Skip to Main Content

Legal Writing & Research

Material for in-class librarian research sessions.

Review Equal Pay Practice Assignment & GenAI

October 8, 2024

Learning Objectives

Students will…

Research Review

  1. Reflect on their ability to conduct legal research for the California Equal Pay Practice Assignment to identify strengths and areas for improvement.

Generative AI

  1. Apply the RICE prompt engineering principles to create a prompt for Lexis’s AI Assistant.
  2. Execute generative AI prompts for legal research in Lexis’s AI Assistant and Westlaw’s Ask Practical Law AI.
  3. Analyze usage, input, and output factors of AI-generated content to determine its usefulness and reliability for legal research.

Equal Pay Hypo

A new client, Farrah Peyton, has visited your law firm. She is a female software developer for a California company, EquiSoft. She recently learned that a male employee of her company earns $155,000 in annual base salary, which is $20,000 more than Farrah earns each year. The male employee has worked at the company one year longer than Farrah. However, the two have the same job title and job duties, and Farrah believes they both have received substantially similar annual performance reviews since being employed at EquiSoft. Before joining EquiSoft, Farrah earned 130,000 per year in her previous job, and she has learned that her male counterpart earned $150,000 per year in his previous job. He has 20 years of relevant experience and Farrah has 10 years of relevant experience. She would like to bring a case against her company for unequal pay based on sex under California’s Labor Code. She wonders if the company could successfully argue that they based these employees’ different pay on the salary they earned at their last job, not on the basis of sex. 1) Does Farrah have sufficient evidence to bring her case, and 2) does EquiSoft have evidence it can use to show that the difference in pay was permitted under the California Labor Code? Focus your research on the California code, California cases, and California secondary sources.  

Generative AI

Evaluating Generative AI Content

Usage: “Did I use the right tool?” Input: “Did I use an effective prompt?” Output: “Did the tool give an acceptable response?”
  • Designed purpose of tool
  • Scope of training and/or RAG
  • Tool transparency
  • Prompt engineering principles (RICE)
  • Influence of follow-up interactions
  • Missing perspectives from prompts
  • Source & accuracy verification
  • Bias & perspective in response
  • Interaction dynamic between AI & user
  • Critical evaluation considering ultimate research objective

Adapted from Mary Ann Naumann, Re-Engineering Research: Integrating Generative AI & Prompt Engineering into Information Literacy Programs (June 30, 2024).

 

Principles of Prompt Engineering: RICE

  • R: Role (assigning a role to the AI)
    • Some legal AI tools, including Lexis and Westlaw tools, do not require the prompt to include a role because the legal role is built into the tool.
  • I:   Instructions (specific tasks for the AI)
  • C: Context (providing necessary background info)
  • E: Expectations (clarifying desired outcomes)
    • Constraints/formatting the response should follow
    • Examples of how to complete the instructions

Sarah Gotschall, A Legal Research Prompting Guide and Generative AI System Comparison Exercise, AI Law Librarians (July 17, 2024), https://www.ailawlibrarians.com/2024/07/17/a-legal-research-prompting-guide-and-generative-ai-system-comparison-exercise/.