ComparisonHigh riskComparison recommended

AI Commercial Auto Fleet Renewal Analysis Playbook

A national logistics company with a 1,200-vehicle fleet is up for renewal. The fleet has a 3-year combined loss ratio of 118%. The broker is claiming that 60% of the losses came from one catastrophic accident (an at-fault crash involving a fatality). The carrier's underwriting guidelines require a loss ratio below 90% for standard renewal.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A national logistics company with a 1,200-vehicle fleet is up for renewal.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Commercial Auto Fleet Renewal Analysis".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • 3-year loss run (all claims, by vehicle type, by driver, by loss cause)
  • Large loss detail for the catastrophic accident
  • Fleet safety program documentation (telematics, driver training, MVR policy)
  • Industry loss ratios for commercial trucking fleets at similar size
  • Current premium and proposed renewal terms

Attachments: Multiple attachments (Spreadsheets, Documents)

The Prompt

You are a commercial auto underwriter analyzing a 1,200-vehicle fleet with an adverse loss ratio. I am attaching:

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

Produce:
1. Normalize the 3-year loss ratio excluding the catastrophic loss: what is the attritional loss ratio, and how does it compare to industry benchmarks?
2. Analyze the non-catastrophic loss patterns: are frequency losses concentrated in specific drivers, vehicle types, routes, or time periods?
3. Assess the fleet safety program: does the telematics data show improving or deteriorating driver behavior trends?
4. Calculate the indicated premium at attritional loss cost and build the case for deviation from the 90% standard.
5. Tell me whether to renew, non-renew, or renew with conditions (driver exclusions, safety program requirements, increased retention).

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

What to expect

  • Normalized attritional loss ratio analysis
  • Non-catastrophic loss pattern analysis
  • Fleet safety program assessment
  • Indicated premium deviation analysis
  • Renew/non-renew/conditions recommendation with specific conditions

Review before you act

  • Validate this output against source files before relying on it: Normalize the 3-year loss ratio excluding the catastrophic loss: what is the attritional loss ratio, and how does it compare to industry benchmarks?.
  • Validate this output against source files before relying on it: Analyze the non-catastrophic loss patterns: are frequency losses concentrated in specific drivers, vehicle types, routes, or time periods?.
  • Validate this output against source files before relying on it: Assess the fleet safety program: does the telematics data show improving or deteriorating driver behavior trends?.
  • Validate this output against source files before relying on it: Calculate the indicated premium at attritional loss cost and build the case for deviation from the 90% standard.
  • 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 Commercial Auto Fleet Renewal Analysis, 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 normalized attritional loss ratio analysis; non-catastrophic loss pattern analysis; fleet safety program assessment; indicated premium deviation analysis. 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 UnderwritingCore Commercial LinesComparisonHighMultiple 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.