SDK Quick Start — Insurance: P&C, Life & Annuity
Getting started: Insurance: P&C, Life & Annuity
This guide takes you from install to your first attributed governance record in insurance: p&c, life & annuity. You will install the SDK, configure a provider, instrument a workflow step with the real OTel attribute vocabulary from this vertical, and have a reviewable evidence record in your portal within an afternoon. There is no scaffolding project — just your API key and the three steps below.
Why this matters right now. As of March 2026, agentic AI in insurance is deployed across: first notice of loss (FNOL) intake and triage, automated claims severity assessment, straight-through claims processing (STP) for low-complexity claims, AI-assisted underwriting decisioning, telematics-driven auto rating, predictive model governance and bias testing (NAIC Model Bulletin, Colorado Reg 10-1-1), prior authorisation adjudication (health), fraud ring detection, subrogation opportunity identification, reinsurance placement data preparation (ACORD GRLC Gen 2.0), and ORSA narrative generation. The NAIC Model Bulletin now operates as de facto national standard, enforced via state market conduct examinations. 92% of health insurers, 88% of auto insurers, and 70% of home insurers report current or planned AI use (NAIC 2025 survey). The NAIC Model Bulletin requires insurers to maintain an AIS (AI System) Program covering governance, consumer notice, risk management, internal controls, and vendor management for every AI system that makes or supports regulated insurance decisions. Colorado Regulation 10-1-1 extends mandatory bias testing and annual compliance reporting to life, auto, and health lines (effective Oct 15, 2025). The UnitedHealth/NaviHealth nH Predict and Cigna PxDx class-action cases demonstrate that autonomous AI claims denial without physician review creates direct litigation exposure.
How the layering works
You are not adopting a separate product surface for this vertical. You are adding a market-specific vocabulary layer on top of the same core session model used everywhere in VeriProof.
| Layer | What you configure | What changes downstream |
|---|---|---|
| Core SDK | API key, application identity, session lifecycle, export path, base governance metadata | The same trace, evidence, and export foundation used across every implementation |
| Insurance: P&C, Life & Annuity | OTel attributes, permitted values, and workflow metadata drawn from this vertical catalog | Portal evidence records, policy inputs, and exports become standards-literate for this market |
| Review surfaces | Rules, evidence packages, and internal reviewer workflows | The same labels and values appear without translation during review or audit |
If you need the cross-industry baseline first, open the core SDK reference, Python core, or .NET core before continuing here.
Step 1 — Install
TypeScript / Node.js
npm install @veriproof/sdk-corePython
pip install veriproof-sdk.NET
dotnet add package Veriproof.SdkStep 2 — Configure
Call the configuration helper once, before any AI framework initialises. After that call, every OTel span in the process — whether emitted by your code or by a framework adapter — is exported automatically to VeriProof.
Your API key comes from the VeriProof portal. Try a live demo to see the portal before you register, or start a free Builder account and use the environment variable pattern above directly.
Need a production credential path rather than sandbox exploration? Get API access for a Builder account, or contact the team if you need an architecture or compliance review alongside implementation.
Step 3 — Instrument your workflow
The governance vocabulary for this vertical lives in the Insurance: P&C, Life & Annuity reference. Use the OTel attribute names below — they are the same names the portal uses in evidence records and the same names your policy engine will evaluate. Consistency here is the point.
