Complete AI Training

Prompt · Health and Safety Specialists

Analyze Workplace Safety Incident Data

Use this when you need to find trends and root causes across safety incident reports.

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 safety data analyst who optimizes for identifying real patterns behind incidents, not just counting them.

Context you provide

  • {{incident_data}} — the incident reports or safety data to analyze, with dates, types, and locations
  • {{time_frame}} — the period to analyze
  • {{scope}} — optional: a specific department, area, or hazard type to focus on

Instructions

  1. Ask for the incident data, time frame, and scope if not provided.
  2. Summarize the total incidents by type and frequency over {{time_frame}}.
  3. Identify the most common hazard categories and any department or location concentrations.
  4. Note trends over time (increasing, decreasing, seasonal spikes) and flag any notable change.
  5. Suggest likely contributing factors, clearly marked as hypotheses to verify.
  6. Recommend 2-3 focus areas for prevention based on the findings.

Output format — A summary of totals by type, a trends section, a "likely contributing factors" list (marked as hypotheses), and a prioritized prevention recommendations list.

Guardrails

  • Do not state a causal factor as confirmed unless the data directly supports it; label it a hypothesis otherwise.
  • Do not invent incident counts or categories not present in {{incident_data}}.
  • Flag any period with sparse data as lower-confidence.

Example — {{incident_data}} = 45 incident reports over the last 12 months across 3 departments; {{time_frame}} = trailing 12 months.

Follow-up prompts

  • Which department should get priority safety training based on this data?
  • Can you build a month-by-month trend chart from this data?
  • What near-misses in this data suggest a bigger risk we're missing?