The Deliverables

For Both Executive and Technical Readers

Engagement §04 lists eight things you receive. Here is one real example of each, drawn from Coastal_Property.bayes, the same 12-node model used on the Inference page.

Coastal_Property.bayes is a property-insurance portfolio model: twelve nodes running from Climate Trend and Storm Season through Building Age, Material Condition, and Code Compliance, into Flood Damage, Claim Severity, Rate Adequacy, Portfolio Loss, and Reinsurance Cost. The examples below are representative, illustrating the format and rigor of each artifact, not disclosing a named client's numbers. But every mechanism shown (the graph, the schema, the inference direction, the sensitivity check) is the real one this practice uses.

The Model Itself

A diagram of what drives what, reviewed and signed off by the named experts. This is the artifact executives use. Nobody needs to open Bayes Server to read it.

Coastal_Property.bayes open in Bayes Server, prior state, no evidence set. All twelve nodes shown with their elicited prior distributions: Climate Trend, Sea Level, Storm Season, Building Age, Storm Surge, Material Condition, Code Compliance, Flood Damage, Rate Adequacy, Claim Severity, Portfolio Loss, Reinsurance Cost.

This is the model itself, open in Bayes Server, prior state, no evidence set. Each bar chart is one node's elicited distribution: Climate Trend at top-left showing 40% Worsening, down through Storm Surge, Material Condition, and Code Compliance into Flood Damage, Claim Severity, Portfolio Loss, and finally Reinsurance Cost. Reading left to right along any row is reading the graph your experts signed off on.

This is a real screenshot of Coastal_Property.bayes open in Bayes Server, not a redrawn diagram. In an engagement, the causal map you receive is this same view, with every bar traceable back to the expert session that set it.

The Model Itself

Runs in Bayes Server. It is yours, no licence to me, no dependency on my continued involvement. Set evidence, run inference, and read the posterior directly.

Coastal_Property.bayes

12 nodes, 12 links, discrete 3-state variables throughout. Supports observational (Rung 1), interventional (Rung 2), and counterfactual (Rung 3) queries, the same file used for the forward, backward, and do() examples on the Inference page.

The Model Itself

A plain statement of what the model covers: which factors, which population, which kinds of question it can answer. It defines the model’s boundary so nobody applies it where it does not belong. This is the same Scope Card schema specified in EARA §5.2, filled in for this model.

Scope Card coastal_property_portfolio · v1.0.0
DomainProperty insurance, coastal underwriting
PopulationCoastal residential portfolio, current treaty year
VariablesClimate Trend, Storm Season, Building Age, Sea Level, Storm Surge, Material Condition, Code Compliance, Flood Damage, Claim Severity, Rate Adequacy, Portfolio Loss, Reinsurance Cost. 12 nodes
Supported queriesObservational, interventional, counterfactual (Rungs 1–3)
Evidence acceptedHard and soft evidence
AssumptionsNo unmeasured confounding between Code Compliance and Flood Damage beyond Building Age. Storm Surge screens Sea Level and Storm Season from all downstream nodes.
Valid regimeCurrent underwriting year; re-elicit on treaty renewal
Prepared by: Lead underwriter + actuarial lead Reviewed by: Engagement sponsor Signed: at model handover, week 6

Population, assumptions, and signatories are representative. A real engagement's Scope Card names the actual experts and the actual regime. The schema, the fields, and the fact that no model is invoked without one, are exactly as specified.

The Evidence It Works

What was checked mathematically, and what was checked against real outcomes, reported separately, per the Validation component: reliability diagrams, held-out log-score, and do() predictions compared against observed interventions. Where only the first was possible, the report says so.

Validation Report coastal_property_portfolio · v1.0.0
CheckMethodResult
CalibrationReliability diagram across all 12 nodes' posterior statesPredicted vs. observed frequency tracked within a few points across states, no systematic over- or under-confidence
Predictive fitHeld-out log-score on withheld claims, vs. a naive base-rate modelImproved held-out log-score; largest gain on Claim Severity, where Flood Damage carries real information the base rate lacks
Interventionaldo(Code Compliance = Compliant) predictions vs. a matched cohort of retrofitted propertiesDirectionally confirmed: retrofitted properties showed lower Flood Damage in the direction and rough magnitude the model predicted
Prepared by: Model author, with actuarial review Reviewed by: Engagement sponsor Run against: Coastal_Property.bayes v1.0.0

Figures are representative of the format this report takes, not a specific client's audited numbers. Where a real engagement lacks a matched cohort for the interventional check, the report states that plainly rather than substituting a correlational proxy.

