Class Information
Time: Mondays, 7:00 PM - 9:30 PM
Location: 415 Schapiro CEPSR
Term: Fall 2026
Description
Welcome to COMS 4995-15! In this course, you will learn how to practically instantiate and apply LLMs by designing intelligent, interactive agents. Moving beyond basic prompting, this course explores the full lifecycle of building LLM-powered applications, from reasoning and planning to extending capabilities with memory, retrieval, and tool integration. Through hands-on projects, you will learn techniques such as Retrieval-Augmented Generation (RAG) and multi-step agent design, while also addressing reliability and safety by diagnosing failure modes, implementing guardrails, and conducting systematic evaluations. The course culminates in a final project where you build and present your own LLM agent. Python proficiency is required, but no prior machine learning background is assumed.
Important Links
Course Schedule
| Week | Date | Lecture Topic | Homework |
|---|---|---|---|
| Module 1: Interacting with LLMs | |||
| 1 | Sep 14 | What is an Agent? A brief history of language modeling | HW 1 Released |
| 2 | Sep 21 | LLM architectures and training | |
| 3 | Sep 28 | How does an LLM generate text? | HW 1 Due HW 2 Released |
| 4 | Oct 5 | Prompting, Reasoning, & Memory | |
| Module 2: Building an LLM Agent | |||
| 5 | Oct 12 | Post-training & Retrieval | HW 2 Due HW 3 Released |
| 6 | Oct 19 | Prompt chaining, routing, and planning | |
| 7 | Oct 26 | Tool Calling, Frameworks, & MCP | HW 3 Due |
| - | Nov 2 | Academic Holiday - No Class | |
| 8 | Nov 9 | AI safety | Final Project Released |
| 9 | Nov 16 | Vibe coding & agent evaluation | Project Proposal Due |
| Module 3: LLM Agents in the real world | |||
| 10 | Nov 23 | Guest Lectures: Open problems with LLM agents | |
| 11 | Nov 30 | Guest Lectures: Deploying LLM agents in industry | |
| 12 | Dec 7 | Final Project Presentations | |
| 13 | Dec 14 | Final Project Presentations | Final Project Due |
Assignments & Grading
Assignments are due at 11:59 PM Eastern Time. Every student has 3 late days that may be used at their discretion across the semester; beyond this allowance, late work will not be accepted. Grades will be 45% homeworks, 35% final project, and 20% participation. Participation is based on attendance + completion of class labs and activities. You are allowed to miss class 2 times without penalty.
Course Staff
