Generative AI for the making of software.
Fifteen graduate scholars spent twelve weeks at the College of William & Mary learning how code-aware language models actually behave: where they hallucinate, how to measure their failures, and how to build workflows that don't collapse in production. Eleven projects shipped this spring.
Eight chapters of theory and practice.
Each chapter is an overview of the topics studied in detail across lectures, lab handouts, and seminar discussions.
Mining repositories
Collecting, cleaning, and tokenizing source-code data from public repositories. PyDriller, BPE, deduplication with MinHash, and the ethics of training on copyleft code.
Modeling code
From n-grams to the naturalness hypothesis. Probability refresher, MLE, perplexity, smoothing, sampling temperature — and why code is more predictable than English.
Evaluating rigorously
Classification metrics, BLEU and its discontents, CodeBLEU, pass@k, embeddings, SIDE, and the unglamorous human-evaluation rubric the best papers include without making a show of it.
Deep learning
Neural networks, backpropagation, embeddings, LSTM/GRU, attention, transformers, autoregressive generation, pre-training, and fine-tuning — the engine room.
Prompting LLMs
In-context learning, few-shot, chain-of-thought, prompt engineering, RAG, tool use, context-window management, prompt chaining, self-consistency, and prompt evaluation.
Hallucinations in code
How LLMs fabricate, the CodeHalu taxonomy, RAG mitigation, prompt defenses, tool-augmented generation, production case studies, and hallucination-resistant workflows.
Vibe coding & agents
Iterative human-LLM coding loops, autonomous coding agents with tool use, MCP, structured outputs, agent harnesses, evaluation under autonomy, and the practical patterns for shipping production code via natural-language workflows.
NP-completeness
Reductions, hardness, and what LLMs do when the underlying problem isn't tractable. Where statistical pattern-matching collides with the unforgiving floor of computational complexity.
Genetic algorithms
Population search, fitness landscapes, crossover, fitness approximation with LLM predictors, the GA+LLM architecture, and the honest limits of evolutionary search over code.
Fifteen students.
The Fall 2025 roster of CSCI 655 — fifteen students across eleven capstone groups, sorted by student number. Open the cohort page for full profiles and per-student capstones.
Eleven capstones, nine domains.
Each group chose a real problem, scoped a system, and built something that runs. Reviewed against five rubric criteria — market analysis, differentiation, technical framework, vibe-coding, and live demo. All eleven groups shipped on schedule.
Stock Investment AI
An algorithmic stock-prediction interface with explainable retrieval-grounded recommendations. Pairs price-signal modeling with LLM-generated reasoning over filings.
Multimodal Video Indexing
Natural-language search across video archives, replacing brittle metadata-only retrieval with vision-and-language embeddings indexed at scene granularity.
Sports Betting Arbitrage
Real-time cross-sportsbook arbitrage detection with risk-aware position sizing. Surfaces price disagreements before they close.
PlotForge
A plotting interface for data analysis aimed at students, educators, and lightweight analysts. Natural-language to charting with iterative refinement.
BURT++
A bug-report assistant that translates non-technical user complaints into actionable engineering tickets — clarifying reproduction steps as it goes.
GenAI Claim Verification
Retrieval-augmented evidence pipeline for verifying factual claims, attaching source citations with calibrated confidence.
W&M Degree Map
A planning tool for liberal-arts students navigating complex general-education requirements. Goal-aware course recommendations with clear-eyed prerequisite traversal.
RAG Rules · Ultimate Frisbee
A retrieval-augmented rules interpreter for self-officiated Ultimate Frisbee. Answers in-game questions by grounding in the official rulebook.
CodeCaster
A coding assistant for social-science students learning to program for data analysis. Designed for the first hundred lines, not the next thousand.
Youth Sports Registration
A multilingual youth-sports registration platform with serious accessibility focus — built to reach families current platforms exclude.
AI-Powered Job Search
A unified career platform consolidating fragmented job-seeker tooling into one assistant — resume, search, outreach, and prep in a single workflow.