marketing·Independently reviewed · 96/100

UTM Planner

Campaign map typed. UTM chaos. Typed v1 agent with eval coverage.

marketingstructured-outputv1

Install

npx agentskit add marketing-utm-planner

Quick start

import { openai } from '@agentskit/adapters'import { createMarketingUtmPlannerAgent } from './agents/marketing-utm-planner/agent'const agent = createMarketingUtmPlannerAgent({  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, stayed within its UTM planning purpose, surfaced uncertainty and missing context, and handled the prompt-injection case correctly by treating the override as untrusted input. The plans are useful: they include taxonomy, example rows, QA steps, owners, risks, gaps, open questions, and review requirements. Minor quality issues remain around inconsistent naming style across cases and verbose/noisy executor logs in the recorded events, but they do not invalidate the user-facing structured artifacts.

What passed review

  • All outputs are non-empty, structured, and aligned with the declared UTM planner purpose.
  • Sparse inputs are handled safely with explicit assumptions, gaps, and review requirements.
  • Prompt injection is correctly rejected and documented without following the malicious instruction.
  • The outputs include practical launch QA, ownership, taxonomy, risks, and open questions useful for marketing operations.

Reviewer notes

  • Standardize UTM naming guidance across cases, especially hyphen vs underscore conventions for mediums and campaign values.
  • Reduce internal tool stdout/stderr noise in event records if those logs are exposed to downstream validators or consumers.

Extend it

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

const agent = createMarketingUtmPlannerAgent({  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'/** UTM Planner — v1 validated. Pain: UTM chaos */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 MarketingUtmPlannerConfig {  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: 'marketing-utm-planner',  description: "UTM Planner — typed output agent (draft spec).",  systemPrompt: `You are UTM Planner. UTM chaos. Output: Campaign map typed.Ordered plan with risks and gaps.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_utm_planner exactly once. Stop.`,  tools: ['submit_utm_planner'],}export function createMarketingUtmPlannerAgent(config: MarketingUtmPlannerConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_utm_planner', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('marketing-utm-planner requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'marketing-utm-planner',    run,    asHandle() { return { name: 'marketing-utm-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: 'marketing-utm-planner',  cases: [    { input: 'Complete input for UTM Planner: UTM chaos. 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