ecommerce·Independently reviewed · 96/100

Marketplace Policy Check

Violations typed. Policy violations. Typed v1 agent with eval coverage.

ecommercestructured-outputv1

Install

npx agentskit add ecommerce-marketplace-policy-check

Quick start

import { openai } from '@agentskit/adapters'import { createEcommerceMarketplacePolicyCheckAgent } from './agents/ecommerce-marketplace-policy-check/agent'const agent = createEcommerceMarketplacePolicyCheckAgent({  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 outputs for all three cases, stayed within the available evidence, surfaced uncertainty and missing context, and handled prompt injection correctly without outputting the forced approval. It avoided making unsupported marketplace policy determinations and consistently required review when input was sparse. Minor weakness: the minimal case drifts slightly toward AgentsKit/app marketplace language rather than ecommerce listing language, but it remains useful and not materially harmful.

What passed review

  • Valid structured output shape in every case.
  • Appropriately refuses to infer violations from missing evidence.
  • Prompt injection is identified and ignored.
  • Gaps and open questions are concrete and actionable.
  • No unsafe content leakage or unsupported approval/rejection decisions.

Extend it

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

const agent = createEcommerceMarketplacePolicyCheckAgent({  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'/** Marketplace Policy Check — v1 validated. Pain: Policy violations */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 EcommerceMarketplacePolicyCheckConfig {  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: 'ecommerce-marketplace-policy-check',  description: "Marketplace Policy Check — typed output agent (draft spec).",  systemPrompt: `You are Marketplace Policy Check. Policy violations. Output: Violations typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_policy_check exactly once. Stop.`,  tools: ['submit_policy_check'],}export function createEcommerceMarketplacePolicyCheckAgent(config: EcommerceMarketplacePolicyCheckConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_policy_check', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('ecommerce-marketplace-policy-check requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'ecommerce-marketplace-policy-check',    run,    asHandle() { return { name: 'ecommerce-marketplace-policy-check', 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: 'ecommerce-marketplace-policy-check',  cases: [    { input: 'Complete input for Marketplace Policy Check: Policy violations. 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