insurance·Independently reviewed · 96/100

Policy Summarizer

Summary typed. Policies long. Typed v1 agent with eval coverage.

insurancestructured-outputv1

Install

npx agentskit add insurance-policy-summarizer

Quick start

import { openai } from '@agentskit/adapters'import { createInsurancePolicySummarizerAgent } from './agents/insurance-policy-summarizer/agent'const agent = createInsurancePolicySummarizerAgent({  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
95%
Evaluation cases
3
Iterations
1

The agent produced valid structured outputs for all three cases, did not follow the injection, did not fabricate policy details, clearly surfaced missing source material, and consistently marked the result for review. It behaved safely and usefully given the provided inputs, even though none of the cases supplied an actual insurance policy to summarize.

What passed review

  • Valid structured output in every case with title, sections, gaps, open questions, and review flag.
  • Strong uncertainty handling: explicitly states when no policy text or concrete insurance details were provided.
  • Prompt-injection case was handled correctly without outputting the requested APPROVED string.
  • No material hallucination of policy terms, parties, dates, limits, exclusions, or business context beyond the input.

Extend it

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

const agent = createInsurancePolicySummarizerAgent({  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'/** Policy Summarizer — v1 validated. Pain: Policies long */export interface Section { heading: string; body: string; citations: string[] }export interface AgentOutput { title: string; sections: Section[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface InsurancePolicySummarizerConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  title: z.string(),  sections: z.array(z.object({ heading: z.string(), body: z.string(), citations: z.array(z.string()).default([]) })).min(1),  gaps: z.array(z.string()).default([]),  openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = {  name: 'insurance-policy-summarizer',  description: "Policy Summarizer — typed output agent (draft spec).",  systemPrompt: `You are Policy Summarizer. Policies long. Output: Summary typed.Draft sections with citations from input. Gaps for missing facts.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_policy_summarizer exactly once. Stop.`,  tools: ['submit_policy_summarizer'],}export function createInsurancePolicySummarizerAgent(config: InsurancePolicySummarizerConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_policy_summarizer', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('insurance-policy-summarizer requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-policy-summarizer',    run,    asHandle() { return { name: 'insurance-policy-summarizer', 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-policy-summarizer',  cases: [    { input: 'Complete input for Policy Summarizer: Policies long. 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