full of papers that do not exist. Build a multi-agent assistant that plans a search, queries open scholarly databases, reads abstracts and open-access full texts, drafts a structured review, and refuses to cite anything it cannot resolve to a real DOI or arXiv record with a supporting passage. Then measure whether multiple agents actually beat a single agent on quality and cost.
Tenancy Rights Guided Assistant with Rules as Code for Punjab and Lagos Rental Laws
Tenants in Lahore and Lagos often do not know whether a rent increase, an eviction notice or a withheld deposit is lawful, and lawyers are expensive. Build a guided web assistant that asks a tenant a few plain questions and explains, with the exact provisions, what the local tenancy law says about their situation, using rules encoded from the statute and reviewed by a law teacher. It generates a short letter template the tenant can adapt.
AI Incident Log and Postmortem Tracker for LLM Products
When an LLM feature misbehaves (a harmful answer, a leaked system prompt, a wrong refund, a runaway cost spike), most teams handle it in a chat thread and forget it. Build an incident tracker designed for AI failures: capture the exact prompt, context and model version, classify the failure, run a blameless postmortem, turn the case into a regression test, and track whether the fix held.
Privacy-First Legal Aid Intake and Case Routing for NGO Legal Clinics
NGO legal clinics and university law clinics in Pakistan, India, Nigeria and Kenya take requests by phone, walk-in and WhatsApp, and sensitive details about domestic abuse, labour disputes or police cases end up in personal phones and spreadsheets. Build a secure intake system with a guided form, issue classification into a standard legal taxonomy, routing to the right volunteer lawyer, and strict access control, encryption and audit logs. Threat-model it before writing code.
Shariah Stock Screening and Dividend Purification Calculator with Transparent Methodology
Muslim investors in Pakistan, the Gulf, Malaysia and the UK want to know whether a listed company meets Shariah screening rules and how much of a dividend to give away as purification, but most tools hide their method. Build a screening web app that reads company financial statements, applies a chosen published screening methodology step by step, shows every ratio and its source line, and calculates purification amounts. Let users compare how different methodologies change the result.
Offline AI Tutor Hotspot on a Raspberry Pi for Schools Without Internet
Many schools have a few phones or tablets but no reliable internet. Build a Raspberry Pi box that runs a small open language model and a curriculum-grounded retrieval system completely offline, creates its own Wi-Fi network, and lets students ask questions about their textbook in Urdu or English from any browser. Teachers control what content is loaded and see which topics students ask about most.
Arabic Diacritics Reading Tutor with Automatic Tashkeel Feedback for Learners
Learners of Arabic, from schoolchildren in Pakistan and Nigeria to expatriate workers in the Gulf, struggle to read text without short vowel marks (tashkeel). Build a tutor that removes the marks from a passage, asks the learner to add them, and checks the answer against an automatic diacritiser and a verified reference, explaining errors by grammar rule. Measure diacritiser accuracy and whether learners improve.
AI System Inventory and Risk-Tier Register for Software Companies
Most companies cannot answer a simple question: where are we using AI? Build an inventory and risk register that discovers AI use (features in the product, AI tools staff sign into, AI APIs in code and cloud bills), records an owner and purpose for each, assigns a risk tier from a clear rubric mapped to the NIST AI RMF and the EU AI Act, and schedules reviews. Designed for software houses that sell to clients abroad.
USSD and SMS Revision Quizzes for Students on Feature Phones
Many secondary school students in Kenya, Nigeria, Pakistan and Bangladesh have access only to a family feature phone, with no data plan. Build a revision quiz service over USSD menus and SMS that delivers short, syllabus-linked multiple-choice quizzes, adapts to each student's weak topics and gives teachers a web dashboard. Engineer it for USSD's tight limits: short sessions, 160-character screens and dropped connections.
Brand-Consistent AI Video Ad Generator with Automatic Checks and Disclosure Labels
Small brands want short video ads for Instagram, TikTok and YouTube but cannot afford a studio, and AI video tools produce clips that drift off-brand and are not clearly labelled as AI-made. Build a generator that turns a product brief and brand kit into short ads in several formats, then automatically checks every frame for logo, colours, text spelling and banned claims, and adds a visible AI label plus Content Credentials before export.
Raast Merchant Payments Integration Kit with Dynamic QR, Request to Pay and Reconciliation
Pakistan's Raast instant payment system supports merchant payments by QR code, alias and request to pay, but small businesses and developers struggle to connect it to their shops and invoices. Build an open integration kit: a simulated payment service provider API modelled on Raast's person-to-merchant flows, a merchant dashboard, dynamic QR generation per order, request-to-pay links and automatic reconciliation of payments to orders. Design it so a real provider's API could replace the simulator later.
Remittance Cost Comparator for Gulf to South Asia Corridors Using World Bank Price Data
Workers in Saudi Arabia, the UAE and Qatar send billions home to Pakistan, India, Bangladesh and Nepal, and the true cost hides in the exchange rate margin, not the fee. Build a comparator that uses the World Bank's Remittance Prices Worldwide data plus user-entered quotes to show the real amount received, explains fee versus margin, and tracks corridors against the international 3 percent cost target.
