ComparisonHigh riskComparison recommended

AI Playbook for Umbrella/Excess Layer Pricing

A commercial underwriter is pricing a $25M umbrella layer excess of a $5M primary for a $500M revenue manufacturing company. The primary carrier has experienced $3.4M in losses in the past 3 years. The umbrella layer has been loss-free for 7 years. The broker is pushing for a flat renewal.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A commercial underwriter is pricing a $25M umbrella layer excess of a $5M primary for a $500M revenue manufacturing company.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Umbrella/Excess Layer Pricing".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • Primary carrier loss run (5 years, all lines)
  • Umbrella loss run (7 years, loss-free)
  • Current primary and umbrella policy terms
  • Industry excess loss development factors for manufacturing
  • Broker's renewal presentation with flat rate request

Attachments: Multiple attachments (Spreadsheets, Documents)

The Prompt

You are a commercial umbrella underwriter pricing a $25M excess layer for a manufacturing company. I am attaching:

Work only from the attached source files. If a conclusion is not supported, say so.

Produce:
1. Calculate the primary layer loss trend and assess whether primary losses are developing toward the umbrella attachment point in a modeled scenario.
2. Estimate the umbrella layer's expected loss cost using excess loss factors and the primary loss trend.
3. Assess the 7-year loss-free umbrella history: how much credit does this warrant vs. the adverse primary loss trend?
4. Calculate the indicated rate change for the umbrella layer and compare to the broker's flat renewal request.
5. Tell me the negotiation position: what rate increase is defensible, what conditions or coverage restrictions are warranted, and what the walk-away terms are.

Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.

What to expect

  • Primary loss trend and attachment point proximity analysis
  • Umbrella expected loss cost calculation
  • Loss-free credit assessment
  • Indicated rate change calculation
  • Negotiation position with walk-away terms

Review before you act

  • Validate this output against source files before relying on it: Calculate the primary layer loss trend and assess whether primary losses are developing toward the umbrella attachment point in a modeled scenario.
  • Validate this output against source files before relying on it: Estimate the umbrella layer's expected loss cost using excess loss factors and the primary loss trend.
  • Validate this output against source files before relying on it: Assess the 7-year loss-free umbrella history: how much credit does this warrant vs. the adverse primary loss trend?.
  • Validate this output against source files before relying on it: Calculate the indicated rate change for the umbrella layer and compare to the broker's flat renewal request.
  • Confirm every cited figure, date, counterparty, or requirement against the attached originals — models compress and can drop a qualifier.
  • Treat disagreement between models as a review item, especially on classification, materiality, and recommended next action.
  • Do not authorize an operational, clinical, legal, credit, or enforcement action solely because the models agree.

Why compare models on this

For Umbrella/Excess Layer Pricing, running the same attachments across independent models is useful because the hard part is classification and completeness, not fluency. The workflow is already designed to surface primary loss trend and attachment point proximity analysis; umbrella expected loss cost calculation; loss-free credit assessment; indicated rate change calculation. Those are comparison artifacts — they only exist if more than one model runs. Models split on tail scenarios, aggregation, and whether a hazard is excluded. Divergence is a referral to a specialist underwriter, not a silent average of three prices.

Insurance UnderwritingTreaty and ExcessComparisonHighMultiple attachments

See governed multi-model AI on your own prompt

Compare GPT-5, Claude, and Gemini side by side, with human review and a decision record built in.