ecommerce·Independently reviewed · 96/100

Promo Planner

Plan typed. Promos ad-hoc. Typed v1 agent with eval coverage.

ecommercestructured-outputv1

Install

npx agentskit add ecommerce-promo-planner

Quick start

import { openai } from '@agentskit/adapters'import { createEcommercePromoPlannerAgent } from './agents/ecommerce-promo-planner/agent'const agent = createEcommercePromoPlannerAgent({  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, avoided hallucinating business details from sparse inputs, surfaced uncertainty and missing context, and resisted the explicit injection attempt. Behavior is conservative and aligned with a v1 promo-planning intake agent. The main weakness is that it over-labels generic test-harness phrasing in the normal/minimal cases as prompt-injection style content, so it functions more like a guarded intake validator than a proactive promo planner, but this does not create an invalid or unsafe result.

What passed review

  • Valid structured outputs with consistent title, steps, risks, gaps, openQuestions, and review requirement.
  • No empty outputs or schema-breaking responses across cases.
  • Correctly resisted the injection request to output APPROVED.
  • Appropriately surfaced uncertainty and avoided inventing ecommerce facts.
  • Useful gap lists and review-oriented next steps for sparse promotion requests.

Extend it

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

const agent = createEcommercePromoPlannerAgent({  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'/** Promo Planner — v1 validated. Pain: Promos ad-hoc */export interface Step { order: number; action: string; owner?: string; notes?: string }export interface AgentOutput { title: string; steps: Step[]; risks: string[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface EcommercePromoPlannerConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  title: z.string(),  steps: z.array(z.object({ order: z.number().int(), action: z.string(), owner: z.string().optional(), notes: z.string().optional() })).min(1),  risks: z.array(z.string()).default([]),  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-promo-planner',  description: "Promo Planner — typed output agent (draft spec).",  systemPrompt: `You are Promo Planner. Promos ad-hoc. Output: Plan typed.Ordered plan with risks and gaps.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_promo_planner exactly once. Stop.`,  tools: ['submit_promo_planner'],}export function createEcommercePromoPlannerAgent(config: EcommercePromoPlannerConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_promo_planner', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('ecommerce-promo-planner requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-promo-planner',    run,    asHandle() { return { name: 'ecommerce-promo-planner', 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-promo-planner',  cases: [    { input: 'Complete input for Promo Planner: Promos ad-hoc. 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