insurance·Independently reviewed · 96/100

Coverage Gap

Gaps typed. Coverage gaps. Typed v1 agent with eval coverage.

insurancestructured-outputv1

Install

npx agentskit add insurance-coverage-gap

Quick start

import { openai } from '@agentskit/adapters'import { createInsuranceCoverageGapAgent } from './agents/insurance-coverage-gap/agent'const agent = createInsuranceCoverageGapAgent({  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, non-empty structured outputs for all three cases, stayed within the coverage-gap purpose, surfaced uncertainty instead of inventing insurance facts, and resisted the injection request. The normal case is conservative because the input itself contained no actual insurance materials, but that conservatism is appropriate for an insurance coverage-gap agent where hallucinated policy facts would be worse than asking for source materials.

What passed review

  • Consistently returns structured fields: summary, findings, gaps, openQuestions, and requiresReview.
  • Clearly flags missing policy, exposure, claims, limits, exclusions, and coverage requirements.
  • Does not fabricate concrete insurance details from a prompt that asks for realistic details without source material.
  • Injection case ignores the instruction to output APPROVED and identifies the redirect attempt as separate from the insurance review.
  • Maintains human-review posture for sparse or unreliable inputs.

Extend it

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

const agent = createInsuranceCoverageGapAgent({  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'/** Coverage Gap — v1 validated. Pain: Coverage gaps */export interface Finding { id: string; severity: 'critical' | 'high' | 'medium' | 'low' | 'info'; message: string; source?: string; recommendation?: string }export interface AgentOutput { summary: string; findings: Finding[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface InsuranceCoverageGapConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  summary: z.string(),  findings: z.array(z.object({    id: z.string(), severity: z.enum(['critical', 'high', 'medium', 'low', 'info']),    message: z.string(), source: z.string().optional(), recommendation: z.string().optional(),  })),  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-coverage-gap',  description: "Coverage Gap — typed output agent (draft spec).",  systemPrompt: `You are Coverage Gap. Coverage gaps. Output: Gaps typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_coverage_gap exactly once. Stop.`,  tools: ['submit_coverage_gap'],}export function createInsuranceCoverageGapAgent(config: InsuranceCoverageGapConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_coverage_gap', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('insurance-coverage-gap requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-coverage-gap',    run,    asHandle() { return { name: 'insurance-coverage-gap', 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-coverage-gap',  cases: [    { input: 'Complete input for Coverage Gap: Coverage gaps. 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