The Evidence It Works

Which conclusions still hold if an expert’s estimate was wrong, per the Robustness component: perturb the CPTs, re-run, measure what changed. This is the section a regulator reads first.

Robustness Report coastal_property_portfolio · v1.0.0
CheckMethodResult
Sensitivity±15% perturbation of the elicited Code Compliance → Flood Damage CPTThe conclusion that do(Code Compliance = Compliant) lowers expected Portfolio Loss held under every perturbation tested. The direction is robust even if the exact magnitude the underwriters gave was off
Necessity of evidenceRe-run the Portfolio Loss = High attribution with each upstream node's evidence removed in turnRemoving Storm Season evidence changed the upstream posterior by a small margin, not necessary for this attribution. Removing Code Compliance evidence changed it substantially. That node was load-bearing
Prepared by: Model author Reviewed by: Engagement sponsor Run against: Coastal_Property.bayes v1.0.0

Why This MattersThe regulator's question is never "is the model right?" It's "how much of your recommendation depends on a number one expert guessed?" This report answers that directly, per conclusion, rather than asserting the model is generally trustworthy.

The Evidence It Works

Where every number came from and who supplied it. Provenance for the whole model. As the Inference page puts it: "The node probabilities were elicited from your underwriting and actuarial teams. I am not generating these numbers. I am reading them from the model."

Elicitation Record coastal_property_portfolio · v1.0.0
NodeElicited FromMethod
Storm SurgeCatastrophe modeling leadStructured interview against historical surge data by coastal segment
Material ConditionSenior property inspectorStructured interview + inspection-report sample review
Code ComplianceUnderwriting leadStructured interview against permit and retrofit records
Claim SeverityClaims directorStructured interview, cross-checked against five years of settled claims
Rate AdequacyActuarial leadStructured interview against current rate filings
Sessions run: Weeks 1–2, elicitation phase Recorded by: Reasoning architect Model version: v1.0.0

Names above are role titles, not individuals. A real elicitation record names the actual person, the actual session date, and the actual model version each number entered under. That specificity is the point: two years from now, a re-elicitation starts from what these people said last time, not from nothing.

Using and Keeping It

Real questions from your business, run end to end, each with the full record of how the answer was reached. These three are the same worked examples shown on the Inference page, reproduced here as deliverable entries rather than illustrations.

Worked Question Set coastal_property_portfolio · v1.0.0
Backward · attribution

“Portfolio Loss came in High this quarter. What upstream factors does that implicate?”

Evidence entered at Portfolio Loss = High and propagated upstream through Claim Severity, Flood Damage, and their parents. Answer derived from Coastal_Property.bayes; audit trail is the model file plus its elicitation record.

Interventional · what-if

“If we required Code Compliance across the portfolio, how much would that actually move Portfolio Loss?”

do(Code Compliance = Compliant) severs the edge from Building Age, isolating the effect of enforcement itself rather than the selection effect of which buildings happen to already comply. This is the query correlation cannot answer.

Forward · prediction

“Given the current Climate Trend and Storm Season outlook, what should we expect for Claim Severity?”

Evidence enters at the upstream nodes and propagates forward through Storm Surge, Material Condition, and Code Compliance to a posterior over Flood Damage and Claim Severity, the prediction direction, run before the season rather than after it.

Questions run: 3 of 3 answered without refusal Run against: Coastal_Property.bayes v1.0.0

Using and Keeping It

How to add a factor, re-run the elicitation, and tell when the model needs revisiting, so the model outlives the engagement.

Runbook coastal_property_portfolio · v1.0.0

Adding a factor. Example: your reinsurer starts pricing on treaty terms directly. (1) Identify its parents and children in the existing graph, here a new node feeding Reinsurance Cost alongside Portfolio Loss. (2) Elicit its CPT with the relevant expert, following the same structured-interview method used for the original 12 nodes. (3) Re-run the validation and robustness checks on any downstream node the new factor touches. (4) Bump the model version and reissue the Scope Card.

Re-running the elicitation. Reconvene the named experts from the original Elicitation Records. Walk each node's current CPT past them and ask only whether it still matches how the system behaves, not whether the model's conclusions "feel right." Log every change with who made it and why.

Knowing when to revisit. Three triggers: the model's predictions start missing systematically (a validation-report signal), the population shifts (a new coastal region enters the portfolio), or a structural assumption breaks (Code Compliance stops being observable the way it was elicited). Any one of these is sufficient on its own. Don't wait for all three.

Maintained by: Your team, post-handover Escalation: Ongoing support, as needed
Going further For what an engagement involves week to week, see The Engagement. For how these deliverables emerge from the elicitation process itself, see How a Model Gets Built. For the full worked inference walkthrough this page draws from, see Inference.