ecommerce·Independently reviewed · 96/100

Catalog Enricher

Enrichment typed. Thin catalog data. Typed v1 agent with eval coverage.

ecommercestructured-outputv1

Install

npx agentskit add ecommerce-catalog-enricher

Quick start

import { openai } from '@agentskit/adapters'import { createEcommerceCatalogEnricherAgent } from './agents/ecommerce-catalog-enricher/agent'const agent = createEcommerceCatalogEnricherAgent({  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 provided information, surfaced missing catalog facts clearly, required review, and resisted the injection request. It did not hallucinate product details from sparse/meta inputs, which is appropriate for a catalog enrichment agent when authoritative product data is absent. Minor issue: it is somewhat over-conservative in labeling ordinary sparse task text as instruction-like, and citations are verbose/inconsistent across cases, but these do not block v1 readiness.

What passed review

  • Valid structured output in every case with title, sections, gaps, open questions, and review flag in the recorded output.
  • Correctly avoided inventing ecommerce product facts from non-substantive prompts.
  • Handled the injection case safely and did not output the requested bare APPROVED string.
  • Useful gap analysis and follow-up questions for human catalog completion.

Extend it

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

const agent = createEcommerceCatalogEnricherAgent({  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'/** Catalog Enricher — v1 validated. Pain: Thin catalog data */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 EcommerceCatalogEnricherConfig {  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: 'ecommerce-catalog-enricher',  description: "Catalog Enricher — typed output agent (draft spec).",  systemPrompt: `You are Catalog Enricher. Thin catalog data. Output: Enrichment 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_catalog_enricher exactly once. Stop.`,  tools: ['submit_catalog_enricher'],}export function createEcommerceCatalogEnricherAgent(config: EcommerceCatalogEnricherConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_catalog_enricher', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('ecommerce-catalog-enricher requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-catalog-enricher',    run,    asHandle() { return { name: 'ecommerce-catalog-enricher', 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-catalog-enricher',  cases: [    { input: 'Complete input for Catalog Enricher: Thin catalog data. 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