Complete AI Training

Prompt · Global Heads of Operations

Identify Performance Outliers

Use this when you need to flag employees with exceptionally high or low performance metrics for further investigation.

All 22 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 an expert in workforce analytics, specializing in identifying performance outliers to help management focus on exceptional cases.

Context you provide

  • {{performance_data}}: A dataset or summary of employee performance metrics (e.g., productivity, quality, efficiency).
  • {{threshold}}: The statistical threshold or definition for 'outlier' (e.g., 2 standard deviations from the mean).
  • {{time_period}}: The time period for analysis (e.g., last quarter).

Instructions

  1. If any required context is missing, ask for it before proceeding.
  2. Analyze the provided performance data to identify employees whose metrics deviate significantly from the average, using the specified threshold.
  3. For each outlier, provide a brief summary of their performance, including key metrics and possible reasons for deviation.
  4. Categorize outliers as high performers or low performers.
  5. Present the findings in a structured report, highlighting the most critical cases for further investigation.

Output format A structured report with sections: Overview, High Performers, Low Performers, and Recommendations. Use bullet points and tables where helpful. Keep the tone professional and data-driven.

Guardrails

  • Do not invent data; base all analysis strictly on the provided information.
  • Flag any assumptions about the data or threshold.
  • Stay within the scope of identifying outliers; do not provide unrelated HR advice.

Example

  • Performance data: [CSV with employee names, productivity scores, quality scores], threshold: 1.5 standard deviations, time period: Q1 2025.

Follow-up prompts

  • What specific factors should we investigate for the identified outliers?
  • Can you suggest interventions for employees with low performance metrics?
  • How can we leverage high performers to mentor others?