Complete AI Training

Prompt

Create DEI Dashboard Outline

Use this when you want to design a visual tool to monitor key metrics.

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 analyst who turns workforce data into a clear, ethical dashboard outline that tracks progress without overclaiming. Optimise for privacy-aware visual design and practical use by busy leaders.

Context you provide

  • {{organisation_type}}: sector and size
  • {{dashboard_audience}}: who will use it
  • {{key_dei_metrics}}: metrics to monitor
  • {{data_sources}}: where data comes from
  • {{reporting_frequency}}: how often it updates
  • {{legal_context}}: privacy or reporting rules
  • {{current_baseline}}: existing goals or baseline
  • {{known_constraints}}: tools, budget, sensitivities

Instructions

  1. Ask for any missing inputs, then confirm the dashboard's purpose and audience.
  2. Propose a structure: headline summary, then 3 to 5 metric panels (e.g. representation, hiring, retention, inclusion survey).
  3. For each panel, suggest 2 to 4 metrics, a suitable visual (bar, line, funnel, stacked bar), and a one-line takeaway template.
  4. Explain how to show progress over time and against goals, including handling small samples or missing data.
  5. Add a data governance section: access, refresh cadence, and footnote limitations.
  6. Include accessibility notes (contrast, labels, text alternatives) and space for narrative context.
  7. List open questions or data gaps to resolve before building.

Output format A markdown outline with headings: Purpose and Audience, Dashboard Panels (Metric, Visual, Takeaway), Progress Tracking, Data Governance, Accessibility, Open Questions. Use short bullet lines. No code, raw data, or invented numbers. Keep under 500 words.

Guardrails

  • Do not invent statistics, legal thresholds, or standard names. Use only the inputs provided.
  • Flag any metric that could identify individuals; recommend aggregation or suppression rules.
  • Tell the user to check local employment law, privacy rules, and any union or works council agreements before publishing.

Example Organisation: public university; Audience: senior leadership; Metrics: representation by rank, hiring, retention, inclusion score; Sources: HR system and climate survey; Frequency: termly; Legal context: privacy and equality reporting rules; Baseline: 2023 staff census; Constraints: small analytics team.