AI final year project ideas
AI 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.
90 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.
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.
AI API Spend Attribution per Feature and Customer with Budget Guards
AI features have a cost per request that changes with prompt length, model choice and retries, and a single heavy customer or a bug in an agent loop can burn a month's budget in a day. Build a lightweight library and collector that tag every AI call with feature, customer and model, compute cost from token counts, show cost per feature and per customer, detect unusual spend quickly, and enforce budgets before the bill arrives.
EU AI Act Risk Classification Questionnaire for Software Exporters
Software houses in Pakistan, India and Bangladesh build AI features for European clients, and the EU AI Act can apply to them even though they sit outside the EU. Build a guided questionnaire that walks a developer through the Act's structure (prohibited practices, high-risk categories, transparency duties, general-purpose AI), cites the exact article for every step, and produces a plain-language summary of likely obligations to discuss with a lawyer.
Which LLM Understands Roman Urdu and Bangla Business Messages? A Three-Model Evaluation Harness
Small businesses in Pakistan and Bangladesh get orders and complaints as WhatsApp-style messages in Roman Urdu, Urdu script, Bangla and English mixed together. Build an evaluation harness that compares three LLMs (for example one hosted frontier model, one cheaper hosted model and one open model) on real-shaped tasks such as extracting order details and classifying complaints, with a human-checked gold set, cost per correct answer and a public results page.
Model Card and Datasheet Generator from Training Runs
Model cards and dataset datasheets are the standard way to document what a model does, what data it learned from and where it fails, but they are written by hand at the end, if at all. Build a generator that pulls facts from MLflow runs, dataset files and evaluation results, drafts a model card and datasheet, flags missing or unsupported sections, and keeps the card in sync as the model is retrained.
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.
PII and Secret Leak Audit for LLM Chat Logs and Traces with Retention Rules
LLM apps log everything: prompts, retrieved chunks, tool results and answers. Those logs quietly fill up with phone numbers, CNIC numbers, addresses, API keys and other users' data. Build an auditor that scans existing LLM traces, finds personal data and secrets in English, Urdu and Roman Urdu, shows where each leak entered the pipeline, and enforces retention and masking rules going forward.
Government Notification Watcher with Plain-Language Summaries and Topic Alerts
Tax notifications, regulatory circulars and gazette notices change rules for small businesses and citizens overnight, but they are published as scanned PDFs on scattered government websites. Build a monitored pipeline that checks chosen official pages on a schedule, detects new documents, extracts text (with OCR when needed), writes a short plain-language summary with the source linked, and alerts subscribers by topic. Treat it as a reliability and cost engineering project.
Glacial Lake Growth Monitoring from Sentinel-2 Imagery for Outburst Flood Risk in Northern Pakistan
Glacial lakes in Gilgit-Baltistan and Chitral are growing as glaciers melt, and some can burst and flood villages downstream. Build a pipeline that maps lake outlines from free Sentinel-2 satellite images every month, tracks area change over several years, flags lakes growing fast, and lists the settlements downstream. Validate the outlines against published inventories and hand digitising.
Tool Selection Evals and Description Linter for MCP Servers
An MCP server can work perfectly and still fail in practice because models pick the wrong tool or fill its arguments badly. Build a tool that lints MCP tool names, descriptions and schemas against good-practice rules, generates realistic user requests for each tool, measures how often several models choose the right tool with valid arguments, and suggests rewrites that improve the score.
MCP Server for Public Transport Timetables Built on GTFS Feeds
Build a Model Context Protocol server that lets any AI assistant answer real transport questions correctly: next departures, journeys with transfers, service changes and accessibility, all computed from GTFS timetable data rather than guessed by the model. Where a city has no public feed, the team builds one for a route they know, such as a university shuttle or a metro bus line, and publishes it openly.
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.
Roman Urdu Jailbreak and Policy Drift Red Team for Customer Service Chatbots
Customer service chatbots are tested in English, then deployed to users who write in Urdu, Roman Urdu and a mix of all three. Build a red-team harness that checks whether a bot stays inside its own written rules (no promises it cannot keep, no advice outside its remit, no leaking its instructions) when attacked in local languages and code-switched text, and produces a scorecard the business can act on.
Hallucinated Package Guard for AI Coding Assistants (Slopsquatting Defence)
AI coding assistants sometimes suggest packages that do not exist. Attackers can register those names and wait. Build a guard that checks every new dependency added to a project, by a person or an AI, against the real registry: does it exist, how old is it, who maintains it, does it look like a typo of a popular package, and was it suggested by an AI? It runs in the editor, as a pre-commit hook and in CI.
Crop Disease Photo Triage That Knows When to Ask an Agronomist, on Budget Android Phones
Most crop disease apps give a confident answer for every photo, even blurry ones, the wrong crop or a disease they never saw in training. Build an on-device classifier for a few crops that abstains when unsure and sends those photos to an agronomist review queue; the agronomist's answers become new training labels. The project measures how much accuracy improves when the app is allowed to say "I don't know".
Inter-Annotator Agreement and Adjudication Tool for Data Labelling Teams
AI depends on labelled data, and labelling teams in Pakistan, India, Kenya and elsewhere produce a lot of it. Build a quality layer for labelling projects that measures agreement between annotators, spots unreliable labels and confusing guidelines, routes disagreements to an adjudicator, and estimates true labels from noisy votes, working with exports from Label Studio and similar tools.
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.
Human-Approved AI Agent for Filing and Tracking Citizen Service Requests
Filing a complaint or service request with a city or government office means finding the right portal, filling long forms, attaching documents and then chasing it for weeks. Build an agent that turns a citizen's plain description (in Urdu, Roman Urdu or English) into a correctly filled request, pauses for the citizen to approve every submission, then tracks status and reminds them to follow up. Built and tested against a realistic mock portal you create.
Drone Plant Stand Counting and Gap Mapping for Smallholder Maize and Sugarcane Fields
A few weeks after sowing, farmers need to know how many plants came up and where the gaps are, so they can resow in time. Build a pipeline that takes low-altitude RGB drone photos of a small field, stitches or tiles them, counts plants with a detection or density model, and produces a gap map and an estimate of plant population per acre. Compare it against hand counts in marked sample plots.
River Flood Forecasting with LSTM Models from Upstream Gauges and Satellite Rainfall
Train and evaluate machine learning models that forecast river discharge one to five days ahead for a few South Asian or African river basins, using upstream gauge readings, satellite rainfall and public hydrology datasets. Compare against simple persistence and published global forecasts, and report the lead time at which a warning threshold would have been crossed in past floods. This is the forecasting model, not a sensor network or an alert app.
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.
Hidden Instruction Scanner for Documents Before They Enter a RAG Knowledge Base
Build an ingestion-time scanner that inspects PDFs, Word files, web pages and spreadsheets before they are chunked into a RAG knowledge base, and finds text a human cannot see but a model will read: white or tiny text, invisible Unicode, instructions hidden in metadata, alt text and comments. Suspicious files are quarantined with a highlighted preview so a person decides. It closes the door that indirect prompt injection walks through.
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.