Describe a startup idea. The app runs a full AI pipeline — market sizing, live competitor scan with web search tools, SWOT analysis, and a landing page draft. All streamed.
Design and implement a multi-stage LLM pipeline with distinct agent responsibilities
Use LangChain agents with Tavily web search to do live competitor research
Stream multiple independent pipeline stages to the frontend simultaneously over SSE
Build a pipeline progress tracker that visualizes each stage's completion status
End-to-end interview coach — upload a JD, generate role-specific questions, conduct a mock interview with voice, get scored feedback with improvement suggestions.
Design a complex multi-service architecture before writing any code
Generate role-specific interview questions from a job description using an LLM
Transcribe voice answers using Whisper and deliver questions via TTS
Evaluate free-text interview answers across multiple quality dimensions using LangGraph
Collect open-ended survey responses, cluster them by theme using embeddings, detect sentiment per cluster, and generate an executive summary report automatically.
Collect open-ended survey responses through a full-stack form
Embed text responses and cluster them using k-means to discover latent themes
Auto-generate cluster labels using an LLM given representative examples
Prompt an LLM to synthesize a data-driven executive summary from structured analysis
Upload lecture notes or textbook PDFs. Auto-generate flashcards, quiz yourself with spaced repetition scheduling, and let the AI adapt difficulty based on your performance
Extract and chunk text from PDF uploads for downstream AI processing
Use structured prompt output to auto-generate flashcard Q&A pairs from raw content
Build an interactive quiz UI with card flip animations
Implement the SM-2 spaced repetition algorithm to schedule card reviews
Upload bank statements, auto-categorize transactions with an LLM classifier, visualize spending trends, and chat with your own financial data through a RAG interface.
Parse CSV bank statement files and normalize transaction data
Use batch LLM calls to auto-categorize transactions at scale
Build a RAG interface that answers natural language questions about personal financial data
Enter what's in your fridge, get recipe suggestions, and ask the AI to suggest ingredient substitutions for anything missing. Practical multimodal CRUD plus AI.
Build ingredient-based recipe matching using overlap scoring logic
Highlight matched vs. missing ingredients in a recipe card UI
Design a prompt that contextualizes AI suggestions within a specific recipe
Stream AI substitution suggestions in real time in response to user needs
Track job applications on a Kanban board. On each card, generate a tailored cover letter from the job description and your resume — streamed in real time.
Build a Kanban board with drag-and-drop using @dnd-kit
Store and retrieve user resume data for use in AI-generated content
Generate a tailored cover letter by combining job description and resume in a single prompt
Stream the AI cover letter into the UI in real time using Vercel AI SDK
A note-taking app where every note is embedded on save. The search bar uses semantic similarity to find relevant notes — not just keyword matching. RAG inside a real product.
Build a working notes app and then add AI as a layer on top — not the other way around
Generate and store vector embeddings for every document on save
Build a semantic search endpoint using FAISS similarity search
Demonstrate the difference between keyword search and semantic search to end users
Log, categorize, and visualize personal expenses. Add budgets, monthly summaries, and a chart dashboard. Solid full-stack fundamentals — auth, data model, visual reporting.
Build a full-stack expense tracking app with user-specific data isolation
Design a PostgreSQL schema for financial transaction data
Integrate Recharts to render interactive pie charts, bar charts, and progress bars
Implement budget management with per-category limit tracking
Build your own blog — write, publish, and manage posts with a rich text editor, tag filtering, and a public-facing reader view. Full auth, full CRUD, full stack.
Implement authentication using NextAuth.js with session management
Design a MongoDB schema for a document-based content platform
Build a rich text editor with publish/draft functionality
Create a public reader view with tag filtering and pagination
Full-stack app to manage students, courses, and grades — complete CRUD, user roles, a dashboard with stats, and a clean UI. The classic full-stack portfolio project.
Build a complete full-stack app with authentication, CRUD, and relational data
Implement role-based access control (admin vs student)
Connect a React/Next.js frontend to a REST API backend securely
Build a data dashboard with aggregated stats from a relational database
Implement a full Transformer encoder — multi-head attention, positional encoding, layer norm — in PyTorch from scratch. Train on a classification task. No HuggingFace shortcuts.
Implement scaled dot-product attention and multi-head attention from scratch in PyTorch
Build sinusoidal positional encoding and understand why position matters in Transformers
Assemble a complete Transformer encoder block with residual connections and layer norm
Train an encoder classifier end-to-end on a real text classification dataset
Every challenge includes detailed documentation, technical constraints, and automated evaluation scripts to ensure you have everything you need to succeed.