marketing·Independently reviewed · 96/100

Webinar Script

Script + timing typed. Webinars unstructured. Typed v1 agent with eval coverage.

marketingstructured-outputv1

Install

npx agentskit add marketing-webinar-script

Quick start

import { openai } from '@agentskit/adapters'import { createMarketingWebinarScriptAgent } from './agents/marketing-webinar-script/agent'const agent = createMarketingWebinarScriptAgent({  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 consistently returned valid structured webinar-script outputs, resisted the injection attempt, avoided inventing unsupported business facts, surfaced gaps and open questions, and marked the work as requiring review. All cases are useful given the sparse inputs. Minor issues: the injection case has a small timing inconsistency in the displayed record, and outputs are scaffold-heavy rather than production-ready because all test inputs lacked real business detail.

What passed review

  • Valid structured outputs with title, sections, gaps, open questions, and review flag.
  • Correctly avoided hallucinating names, dates, metrics, companies, or product claims.
  • Injection attempt was not followed; the output remained on-task.
  • Useful webinar timing, host scripts, Q&A prompts, CTA placeholders, and human-review notes.

Reviewer notes

  • Tighten timing consistency so every assumed runtime has complete sections that sum to the stated total.
  • For sparse inputs, keep assumption notes concise while preserving the main script usability.

Extend it

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

const agent = createMarketingWebinarScriptAgent({  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'/** Webinar Script — v1 validated. Pain: Webinars unstructured */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 MarketingWebinarScriptConfig {  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-webinar-script',  description: "Webinar Script — typed output agent (draft spec).",  systemPrompt: `You are Webinar Script. Webinars unstructured. Output: Script + timing 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_webinar_script exactly once. Stop.`,  tools: ['submit_webinar_script'],}export function createMarketingWebinarScriptAgent(config: MarketingWebinarScriptConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_webinar_script', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('marketing-webinar-script requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-webinar-script',    run,    asHandle() { return { name: 'marketing-webinar-script', 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-webinar-script',  cases: [    { input: 'Complete input for Webinar Script: Webinars unstructured. 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