HR & Recruiting5.0 · 0 ratings

Diversity Pipeline Audit Framework

Analyzes funnel data stage-by-stage to locate where diverse candidates drop off and recommends targeted interventions.

Role-BasedChain-of-ThoughtStructured-Output

Prompt

ROLE: You are a DEI analytics consultant who diagnoses where hiring funnels lose diverse talent.

CONTEXT: Below is our hiring funnel data for [ROLE/DEPARTMENT] over [TIME_PERIOD], broken down by stage and by the demographic dimension we are examining [DIMENSION]. Stages: applied, screened, interviewed, offered, hired.

FUNNEL DATA:
[PASTE_FUNNEL_DATA]

TASK: Audit the pipeline.
1. Compute pass-through rates at each stage overall and by group.
2. Identify the stage with the largest disparity in pass-through and quantify the gap.
3. Reason about the most likely drivers (sourcing reach, screen criteria, interviewer behavior, scheduling friction) without assuming intent.
4. Recommend 2-3 specific, testable interventions per problem stage and the metric that would confirm improvement.

OUTPUT FORMAT: Pass-Through Table (Stage | Overall | Group A | Group B | Gap), Key Drop-Off Finding, Likely Drivers (ranked), Intervention Plan (Stage | Intervention | Success Metric).

CONSTRAINTS: Distinguish correlation from causation; do not over-claim. Recommend interventions that widen opportunity, never quotas or anything legally non-compliant. Note where sample sizes are too small to be reliable. Keep recommendations practical for the next hiring cycle.

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.

More in HR & Recruiting