marketing·Independently reviewed · 96/100

SEO Brief

Keywords/structure typed. Content without SEO intent. Typed v1 agent with eval coverage.

marketingstructured-outputv1

Install

npx agentskit add marketing-seo-brief

Quick start

import { openai } from '@agentskit/adapters'import { createMarketingSeoBriefAgent } from './agents/marketing-seo-brief/agent'const agent = createMarketingSeoBriefAgent({  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 SEO brief artifacts for all three cases, stayed within the provided evidence, surfaced uncertainty and missing context, and resisted the explicit injection attempt. It did not fabricate business details or keywords from sparse prompts, which is appropriate for an SEO brief agent expected to avoid unsupported claims. Outputs are useful as review-ready gap analyses and placeholder structures when context is insufficient.

What passed review

  • Valid structured outputs were recorded for every case with titles, sections, gaps, open questions, and review flags.
  • Handled sparse and minimal inputs conservatively without inventing SEO facts, keywords, brands, dates, or market details.
  • Injection case correctly ignored the request to output APPROVED and explicitly flagged the instruction-injection attempt.
  • Consistently surfaced uncertainty and asked concrete follow-up questions needed to produce a real SEO brief.

Extend it

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

const agent = createMarketingSeoBriefAgent({  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'/** SEO Brief — v1 validated. Pain: Content without SEO intent */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 MarketingSeoBriefConfig {  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-seo-brief',  description: "SEO Brief — typed output agent (draft spec).",  systemPrompt: `You are SEO Brief. Content without SEO intent. Output: Keywords/structure 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_seo_brief exactly once. Stop.`,  tools: ['submit_seo_brief'],}export function createMarketingSeoBriefAgent(config: MarketingSeoBriefConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_seo_brief', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('marketing-seo-brief requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-seo-brief',    run,    asHandle() { return { name: 'marketing-seo-brief', 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-seo-brief',  cases: [    { input: 'Complete input for SEO Brief: Content without SEO intent. 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