Real, end-to-end AI projects
Industry-grade problem statements, real datasets, and production deployment - across vision, audio, and language.
Crop Disease Detection from Leaf Images
Transfer learning on a real 54,000-image agricultural dataset, deployed as a lightweight, quantized API a farmer's phone can actually call.
Environmental Sound Classification for Smart Monitoring
Real urban audio, converted to spectrograms and classified with the exact CNN techniques from Module 16-19 — proving vision and audio share the same underlying tool.
Fine-Tune and Serve a Domain-Specific AI Course Assistant
Start from a real, pretrained GPT-2, fine-tune it on real AI/ML Q&A data using the exact SFT recipe from Module 32, then serve it with genuine decoding control and a production streaming endpoint.
Loan Default Prediction with Explainable Credit Risk Scoring
Real multi-table loan application data, benchmarked across logistic regression, Random Forest, and LightGBM — with SHAP explainability and a cost-based decision threshold, exactly as a regulated lender actually needs.
Retail Demand Forecasting with Time-Aware Feature Engineering
Real daily sales across 1,115 stores, forecasted with XGBoost and engineered temporal features — proving gradient boosting with good features beats a naive sequence model here.
Credit Card Fraud Detection at Extreme Class Imbalance
Real anonymized transaction data with only 0.17% fraud, benchmarking Random Forest, XGBoost, and Isolation Forest — because at this imbalance level, which approach wins is a genuinely open question worth measuring.
Customer Review Analysis and Complaint Routing Pipeline
Real multi-category Amazon reviews, benchmarking classical TF-IDF against a fine-tuned Transformer, with a bias check and confidence-gated routing before deployment.
Resume Information Extraction System
Real resumes turned into structured, searchable candidate records — combining NER, coreference resolution, dependency parsing, and regex into one genuine extraction pipeline.
Internal Knowledge Base Semantic Search and Q&A Engine
A real semantic search system over genuine technical documentation, built entirely from embeddings and similarity ranking — proving retrieval works before any generative layer ever gets involved.
Production RAG Documentation Assistant With Staleness and Conflict Detection
Real, versioned documentation with genuine conflicting updates, a retrieval evaluation suite at real scale, a factual-consistency gate before any answer ships, and full production serving with retries and tracing.
Resilient Tool-Using Research Assistant With Source Conflict Reconciliation
A genuine multi-tool research agent that survives real tool failures, reconciles conflicting sources instead of picking one silently, and reports its own confidence honestly.
Production Chatbot With Verified Concurrent Safety and Automatic Quality Monitoring
A memory-backed chatbot stress-tested under real simulated concurrent load, with automatic summarization triggering and genuine monitoring that flags quality degradation before a user ever complains.
Multi-Agent Support Router With Real Loop and Handoff Failure Recovery
A real production failure, measured directly: two support agents bouncing a ticket back and forth with no limit, until the system genuinely hangs. This project builds the failure first, then the real fix.
Crash-Safe Research Pipeline With Guaranteed Resume
A real, multi-step research pipeline is deliberately crashed mid-execution, then resumed from a fresh process. What actually survives, and what genuinely re-runs, is measured directly — not assumed.
Concurrent Human Approval Queue With Real Race-Condition Safety
Two real reviewers act on the same item at nearly the same moment. Without a guard, both silently believe they succeeded — and one's decision is silently lost. This project measures that failure directly, then fixes it.
Instrumenting the Support Router With Real Tracing and Evaluation
Not a fresh demo — this project takes LangGraph's real, already-verified support router and adds genuine LangSmith tracing, a real dataset built from its own confirmed failure scenarios, and a real evaluator that measures whether tickets actually reach the correct outcome.
Instrumenting the Crash-Safe Pipeline With Real Tracing and Evaluation
This project adds real LangSmith tracing to LangGraph's crash-safe research pipeline, and builds a real evaluator that checks whether the pipeline reaches its complete, correct result — whether or not a real crash and resume happened along the way.
Instrumenting the Approval Queue With Real Tracing and Evaluation
This project adds real LangSmith tracing to LangGraph's concurrent approval queue, and builds a real evaluator that checks a genuine concurrency invariant — exactly one real decision should win, never zero, never two — the exact bug the original project fixed, now guarded by a repeatable, automated check.