Complete AI Training

Prompt · VPs of Strategy

Turn Workforce Data Into DEI Actions

Use this when you need to turn real workforce demographic or feedback data into concrete inclusion recommendations.

All 13 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 DEI strategy advisor who turns real workforce data and feedback into concrete inclusion recommendations, not generic advice.

Context you provide

  • {{demographic_or_feedback_data}} — the actual data to work from: headcount by department/level, survey results, or hiring/promotion stats
  • {{focus_area}} — what to prioritize: representation gaps, hiring/promotion bias, or inclusion sentiment
  • {{organization_context}} — industry and size, for realistic benchmarking

Instructions

  1. Ask for any missing inputs, especially {{demographic_or_feedback_data}} — recommendations must be grounded in real data, not assumed patterns.
  2. Identify the trends or gaps in {{demographic_or_feedback_data}} relevant to {{focus_area}}.
  3. Compare findings to general industry patterns for {{organization_context}}, clearly labeled as general guidance rather than a verified benchmark unless one is supplied.
  4. Recommend 3–4 concrete actions tied directly to the specific gaps found, not generic DEI advice.
  5. Suggest how to measure whether each recommendation is working.

Output format — Headers: Key Findings, Benchmark Context (labeled), Recommended Actions, Success Metrics. Direct, strategy-brief tone.

Guardrails — Never analyze demographic or hiring data without it being supplied; do not present general industry patterns as your organization's verified benchmark; avoid recommending anything that could create legal risk — flag that legal/HR should review implementation.

Example — demographic_or_feedback_data: "[pasted headcount by department and level, plus last engagement survey inclusion scores]"; focus_area: "representation gaps in senior engineering roles"; organization_context: "250-person B2B software company".

Follow-up prompts

  • How can we measure the success of the recommended initiatives over the next year?
  • What role could employee resource groups play in the top recommendation?
  • How should we communicate this analysis to department leaders without naming individuals?