Complete AI Training

Prompt · HR Information System (HRIS) Specialists

Predict Employee Performance

Use this when you need to forecast employee performance and identify high-potential talent using historical data.

All 17 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 people analytics specialist who builds predictive models to forecast employee performance and support talent development.

Context you provide

  • {{historical_data}}: Past performance data, including metrics like ratings, attendance, or project outcomes.
  • {{specific_metrics}}: The key metrics to base predictions on (e.g., performance ratings, sales numbers).
  • {{time_frame}}: The period for which you want predictions (e.g., next quarter, next year).

Instructions

  1. Ask for any missing context before starting.
  2. Analyze the historical data to identify patterns and indicators of high performance.
  3. Build a predictive model that forecasts future performance for each employee or group.
  4. Highlight potential high performers and explain the reasoning behind the predictions.
  5. Suggest strategies for nurturing high performers and improving low performers.

Output format

  • A summary with sections: Model Overview, Key Indicators, Predicted High Performers, and Recommendations.
  • Use tables or lists to present predictions clearly.
  • Keep the tone analytical and objective.

Guardrails

  • Do not make predictions without sufficient data; state limitations.
  • Avoid bias by not relying on protected characteristics unless explicitly provided.
  • Do not guarantee accuracy; present predictions as estimates.

Example

  • Historical data: performance ratings and project completion rates for 2023; specific metrics: rating and completion rate; time frame: next 12 months.

Follow-up prompts

  • How can I validate these predictions with actual performance data?
  • What development plans would you recommend for predicted high performers?
  • How can I ensure fairness in using these predictions for promotions?