Protocol-Locked Danger Sign Triage Assistant for Community Health Workers in Urdu, Bangla and Arabic
Build a phone assistant that walks a community health worker through a sick child visit in Urdu, Bangla or Arabic, where the triage decision comes from an encoded clinical protocol, never from a language model. The model only does what it is good at: understanding a spoken or typed answer in a local language and turning it into a protocol field. The project tests whether that split keeps the decisions safe while making the tool easier to use than a long paper form.
Citation-Checked Legal Question Answering over Pakistan Code and India Code
Law students and junior lawyers in Pakistan and India increasingly ask AI tools legal questions, and those tools sometimes cite sections that do not exist or misquote them. Build a retrieval-augmented assistant over official statute text from Pakistan Code or India Code where every answer cites specific sections, and a separate checker verifies that each cited section exists and that quoted text matches the source before the answer is shown. Measure hallucinated citations before and after the checker.
Bangla Writing Feedback Tutor with Spelling and Grammar Error Detection for School Students
Students in Bangladesh and West Bengal write essays and letters in Bangla for exams, but teachers with large classes cannot give detailed feedback on every piece, and mainstream writing assistants offer little or no Bangla support. Build a tutor that marks likely spelling and grammar errors in a student's Bangla text, explains each one in simple Bangla and tracks a student's common mistakes over time. Evaluate it on real student writing marked by teachers.
University Exam Timetable and Invigilator Planner Benchmarked on ITC 2007 Datasets
Every semester, exam offices build timetables by hand and students end up with clashes, three papers in a row or exams in rooms that are too small, while invigilator duties are shared unfairly. Build an exam scheduler that assigns exams to slots and rooms, spreads each student's papers, assigns invigilators fairly, and is tested on the public ITC 2007 examination benchmark before being run on your own university's anonymised data.
FAO-56 Irrigation Scheduling Advisor for Small Farms Using Weather Forecasts
Build a web and SMS advisor that tells a farmer when to irrigate and roughly how much, using the FAO-56 crop water balance method, open weather forecasts and a few facts about the field (crop, sowing date, soil type). No sensors needed. The project checks the advice against a published crop model and shows how much water the schedule saves compared with a fixed calendar.
Sentence-Level Groundedness Checker for RAG Answers with Human-Calibrated Thresholds
RAG apps cite sources, but a citation does not prove the sentence next to it is supported. Build a drop-in checker that splits each answer into claims, checks every claim against the retrieved passages with a natural language inference model and an LLM judge, highlights unsupported sentences in the UI, and sets its thresholds from human labels rather than guesses. Test it on English and Urdu answers.
Student Mental Health Check-In App with Human Counsellor Escalation
Build a private weekly check-in app for university students that uses short, validated questionnaires, shows students their own trends and routes anyone who reports serious distress to a real person at the counselling service, fast. The software never diagnoses or gives therapy. The project is about the escalation path: who gets alerted, how quickly, what happens if nobody responds, and how student privacy is protected throughout.
Pairwise Preference Labelling App for Urdu LLM Answers with Rater Calibration
Language models learn what 'good' means from human preference data, and very little of it is in Urdu. Build a mobile-friendly app where raters compare two model answers to an Urdu or Roman Urdu prompt, choose the better one against a clear rubric, and explain why. The system checks rater consistency, corrects for position bias, and produces a clean, documented preference dataset and a small leaderboard.
Home Sound Alerts on a Vibrating Wristband for Deaf and Hard of Hearing People
Build a small listening device that recognises important household sounds, such as the doorbell, a pressure cooker whistle, a baby crying or a smoke alarm, entirely on the device, and sends a distinct vibration pattern to a wristband. Deaf and hard of hearing people often miss these sounds, and phone-based features are limited to a fixed list of mostly Western sounds. The project lets users teach the device sounds from their own home.
Urdu Speech Therapy Practice Game for Children with Therapist Review and Sound Scoring
Build a tablet and phone game that turns daily speech therapy homework into play for Urdu-speaking children with speech sound disorders, records each attempt, gives a first automatic score for a small set of target sounds, and sends recordings to the child's therapist for review. Speech therapists in Pakistan are few and far between, so most practice happens at home without feedback. The game keeps children practising and keeps the therapist in charge.
Urdu Misinformation Inoculation Game for WhatsApp Forwards
Build a short browser game in Urdu where players run a fake forwarding account in a simulated chat app and learn the techniques behind misleading forwards: fake official notices, edited screenshots, out-of-context videos, miracle cures and impersonation. It follows the inoculation approach from published research and is tested with a controlled study, because a replication in India found the original game did not help people tell true from false headlines. The aim is a game that actually works for local audiences.
Clustered Short-Answer Grading for Large University Classes with Lecturer Control
Build a grading tool that groups similar typed short answers from an online quiz, lets the lecturer grade and comment on each group once, and flags unusual answers for individual reading. Lecturers with hundreds of students often switch to multiple choice because written answers take too long to mark. The project uses sentence embeddings and clustering, keeps every grade under the lecturer's control and measures how much marking time it saves.
Browse project ideas by domain and difficulty
Each of these is its own page, so you can send someone straight to the AI ideas or the beginner ones.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Sessions are free for approved Sefism members, and a few slots open each week.
- 1:1 Mentorship
- Fresh Graduate Mentorship
- Career Guidance
Brand deals, promos and partnerships: tauseeffayyaz@gmail.com
Follow along
New writing, resources and project ideas land here first.