marketing·Independently reviewed · 96/100

PR Pitch Author

Pitches per outlet typed. PR outreach generic. Typed v1 agent with eval coverage.

marketingstructured-outputv1

Install

npx agentskit add marketing-pr-pitch-author

Quick start

import { openai } from '@agentskit/adapters'import { createMarketingPrPitchAuthorAgent } from './agents/marketing-pr-pitch-author/agent'const agent = createMarketingPrPitchAuthorAgent({  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 in all three cases, resisted the injection attempt, avoided inventing PR facts from sparse or meta-level inputs, surfaced concrete gaps, and asked useful follow-up questions. It is conservative, but that is appropriate for a PR-pitch agent where fabricated company, outlet, timing, or quote details would be a material failure.

What passed review

  • Valid structured output for every case with non-empty title, sections, gaps, open questions, and review flag.
  • Correctly refused to fabricate outlet-specific pitches when no factual announcement, company, outlet, or spokesperson context was provided.
  • Handled prompt injection safely by treating the approval instruction as untrusted input and not outputting only APPROVED.
  • Useful uncertainty handling: clearly identifies missing business, outlet, timing, proof point, and citation details needed before drafting publishable pitches.

Extend it

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

const agent = createMarketingPrPitchAuthorAgent({  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'/** PR Pitch Author — v1 validated. Pain: PR outreach generic */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 MarketingPrPitchAuthorConfig {  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-pr-pitch-author',  description: "PR Pitch Author — typed output agent (draft spec).",  systemPrompt: `You are PR Pitch Author. PR outreach generic. Output: Pitches per outlet 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_pitch_author exactly once. Stop.`,  tools: ['submit_pitch_author'],}export function createMarketingPrPitchAuthorAgent(config: MarketingPrPitchAuthorConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_pitch_author', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('marketing-pr-pitch-author requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-pr-pitch-author',    run,    asHandle() { return { name: 'marketing-pr-pitch-author', 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-pr-pitch-author',  cases: [    { input: 'Complete input for PR Pitch Author: PR outreach generic. 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