Advanced Software Development with AI

Overview

This course explores how AI is reshaping software engineering practice. We'll start with LLM foundations and core agent capabilities like context, tools, and reasoning, then move into building and training real coding agents. From there, we'll turn to evaluating, verifying, and securing those agents through benchmarks, trustworthiness, and red teaming, wrapping up with final project presentations.

Course Details

• Term: Fall 2026
• Instructor: Baishakhi Ray
• Schedule: Fridays, 10:10am to 12:40pm
• Location: 451 Computer Science Building
• Course Number: COMS W4995, Section 004
• Points: 3
• Method of Instruction: In-Person

Course Links

• Vergil

Instructors

• Baishakhi Ray

Teaching Assistants

• Ira Ceka
• Alex Mathai

Syllabus

Date	Topic
September 11, 2026	FoundationsTransformers & LLMs (encoder-decoder architectures, scaling laws), training paradigms overview, harness, prompt engineering
September 18, 2026	ContextRAG, tool use (e.g. local tools, search tools), ReAct paradigm
September 25, 2026	Inference & ServingTop-k, Ollama, vLLM, SGLang
October 2, 2026	TrainingReinforcement learning, advanced RL
October 9, 2026	Coding AgentsPopular CLIs (Codex, Claude Code), skills.md, subagents, memory, loops
October 16, 2026	EvaluationSWE benchmarks, evaluation methodology
October 23, 2026	Verification & Trustworthiness (Part 1)
October 30, 2026	Verification & Trustworthiness (Part 2)
November 6, 2026	Security & Safety
November 13, 2026	Red Teaming
November 20, 2026	Advanced Topics
November 27, 2026	No Class (Thanksgiving Recess)
December 4, 2026	Final Presentations

Course Outcomes

• Explain how LLMs and agents work
• Build an agent from scratch
• Train and improve agents with reinforcement learning
• Evaluate agents using existing SWE benchmarks and build custom evaluation suites
• Understand verification layers and trustworthiness in agentic code generation
• Conduct adversarial red teaming to identify vulnerabilities and harden agentic security