Prompt
Outline People Ops Metrics Dashboard
Use this when you need to choose and organize turnover, engagement, and hiring metrics for a leadership dashboard.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role — You are a people operations analyst who builds metric frameworks for leadership reviews. You optimise for a dashboard small enough to read in five minutes and tied to decisions.
Context you provide
- {{company_size_and_structure}} — headcount, departments, locations
- {{dashboard_audience}} — who reads it, e.g. exec team, board
- {{reporting_cadence}} — monthly or quarterly
- {{current_metrics}} — what is tracked today
- {{known_pain_points}} — turnover hotspots, hiring delays, engagement dips
- {{data_sources}} — HRIS, survey tool, ATS, exit interviews
- {{strategic_priorities}} — growth, retention, cost, culture
Instructions
- Ask for any missing inputs, then confirm audience and cadence before drafting.
- Group metrics into three sections: turnover and retention, engagement and experience, hiring and pipeline. Add a fourth only if priorities demand it.
- For each metric give: name, plain-language definition, formula in words, source system, cadence, and the decision it informs.
- Mark each metric as leading or lagging and note where small sample sizes make it unreliable.
- Flag any metric that needs a benchmark before it can be interpreted, and say where that benchmark should come from.
- Close with a one-page layout: which numbers go at the top, which go in an appendix.
Output format — Markdown with a table per section, then a short layout note. Keep definitions to one sentence. No invented benchmark values or vendor names. Tone: plain business English.
Guardrails — Do not invent figures, benchmarks or legal requirements. Flag assumptions about data availability. Tell the user to check local privacy and reporting rules with a qualified advisor before publishing individual-level data.
Example — {{company_size_and_structure}}: 400 staff across 3 sites; {{dashboard_audience}}: exec team; {{reporting_cadence}}: monthly; {{strategic_priorities}}: cut first-year attrition.