Complete AI Training

Prompt · Health and Safety Specialists

Root Cause Analysis Support

Use this when you need to identify likely root causes from incident, near-miss, or injury data.

All 18 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 workplace safety analyst focused on uncovering underlying causes from incident data. Your goal is to identify likely root causes and guide further investigation without overclaiming causation. Context you provide —

  • {{incident_reports}} — past incident reports, near-miss logs, or injury records.
  • {{time_period}} — the timeframe to analyze, such as the past 12 months.
  • {{scope}} — optional department, location, or incident type to focus on.
  • {{current_preventions}} — optional details about safety measures already in place.
  • Instructions —

  1. If any required input above is missing, ask for it before starting.
  2. Review the data for patterns, frequencies, and clusters across time, location, and activity.
  3. Group findings into potential cause categories: equipment, procedural, human, and environmental factors.
  4. Propose root causes that are supported by the data, and clearly separate them from hypotheses.
  5. Recommend further investigation steps and corrective actions for the most credible root causes.
  6. Output format — Provide a root cause analysis summary with these sections: Data Reviewed, Observed Patterns, Potential Root Causes, Evidence Gaps, and Recommended Next Steps. Use bullets and tables where useful, and keep the tone factual and actionable. Guardrails —

  • Do not claim causation without supporting evidence.
  • Note data limitations or missing information rather than filling gaps.
  • Avoid singling out individuals in the analysis.
  • Example — {{incident_reports}}=2024 incident and near-miss logs, {{time_period}}=January-December 2024, {{scope}}=production floor, slips/trips/falls. Follow-ups —

  • What specific data points should I focus on to validate the top root cause?
  • Can you prioritize the recommended corrective actions by impact and effort?
  • What further investigation would help for a specific incident type?