HR & Recruiting5.0 · 0 ratings

Compensation Benchmarking Reasoner

Builds a structured compensation analysis and recommended salary band using market data inputs and internal equity checks.

Role-BasedChain-of-ThoughtStructured-Output

Prompt

ROLE: You are a total-rewards analyst who builds defensible compensation recommendations.

CONTEXT: We are setting pay for [JOB_TITLE] at [LEVEL] in [GEOGRAPHIC_MARKET]. Market data points I have gathered: [MARKET_DATA_SOURCES_AND_FIGURES]. Our internal comparators currently earn: [INTERNAL_RANGE]. Budget ceiling: [BUDGET]. Our pay philosophy targets the [PERCENTILE] percentile.

TASK: Recommend a salary band with clear reasoning.
1. Reconcile the market data points, noting outliers and source reliability.
2. Reason step by step toward a base range (min, mid, max) consistent with our target percentile.
3. Run an internal-equity check against the comparators and flag any compression risk.
4. Recommend the variable pay, equity, or sign-on structure if relevant.
5. List assumptions and the questions a compensation committee would ask.

OUTPUT FORMAT: Sections: Data Reconciliation, Recommended Band Table (Min/Mid/Max), Internal Equity Check, Total Comp Structure, Assumptions & Open Questions.

CONSTRAINTS: Show the reasoning that connects data to the band; do not output a number without justification. Stay within the stated budget ceiling or flag the conflict explicitly. Treat all figures as estimates and recommend validating with a current survey. Avoid any factor that could create pay discrimination.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

Open in Studio How to prompt AI correctly

More in HR & Recruiting

Structured Behavioral Interview Guide Builder

Generates a competency-mapped behavioral interview guide with STAR-anchored questions and a calibrated scoring rubric for any role.

Read prompt

Inclusive Job Description Rewriter

Rewrites a job description to remove biased language, reduce inflated requirements, and widen the qualified applicant pool.

Read prompt

Candidate Sourcing Boolean String Architect

Produces layered Boolean search strings and platform-specific variants to surface hard-to-find passive candidates.

Read prompt

Resume-to-Role Fit Screener

Evaluates a resume against a job description with an evidence-based fit score, gaps, and recommended screening questions.

Read prompt