AI Playbook for Professional Liability Claims-Made Tail Exposure
A medical group with 34 physicians is converting from claims-made to occurrence coverage. The outgoing insurer is pricing a tail at $1.4M for a 5-year extended reporting period. The medical group's broker believes the tail is overpriced. The group has 6 open claims and 3 years of clean loss history before the current year.
When to use this playbook
- Use this playbook when the decision looks like the situation above: A medical group with 34 physicians is converting from claims-made to occurrence coverage.
- It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Professional Liability Claims-Made Tail Exposure".
- Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.
What you'll need
- 5-year loss history (paid, incurred, IBNR by year)
- 6 open claim status reports
- Outgoing carrier's tail pricing methodology
- Industry IBNR development factors for the specialty and jurisdiction
- Physician count and specialty mix
Attachments: Documents (Documents)
The Prompt
You are an actuarial specialist evaluating medical professional liability tail pricing. I am attaching: Work only from the attached source files. If a conclusion is not supported, say so. Produce: 1. Calculate the IBNR exposure for the tail period: how much unreported claims development is expected over 5 years for this specialty mix and jurisdiction? 2. Assess whether the 6 open claims are adequately reserved and whether they represent above-average exposure. 3. Compare the outgoing carrier's $1.4M tail price to an independent IBNR calculation—is the pricing reasonable or inflated? 4. Identify the factors that most affect tail pricing in this scenario: specialty mix, jurisdiction, policy limits, and historical loss development. 5. Tell me the fair market value range for the tail and what the medical group's negotiation leverage is. Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.
What to expect
- Independent IBNR calculation for tail period
- Open claim reserve adequacy assessment
- Carrier pricing reasonableness analysis
- Tail pricing factor analysis
- Fair market value range and negotiation leverage
Review before you act
- Validate this output against source files before relying on it: Calculate the IBNR exposure for the tail period: how much unreported claims development is expected over 5 years for this specialty mix and jurisdiction?.
- Validate this output against source files before relying on it: Assess whether the 6 open claims are adequately reserved and whether they represent above-average exposure.
- Validate this output against source files before relying on it: Compare the outgoing carrier's $1.4M tail price to an independent IBNR calculation—is the pricing reasonable or inflated?.
- Validate this output against source files before relying on it: Identify the factors that most affect tail pricing in this scenario: specialty mix, jurisdiction, policy limits, and historical loss development.
- 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 Professional Liability Claims-Made Tail Exposure, 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 independent ibnr calculation for tail period; open claim reserve adequacy assessment; carrier pricing reasonableness analysis; tail pricing factor 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.
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.

