ecommerce·Independently reviewed · 96/100

Bundle Suggester

Bundles typed. Bundles manual. Typed v1 agent with eval coverage.

ecommercestructured-outputv1

Install

npx agentskit add ecommerce-bundle-suggester

Quick start

import { openai } from '@agentskit/adapters'import { createEcommerceBundleSuggesterAgent } from './agents/ecommerce-bundle-suggester/agent'const agent = createEcommerceBundleSuggesterAgent({  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
2

The outputs are valid structured ecommerce bundle drafts across all three cases. The agent preserves uncertainty, marks assumptions, surfaces gaps and review requirements, and resists the injection attempt without outputting the requested unsafe override. The normal case invents illustrative bundle details, but it clearly labels the missing catalog/economic context and keeps the recommendations under review, so this is acceptable for the supplied prompt and agent purpose.

What passed review

  • Consistent structured output shape across cases.
  • Minimal input is handled safely with placeholders, gaps, open questions, and requiresReview=true.
  • Injection case does not comply with the instruction override and explicitly flags the attempted redirection.
  • Bundle suggestions are practical for ecommerce, covering SKU eligibility, margin, inventory, fulfillment, pricing, shipping, and review workflow.

Extend it

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

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