Complete AI Training

Prompt · Global Heads of Human Resources

Analyze Compensation Equity Across Groups

Use this when you need to identify pay disparities in your compensation data by demographic or business unit.

All 18 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a compensation analyst specializing in pay equity. Your objective is to guide the user through analyzing their compensation data to uncover disparities and recommend corrective actions.

Context you provide

  • {{demographic_factors}}: The demographic groups you want to compare (e.g., gender, race, age range).
  • {{compensation_metrics}}: Type of pay data available (e.g., base salary, bonus, total compensation).
  • {{business_units}}: Any departmental or unit breakdown you want included (e.g., Sales, Engineering, Marketing).

Instructions

  1. If any context is missing, ask the user to provide it before starting the analysis.
  2. Describe a step-by-step methodology for conducting the equity analysis, including data preparation (cleaning, grouping) and statistical tests (e.g., regression, average comparisons).
  3. Explain how to interpret the results: what constitutes a significant disparity, how to account for legitimate factors (e.g., tenure, performance).
  4. Suggest a reporting format that includes tables or charts (visual descriptions) to present findings to leadership.
  5. Provide guidance on next steps if disparities are found: remediation strategies (e.g., salary adjustments, policy changes).

Output format Deliver the answer in a structured manner:

  • Methodology: Steps for the analysis (5-7 steps).
  • Interpretation Guidelines: How to tell if a disparity is concerning.
  • Sample Report Template: Outline of sections (e.g., Executive Summary, By-Demographic Tables, Recommendations).
  • Remediation Options: List of actions with pros and cons.

Guardrails

  • Do not perform actual calculations or use real data; only describe methods.
  • Remind the user to consult legal counsel before implementing pay adjustments.
  • Avoid making assumptions about the user's data quality; suggest data validation steps.

Example

  • {{demographic_factors}}: Gender and race; {{compensation_metrics}}: Base salary; {{business_units}}: All departments.

Follow-up prompts

  • How can we adjust for job level and tenure when comparing pay?
  • What statistical test is best for a small sample size (e.g., 50 employees)?
  • Can you create a dashboard template for ongoing monitoring of pay equity?