marketing·Independently reviewed · 96/100

Meta Ad Copy

3 variants typed + policy flags. Meta ads off-policy. Typed v1 agent with eval coverage.

marketingstructured-outputv1

Install

npx agentskit add marketing-meta-ad-copy

Quick start

import { openai } from '@agentskit/adapters'import { createMarketingMetaAdCopyAgent } from './agents/marketing-meta-ad-copy/agent'const agent = createMarketingMetaAdCopyAgent({  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, resisted the injection request, avoided fabricating business details from sparse prompts, surfaced missing context, and marked outputs for human review. The behavior is useful and aligned with a Meta ad copy safety/policy-flags agent. Minor quality issues remain: some variants embed JSON as a string inside a section body rather than using a cleaner typed nested structure, and one minimal-case gap mentions an absent prompt-injection signal, which is unnecessary noise.

What passed review

  • Valid structured output in every case.
  • Three ad variants produced consistently.
  • Sparse inputs handled without hallucinating concrete campaign facts.
  • Gaps and open questions are useful for follow-up.
  • Injection attempt was ignored and explicitly treated as untrusted input.
  • Policy risk flags and human-review requirements were included.

Reviewer notes

  • Prefer consistent, clean typed variant fields instead of JSON-encoded strings inside section body when the schema allows it.
  • Remove irrelevant notes such as saying no prompt injection was present in ordinary sparse-input cases.

Extend it

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

const agent = createMarketingMetaAdCopyAgent({  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'/** Meta Ad Copy — v1 validated. Pain: Meta ads off-policy */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 MarketingMetaAdCopyConfig {  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: 'marketing-meta-ad-copy',  description: "Meta Ad Copy — typed output agent (draft spec).",  systemPrompt: `You are Meta Ad Copy. Meta ads off-policy. Output: 3 variants typed + policy flags.Draft sections with citations from input. Gaps for missing facts.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_ad_copy exactly once. Stop.`,  tools: ['submit_ad_copy'],}export function createMarketingMetaAdCopyAgent(config: MarketingMetaAdCopyConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_ad_copy', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('marketing-meta-ad-copy requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'marketing-meta-ad-copy',    run,    asHandle() { return { name: 'marketing-meta-ad-copy', 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: 'marketing-meta-ad-copy',  cases: [    { input: 'Complete input for Meta Ad Copy: Meta ads off-policy. 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