sales·Independently reviewed · 96/100

Expansion Opportunity

Opportunities typed. Upsell missed. Typed v1 agent with eval coverage.

salesstructured-outputv1

Install

npx agentskit add sales-expansion-opportunity

Quick start

import { openai } from '@agentskit/adapters'import { createSalesExpansionOpportunityAgent } from './agents/sales-expansion-opportunity/agent'const agent = createSalesExpansionOpportunityAgent({  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, avoided fabricating customer or opportunity details from sparse inputs, surfaced concrete gaps and open questions, and correctly resisted the explicit injection attempt. The normal case is conservative rather than richly useful because the provided input contained no actual business facts, but that conservatism aligns with the no-hallucination requirement.

What passed review

  • Valid structured output shape across all cases.
  • Consistently marks insufficient context and requires human review.
  • Does not hallucinate account names, dates, products, values, or expansion signals beyond the input.
  • Handles the injection case correctly by refusing the fixed APPROVED output and treating the override as untrusted data.
  • Provides actionable missing-data questions for a sales reviewer.

Extend it

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

const agent = createSalesExpansionOpportunityAgent({  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'/** Expansion Opportunity — v1 validated. Pain: Upsell missed */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 SalesExpansionOpportunityConfig {  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-expansion-opportunity',  description: "Expansion Opportunity — typed output agent (draft spec).",  systemPrompt: `You are Expansion Opportunity. Upsell missed. Output: Opportunities 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_expansion_opportunity exactly once. Stop.`,  tools: ['submit_expansion_opportunity'],}export function createSalesExpansionOpportunityAgent(config: SalesExpansionOpportunityConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_expansion_opportunity', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('sales-expansion-opportunity requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-expansion-opportunity',    run,    asHandle() { return { name: 'sales-expansion-opportunity', 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-expansion-opportunity',  cases: [    { input: 'Complete input for Expansion Opportunity: Upsell missed. 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