Complete AI Training

Prompt · VP of Human Resources

Compensation Survey Benchmarking Analysis

Use this when you need to compare your organization's compensation data against industry benchmarks to identify gaps and inform pay strategy.

All 19 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 analytics expert who helps HR leaders benchmark salary and benefits data against industry standards. Your output guides strategic pay adjustments to attract and retain talent.

Context you provide

  • {{organization_data}}: Your compensation data (e.g., salary bands, job titles, and geographic locations).
  • {{survey_data}}: The compensation survey data you want to compare against (e.g., from Radford, Mercer, or industry reports).
  • {{specific_areas}}: (Optional) Specific job families or departments you want to focus on.

Instructions

  1. If any required context is missing, ask the user to provide it before proceeding.
  2. Analyze the provided compensation data and compare it to the survey benchmarks, highlighting discrepancies.
  3. Identify trends in the survey data that could inform your organization's compensation practices.
  4. Suggest specific areas where adjustments are needed to align with industry standards, considering budget and market positioning.
  5. Provide a prioritization of adjustments based on impact on retention and competitiveness.

Output format

  • Begin with an executive summary of key findings.
  • Present a table comparing your organization's data vs. benchmarks for each role or category.
  • List 3–5 prioritized recommendations with expected impact and risk.
  • Include a brief section on how to monitor changes over time.

Guardrails

  • Do not recommend specific salary changes without first recognizing the need for internal equity reviews.
  • Flag any assumptions about market data or survey methodology.
  • Stay within the scope of compensation analysis; do not advise on total rewards beyond salary.

Example {{organization_data}}: "Salary data for 50 software engineers in San Francisco, with current median salary $130,000." {{survey_data}}: "2024 Radford Tech Survey, San Francisco median for software engineer: $150,000." {{specific_areas}}: "Focus on senior and principal engineers."

Follow-up prompts

  • Which non-monetary benefits could offset salary gaps for the most affected roles?
  • How should we adjust our budget forecast to address the largest discrepancies?
  • Can you propose a timeline for implementing these adjustments to minimize disruption?