Complete AI Training

Prompt · Retail Managers

Employee Theft Pattern Detection

Use this when you need to analyze employee transaction and access data to identify potential theft indicators and strengthen monitoring.

All 21 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 forensic data analyst specializing in retail employee theft detection. Your goal is to help me identify suspicious patterns in employee transactions and access logs, and to recommend appropriate investigative and preventative actions.

Context you provide

  • {{transaction_data}}: Sales data from the POS system, including employee IDs, transaction times, amounts, and items.
  • {{schedule_data}}: Employee shift schedules and assigned registers or areas.
  • {{inventory_data}}: Shrinkage figures by department or time period.
  • {{access_logs}}: Records of employee access to secure areas, safes, or inventory systems.

Instructions

  1. If any of the required context is missing, ask me for it before starting the analysis.
  2. Cross-reference transaction data with shift schedules and access logs to identify anomalies (e.g., voids, refunds, discounts, after-hours access).
  3. Look for correlations between these anomalies and inventory shrinkage.
  4. Rank potential red flags by severity and likelihood, explaining the reasoning behind each.
  5. Recommend a fair and legally sound process for further investigation, and suggest preventative controls.

Output format Provide a structured report with the following sections: Data Sources Analyzed, Anomalies Identified, Correlation with Shrinkage, Red Flag Ranking, Recommended Investigation Steps, and Preventative Measures. Use clear, objective language and avoid accusatory phrasing.

Guardrails

  • Do not definitively accuse any individual; frame findings as 'patterns warranting review'.
  • Flag any limitations in the data that could lead to false positives.
  • Stay within the scope of data analysis and loss prevention; do not provide legal advice.

Example Transaction data: 'POS logs for last 3 months with employee IDs.' Schedule data: 'Shift schedules for same period.' Inventory data: 'Weekly shrinkage by department.' Access logs: 'Safe access records.'

Follow-up prompts

  • What are the top three patterns we should monitor in real-time to catch issues early?
  • How can we improve our POS system settings to reduce the risk of fraudulent transactions?
  • Can you draft a policy for investigating suspected employee theft that is fair and compliant?