DATA-462-christina.myers-2025-09-29-12-34-09

Below is a syllabus template that includes WSU's required syllabus elements. Please complete all items highlighted in yellow. 

 

Prompt Engineering for Data Analytics

DATA 462

Semester and Year [tbd]

3 Credit Hours 

Prerequisites: DATA 219; STAT/DATA 360

Course Details

Day and Time: [tbd]

Meeting Location: [tbd]

 

Instructor Contact Information

Instructor Name: [tbd]

Instructor Contact Information: [office location, phone, email] [tbd]

Instructor Office Hours: [click here for best practices] [tbd]

 

TA Name: [tbd]

TA Contact Information: [office location, phone, email]: [tbd]

TA Office Hours: [click here for best practices] [tbd]

 

Course Description

This course introduces undergraduate students to prompt engineering, with a focus on applications in data analytics. Students will learn to design, test, and refine prompts for large language models (LLMs) to perform data cleaning, transformation, summarization, visualization, and narrative generation. Emphasis is placed on hands-on projects, ethical considerations, and evaluation of outputs.

 

Course Materials 

Books: None

Suggested Readings & Resources

Required Readings:

  • White, J., et al. "Prompt Patterns for Better Conversations with Large Language Models." (Available online)

Recommended Resources:

Books/Guides:

  • Manning: Prompt Engineering in Practice (Early access version).
  • Hewing & Leinhos, "Prompt Canvas: A Literature-Based Practitioner Guide" (arXiv:2412.05127).
  • Jay Alammar et al., Hands-On Large Language Models” (O’Reilly, 2024)

Online Platforms:

  • NVIDIA/Coursera: Prompt Engineering and Data Analysis
  • DataCamp: Understanding Prompt Engineering.

Documentation & Repositories:

  • Open-source model hubs (HuggingFace, OpenLLM).
  • OpenAI Cookbook: Practical examples for prompt engineering.
  • LangChain documentation: Tools for chaining prompts and building workflows.

Fees: None

Student Learning Outcomes (SLOs)

By the end of the course, students will be able to:
• Explain key prompt engineering concepts (zero-shot, few-shot, chain-of-thought, role prompting).
• Design prompts for structured and unstructured data tasks.
• Use open-source LLMs and free APIs to build data analytics workflows.
• Evaluate prompt and LLM outputs for correctness, robustness, and bias.
• Integrate prompts into data pipelines and visualization workflows.
• Critically assess ethical and societal implications of LLM use.
• Collaborate effectively using version control and shared platforms (e.g., GitHub, Notion) for prompt development.
• Design inclusive prompts considering multilingual and accessibility needs.

Course Schedule

[Please note that a WSU semester is 15 weeks + Thanksgiving/Spring Break. The schedule below does not include the break.]
Module Dates Lesson Topic

Module 1: Foundations of Prompt Engineering (Weeks 1–4)

Week 1
[dates]

  Introduction to Prompt Engineering & LLMs
  • Overview of Prompt Engineering
  • Overview of LLMs and their role in data analytics
  • Fundamental prompting techniques: zero-shot, one-shot, few-shot prompting
  Week 2
[dates]

Prompt Structure & Basic Strategies

  • Anatomy of a prompt, instruction prompting
  • Role prompting and tone control
  • Prompt Pattern Catalog
  Week 3
[dates]

Prompting for Analytical Thinking

  • Chain-of-Thought (CoT) prompting
  • Self-consistency & reflective prompts
Prompt chaining
  Week 4
[dates]

Prompt Design Principles

  • Specificity, clarity, constraints
  • Best practices & common mistakes
  • Structured data: Prompting for data cleaning, transformation, feature generation
  • Unstructured data: Techniques for text extraction, summarization, sentiment analysis
Module 2: Prompting for Data Analytics Tasks (Weeks 5–9) Week 5
[dates]

Tools of the Trade (Hands-On)

  • Open-source LLMs (e.g., Llama, Mistral) and open APIs
  • Integrating LLMs into notebooks (Jupyter, Google Colab)
  Week 6
[dates]

Statistical Analysis Prompting

  • Prompts for data wrangling & missing value detection
  • Prompts for hypothesis testing, regression, correlation
Natural language → SQL generation
  Week 7
[dates]

