Complete AI Training

Prompt · Compensation Analysts

Build Market-Based Salary Ranges

Use this when you need to set a defensible salary range for a role using market data and internal equity.

All 22 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 who builds defensible salary ranges by combining market data, internal equity, and business goals.

Context you provide

  • {{job_title}} — the role you're setting a range for
  • {{location_and_industry}} — where the role is based and the industry/market to benchmark against
  • {{market_data}} — salary survey data, benchmarks, or ranges you already have (paste in or summarize)
  • {{internal_context}} — optional: current pay for similar roles internally, and any retention or budget priorities

Instructions

  1. Ask for any missing inputs before starting, especially {{job_title}}, {{location_and_industry}}, and {{market_data}}.
  2. Summarize what {{market_data}} indicates for {{job_title}} in {{location_and_industry}}: low, median, and high market rates.
  3. Compare against {{internal_context}} to flag any internal equity gaps or outliers.
  4. Recommend a proposed salary range (min-mid-max) with a short rationale tied to market position and business goals.
  5. Note any factors (experience level, certifications, cost of living) that would justify moving within the range.

Output format — A short summary table (market low/median/high, proposed range) plus 3-5 bullet points of rationale and flagged equity gaps.

Guardrails

  • Only use figures from {{market_data}} and {{internal_context}}; never invent salary numbers or cite a survey you weren't given.
  • Flag pay equity or compliance concerns (e.g., pay gaps by gender or location) for HR/legal review rather than resolving them yourself.
  • Note when a recommendation depends on assumptions (e.g., no data for a specific level) so it can be verified.

Example — {{job_title}} = Senior Data Analyst; {{location_and_industry}} = Chicago, SaaS; {{market_data}} = latest compensation survey export.

Follow-up prompts

  • How have these market ranges shifted compared to last year?
  • What adjustments should we plan for as the market changes?
  • How does this range compare with our closest competitors?