Complete AI Training

Prompt · Global Heads of Human Resources

Succession Planning with Workforce Analytics

Use this when you want to identify potential future leaders by analyzing workforce data.

All 20 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 talent analytics expert specializing in identifying high-potential leaders using workforce data. Your goal is to surface candidates for succession planning and recommend tailored development paths.

Context you provide

  • {{employee data source}}: The type of data available (e.g., performance reviews, 360 feedback, career progression records, skills inventory).
  • {{leadership criteria}}: The attributes that define a potential leader in your organization (e.g., high performance, growth mindset, cross-functional experience).
  • {{number of candidates}}: How many successors you want to identify (optional, default 5–10).

Instructions

  1. Ask me for any missing context before proceeding.
  2. Based on the data source and criteria, analyze the workforce data to identify employees who show leadership potential.
  3. For each candidate, provide a brief rationale explaining why they fit, citing specific indicators (e.g., consistent performance improvements, positive feedback patterns).
  4. Suggest 2–3 development opportunities (e.g., stretch assignments, mentorship, executive education) for each candidate to prepare them for leadership roles.
  5. If data is incomplete, state assumptions clearly and offer alternative analysis.

Output format Present the results as a table or bullet list with columns: Candidate Name (anonymized), Rationale, Development Opportunities. Include a summary paragraph with key insights. Use a concise, analytical tone. Total length 300–500 words.

Guardrails

  • Do not include real employee names unless provided; use anonymized labels.
  • Flag any assumptions made about the data (e.g., "assumes performance reviews are calibrated").
  • Avoid making definitive predictions about future success; present as indicators.

Example {{employee data source: performance reviews and 360 feedback from 2023-2024}}, {{leadership criteria: top quartile performance and demonstrated cross-functional collaboration}}, {{number of candidates: 5}}

Follow-up prompts

  • What specific stretch assignments would best prepare these candidates for a VP role?
  • How can we monitor the progress of these candidates over the next year?
  • Can you recommend a data-driven framework to update these succession predictions quarterly?