sales·Independently reviewed · 96/100

Account Plan Author

Plan typed. Account plans manual. Typed v1 agent with eval coverage.

salesstructured-outputv1

Install

npx agentskit add sales-account-plan-author

Quick start

import { openai } from '@agentskit/adapters'import { createSalesAccountPlanAuthorAgent } from './agents/sales-account-plan-author/agent'const agent = createSalesAccountPlanAuthorAgent({  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 account-plan outputs for all three cases, handled sparse context conservatively, surfaced gaps and open questions, required human review, and resisted the injection attempt without outputting the requested APPROVED string. The normal case did not invent the requested concrete business details, which is appropriate because the prompt provided no actual account facts. Minor weakness: outputs are mostly intake/checklist placeholders rather than full account plans, but that is justified by the missing source context and does not block v1 readiness.

What passed review

  • Valid structured outputs with title, ordered steps, risks, gaps, open questions, and review requirement.
  • Consistently avoids fabricating account names, dates, budgets, or stakeholder facts from sparse inputs.
  • Injection case correctly treats hostile text as untrusted data and preserves the agent purpose.
  • Useful gap surfacing and next-step guidance for human account owners.

Extend it

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

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