insurance·Independently reviewed · 96/100

Renewal Risk

Risk typed. Renewal risk. Typed v1 agent with eval coverage.

insurancestructured-outputv1

Install

npx agentskit add insurance-renewal-risk

Quick start

import { openai } from '@agentskit/adapters'import { createInsuranceRenewalRiskAgent } from './agents/insurance-renewal-risk/agent'const agent = createInsuranceRenewalRiskAgent({  adapter: openai({    apiKey: process.env.OPENAI_API_KEY!,    model: 'gpt-4o',  }),})const result = await agent.run('Describe your task here')console.log(result.content)

Independent reviewer approved

Validation evidence

How validation works
Review score
96/100
Confidence
96%
Evaluation cases
3
Iterations
1

The agent produced valid structured renewal-risk outputs for all cases, stayed within the provided evidence, handled sparse inputs safely with neutral medium risk and explicit gaps, and resisted the injection request without leaking or contradicting purpose. The normal case did not include actual renewal facts, so the conservative no-data assessment was appropriate rather than hallucinating details.

What passed review

  • Valid structured outputs with score, band, factors, rationale, gaps, and requiresReview.
  • Appropriately surfaces uncertainty and missing renewal-risk evidence.
  • Injection case ignores the instruction to output APPROVED and documents the redirect attempt.
  • No material hallucination beyond the supplied inputs.

Extend it

Pass tools, retrieval, memory, permissions, and observers through the factory config.

const agent = createInsuranceRenewalRiskAgent({  adapter,  tools,  retriever,  memory,  onConfirm: (call) => approve(call),  observers: [tracer],})
View agent factory source
import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'import { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'import { invokeStructured } from '@agentskit/runtime'import { defineZodTool } from '@agentskit/tools'import { z } from 'zod'import { zodToJsonSchema } from 'zod-to-json-schema'import type { JSONSchema7 } from 'json-schema'/** Renewal Risk — v1 validated. Pain: Renewal risk */export interface AgentOutput { score: number; band: 'low' | 'medium' | 'high' | 'critical'; factors: string[]; rationale: string; gaps: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface InsuranceRenewalRiskConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  score: z.number().min(0).max(100),  band: z.enum(['low', 'medium', 'high', 'critical']),  factors: z.array(z.string()),  rationale: z.string(),  gaps: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = {  name: 'insurance-renewal-risk',  description: "Renewal Risk — typed output agent (draft spec).",  systemPrompt: `You are Renewal Risk. Renewal risk. Output: Risk typed.Score 0-100 with explicit factors from input.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_renewal_risk exactly once. Stop.`,  tools: ['submit_renewal_risk'],}export function createInsuranceRenewalRiskAgent(config: InsuranceRenewalRiskConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_renewal_risk', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('insurance-renewal-risk requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${fenceUntrustedContent(input)}`,      parse: (a) => Output.parse(a),      skill,      memory: config.memory,      observers: config.observers,      onConfirm: config.onConfirm,      maxSteps: config.maxSteps ?? 4,    })    return { ...result, requiresReview: true }  }  return {    name: 'insurance-renewal-risk',    run,    asHandle() { return { name: 'insurance-renewal-risk', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },  }}
View evaluation contract

Replay these cases with the provider and model you plan to deploy.

import type { EvalSuite } from '@agentskit/eval'export const suite: EvalSuite = {  name: 'insurance-renewal-risk',  cases: [    { input: 'Complete input for Renewal Risk: Renewal risk. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) },    { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 },    { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) },    { input: 'Empty context — only says "process this".', expected: (r: string) => r.length > 5 },  ],}

Was this agent useful?

Your response helps us prioritize agent quality.

Keep exploring

Related agents

View category