sales·Independently reviewed · 96/100

Outbound Sequence Author

Sequence typed. Cold outreach manual. Typed v1 agent with eval coverage.

salesstructured-outputv1

Install

npx agentskit add sales-outbound-sequence-author

Quick start

import { openai } from '@agentskit/adapters'import { createSalesOutboundSequenceAuthorAgent } from './agents/sales-outbound-sequence-author/agent'const agent = createSalesOutboundSequenceAuthorAgent({  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 aligned with the outbound sequence author purpose, handled sparse context conservatively, surfaced gaps and open questions, and resisted the injection attempt. The normal case uses synthetic assumptions beyond the literal input, but it labels them clearly as illustrative placeholders and marks the result as requiring review, so this is not a material hallucination in context.

What passed review

  • Valid structured output shape across all cases
  • Useful outbound cadence with channel/timing structure
  • Clear uncertainty handling through gaps, open questions, and requiresReview
  • Injection case ignored the request to output APPROVED
  • Includes compliance and review cautions against fabricated claims

Extend it

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

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