> ## Content Index
> Fetch the complete content index at: https://fsc.stevens.edu/llms.txt
> Use this file to discover other available public pages before exploring further.

# FE 524: Business Applications in AI Systems Development
- URL: https://fsc.stevens.edu/fe524/
- Published: 2025-09-04T13:10:05.000Z
- Updated: 2026-10-15T17:12:28.000Z
- Author: hfsladmin
- Tags: Courses

Course Description

# Catalog Description

This course explores the applied use of large language models (LLMs). Participants will explore how to use LLMs with a programming language, structures to improve LLM outputs, common AI/LLM system architectures, how to use open LLMs, and how to evaluate the reliability and accuracy of LLMs. The course includes hands-on exercises, discussions, and real-world business applications. 

# Prerequisites

There are no course prerequisites, but students will need (1) general comfort using a computer with a command-line application like Terminal or PowerShell and (2) knowledge of Python or a commitment to learning it. 

# Course Outcomes

This 1-credit course aims for students to gain an understanding of the applied use of large language models (LLMs), particularly: 
- how to use LLMs with a programming language
- common LLM system architectures
- how to use open LLMs
- other related topics (harnesses, inference engines, frameworks, etc)
Concepts will be motivated by examples from quantitative finance or another business domain. 

Instructors

| Professor                                                                   | Email               | Office     |
| --------------------------------------------------------------------------- | ------------------- | ---------- |
| [Ed Loeser](https://fsc.stevens.edu/edward-loeser/ "edward-loeser-profile") | eloeser@stevens.edu | Babbio 109 |

  
Course Offerings

| Campus     | Fall | Spring | Summer |
| ---------- | ---- | ------ | ------ |
| On Campus  | X    | X      |        |
| Web Campus |      |        |        |

  
Course Resources

# Textbook

There is no required textbook. All material will be introduced during class. 

  
Grading

# Grading Policies

- Attendance - 10%
- Homework - 65%
- Project - 25%
  
Lecture Outline (subject to change)

|         | Topic                                                               | Assignment    |
| ------- | ------------------------------------------------------------------- | ------------- |
| Week 1  | course overview, Python setup                                       | HW 1          |
| Week 2  | few-shot learning, Python cont’d                                    | HW 2          |
| Week 3  | few-shot learning, REST APIs                                        | HW 3          |
| Week 4  | LLM APIs, data extraction                                           | HW 4          |
| Week 5  | open models, inference engines                                      | HW 5          |
| Week 6  | tool use, agents                                                    | HW 6          |
| Week 7  | retrieval-augmented generation (RAG), embeddings, similarity search | HW 7          |
| Week 8  | RAG applications, agents, project intro                             | HW 8, project |
| Week 9  | agents, harnesses                                                   | HW 9          |
| Week 10 | agents, harnesses, async                                            | HW 10         |
| Week 11 | agent frameworks, Model Context Protocol (MCP)                      | HW 11         |
| Week 12 | agent frameworks, frontends                                         | HW 12         |
| Week 13 | agent CLIs                                                          | HW 13         |
| Week 14 | training/fine-tuning overview                                       |               |
| Finals  | project presentations                                               |               |