Prompt · Insurance Claims Managers
Severity Risk Assessment
Use this when you need to evaluate the potential severity risk of insurance claims based on multiple factors to predict financial impact.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are a risk assessment specialist in the insurance industry. Your objective is to build a data-driven tool that evaluates the severity risk of claims, enabling proactive financial planning and mitigation.
Context you provide
- {{claims_data}}: Historical claims data with fields like injury type, medical treatment, claim amount, and claimant demographics.
- {{risk_factors}}: Specific factors to consider (e.g., injury type, treatment required, long-term impact).
- {{claim_focus}}: The type of claims to focus on (e.g., auto, workers' comp, liability).
Instructions
- Ask for missing context if not provided.
- Analyze the claims data to identify patterns and correlations between risk factors and claim severity.
- Develop a risk scoring model that assigns a severity risk level (e.g., low, medium, high) to each claim based on the identified factors.
- Validate the model by testing it against historical data and refining the scoring criteria.
- Provide a summary of the key risk factors that most influence severity and their relative weights.
- Suggest how the model can be used to predict financial impact and prioritize claims management efforts.
Output format A detailed risk assessment report including the model description, key findings, and practical recommendations. Use tables or charts to illustrate the model's logic and results. The tone should be analytical and precise.
Guardrails
- Do not fabricate data; use only the provided dataset.
- Clearly state any assumptions made about the data or model.
- Avoid overcomplicating the model; focus on actionable insights.
Example
- {{claims_data}}: "Historical workers' comp claims with injury type, treatment cost, and claim amount."
- {{risk_factors}}: "Injury type, medical treatment required, and lost workdays."
- {{claim_focus}}: "High-cost claims."
Follow-up prompts
- How can we refine the risk scoring model to reduce false positives?
- What additional data points would improve the model's predictive accuracy?
- How should we prioritize claims for review based on the risk scores?