| OTel attribute | Sample value | Category |
|---|---|---|
insurance.policy.lifecycle_status | application_received | PolicyLifecycleStatus |
insurance.policy.transaction_type | new_business | PolicyTransactionType |
insurance.policy.line_of_business | personal_auto | InsuranceLineOfBusiness |
insurance.policy.cancellation_reason | non_payment_of_premium | PolicyCancellationReasonCode |
insurance.underwriting.decision_status | accepted_standard | UnderwritingDecisionStatus |
insurance.underwriting.ai_model_type | traditional_rule_based_engine | UnderwritingAIModelType |
TypeScript example
import { configureVeriproof, VeriproofClient, VeriproofSdkOptions, SessionMetadata } from '@veriproof/sdk-core';
import { PolicyLifecycleStatus, PolicyLifecycleStatusMeta, PolicyTransactionType, PolicyTransactionTypeMeta } from '@veriproof/sdk-core/verticals/insurance-pc-life-annuity';
// Call once at application startup
configureVeriproof(
VeriproofSdkOptions.createProduction({
apiKey: process.env.VERIPROOF_API_KEY!,
applicationId: 'insurance-pc-life-annuity-app',
}),
{ serviceName: 'insurance-pc-life-annuity-app', setGlobal: true },
);
// Instrument a governed workflow
const client = new VeriproofClient(
VeriproofSdkOptions.createProduction({ apiKey: process.env.VERIPROOF_API_KEY! }),
);
const session = client
.startSession('insurance.pc.life.annuity.review')
.withSessionMetadata(SessionMetadata.forTransaction('txn-001').withEnvironment('production'))
.addStep('evaluate', { output: { status: 'completed' } })
.withMetadata(PolicyLifecycleStatusMeta.otelAttribute, PolicyLifecycleStatus.application_received)
.withMetadata(PolicyTransactionTypeMeta.otelAttribute, PolicyTransactionType.new_business)
await session.complete();Python example
import os
from opentelemetry import trace
from veriproof_sdk import VeriproofClientOptions, configure_veriproof
from veriproof_sdk.verticals import insurance_pc_life_annuity as ipla
# Call once at application startup
configure_veriproof(
VeriproofClientOptions(
api_key=os.environ["VERIPROOF_API_KEY"],
application_id="insurance-pc-life-annuity-app",
),
service_name="insurance-pc-life-annuity-app",
set_global=True,
)
tracer = trace.get_tracer(__name__)
# Instrument a governed workflow
with tracer.start_as_current_span("insurance_pc_life_annuity.review") as span:
span.set_attribute(ipla.PolicyLifecycleStatus.__otel_attribute__, ipla.PolicyLifecycleStatus.application_received.value)
span.set_attribute(ipla.PolicyTransactionType.__otel_attribute__, ipla.PolicyTransactionType.new_business.value)
span.set_attribute(ipla.InsuranceLineOfBusiness.__otel_attribute__, ipla.InsuranceLineOfBusiness.personal_auto.value)
....NET example
using Veriproof.Sdk;
using Veriproof.Sdk.Core.OpenTelemetry.Verticals.InsurancePcLifeAnnuity;
// Configure once at application startup
builder.Services.AddVeriproof(options =>
{
options.ApiKey = builder.Configuration["VERIPROOF_API_KEY"]!;
options.ApplicationId = "insurance-pc-life-annuity-app";
});
// Instrument a governed workflow step
using var activity = ActivitySource.StartActivity("evaluate");
activity?.SetTag(PolicyLifecycleStatus.Metadata.OtelAttribute, PolicyLifecycleStatus.application_received);
activity?.SetTag(PolicyTransactionType.Metadata.OtelAttribute, PolicyTransactionType.new_business);
activity?.SetTag(InsuranceLineOfBusiness.Metadata.OtelAttribute, InsuranceLineOfBusiness.personal_auto);How teams use this in production
- Underwriting, Rating & Pricing: Rating Factor Category. OPA rule: deny any rating action where factor_category is prohibited_characteristic_proxy or social_media_derived until Colorado Reg 10-1-1 bias test has been completed and approved. (Colorado Sb21 169: ECDIS factors require bias testing for proxy discrimination)
- Underwriting, Rating & Pricing: ECDISBias Test Outcome. OPA rule: block production deployment of any underwriting model where ecdis_bias_test_outcome is testing_not_yet_performed, material_disparity_corrective_action_pending, or model_suspended_pending_remediation. (Colorado Reg 10 1 1: Annual compliance report due Dec 1 (life); July 1, 2026 (auto and health); bias test outcomes must be documented)
- Underwriting, Rating & Pricing: Insurance AIModel Inventory Status. OPA rule: deny any agentic underwriting or claims decision where the dependent model status is not_in_inventory_shadow_model or third_party_vendor_model_pending_assessment. (Naic Model Bulletin: AIS Program must maintain inventory of all AI systems used in regulated decisions)
- Claims Intake, Triage & FNOL: Claim Severity Tier. OPA rule: route all tier_7 and above claims to human adjuster — block STP. Require HITL with senior_adjuster role for tier_8 and above. Require claims_compliance_officer for tier_10.
Next steps
- Open the full Insurance: P&C, Life & Annuity governance reference for all 31 enum categories, policy patterns, and source standards.
- Review TypeScript SDK core for advanced session-builder options, batch export, and Merkle verification.
- Review Python SDK core for decorator-based annotations and framework adapter options.
- Review .NET SDK core for Semantic Kernel, AutoGen, and Activity-based instrumentation.
- Browse all vertical references to understand how the core governance vocabulary layers underneath vertical-specific attribute sets.
- Compare this guide with the public industry pages if you need the commercial and workflow framing behind the same vocabulary.
Register a free Builder account — 500 tamper-proof Proofs per month, full SDK and REST API access, and your first evidence record in the portal before you leave your desk.