Prompting for Visualization & Storytelling

  • Prompts for summaries, dashboards, and quick insights
  • Generating code for visualizations (Python: Matplotlib, Seaborn)
Automating narratives and report generation
  Week 8
[dates]

Machine Learning Assistance

  • Prompting for feature engineering, model selection, evaluation
  • Few-shot prompts for classification/regression examples
  • Midterm Project Proposal Presentations: Students present their proposed end-to-end prompt workflow projects for peer and instructor feedback.
  Week 9
[dates]

Evaluating Prompt and LLM Outputs

  • Assessing prompt effectiveness and refining prompts through feedback loops (human-in-the-loop evaluation).
  • Metrics to evaluate prompts, including correctness, reproducibility, and robustness.
  • Identifying and addressing hallucinations and inconsistencies in LLM outputs.
Module 3: Advanced Prompt Engineering (Weeks 10–14) Week 10
[dates]

Week 10: Advanced Prompting Techniques

  • Chain-of-thought, self-prompting, and meta-prompts.
  • Applications of these techniques for complex data analysis problems.
  • Tailoring prompts for different audiences.
  Week 11
[dates]

Bias, Fairness, and Ethics

  • Case studies on LLM bias and its implications for business and society.
  • Responsible AI use, privacy concerns, and mitigating misinformation.
  • Inclusive and accessible prompting practices.
  Week 12
[dates]

Domain-Specific Applications

  • Case studies: finance, healthcare, business analytics, social media
  • Applying prompt engineering concepts to real-world datasets
  Week 13
[dates]

Prompt Engineering in Hybrid ML Workflows

  • Comparing and combining prompt-based solutions with traditional machine learning models.
  • Determining when to use prompts vs. traditional methods.
  Week 14
[dates]

Scaling and Deployment

  • Prompt batching, cost estimation, and handling large datasets.
  • Tooling: Versioning prompts, monitoring performance, and wrapping prompts into simple applications.
  Week 15
[dates]

Final Project Work Sessions

  • Dedicated in-class time for students to work on their final projects with instructor support.

 

 

Expectations for Student Effort 

You are expected to spend a minimum of 9 hours per week on a three-credit course, of which 3 hours are spent on instructor-led activities (lectures and discussions) and 6 hours are spent on outside activities. These outside activities include, but are not limited to reading, studying, problem solving, writing, homework, and other preparations for the course. Achievement of course goals may require more than the minimum time commitment. For the most accurate and up to date information go to Academic Regulations.

 

Grading [add more lines if necessary]

Assignment Breakdown
Type of Assignment (tests, papers, etc) Percent of Overall Grade
Weekly Assignments  40%
Midterm Project Proposal 20%
Final Project 

A complete, end-to-end prompt workflow, including:

    • A reproducible notebook or application.
    • A detailed evaluation report of the outputs.
    • An ethical reflection paper.
    • A final in-class presentation.
 40%

 

Grading Schema
Grade Percent Grade Percent
A 93% - 100% C 73% - 76.99%
A-  90% - 92.99% C- 70% - 72.99%
B+  87% - 89.99% D+ 66% - 69.99%
B 83% - 86.99% D 60% - 65.99%
B- 80% - 82.99% F 0% - 59.99%
C+ 77% - 79.99%  

[Provide information about how grades will be rounded (eg, if 89% earns a B+ and 90% earns an A-, what grade is given to a student with an 89.5?]

Attendance and Make-Up Policy 

Students should make all reasonable efforts to attend all class meetings. However, in the event a student is unable to attend a class, it is the responsibility of the student to inform the instructor as soon as possible, explain the reason for the absence (and provide documentation, if appropriate), and make up class work missed within a reasonable amount of time, if allowed. Missing class meetings may result in reducing the overall grade in the class.

 

Academic Integrity Statement

You are responsible for reading WSU's Academic Integrity Policy, which is based on Washington State law. If you cheat in your work in this class you will:

-Be reported to the Center for Community Standards

-Have the right to appeal my decision

-Not be able to drop the course of withdraw from the course until the appeals process is finished

If you have any questions about what you can and cannot do in this course, ask me.

If you want to ask for a change in my decision about academic integrity, use the form at the Center for Community Standards website. You must submit this request within 21 calendar days of the decision.