sales·Independently reviewed · 96/100

Objection Handler

Responses typed. Objections ad-hoc. Typed v1 agent with eval coverage.

salesstructured-outputv1

Install

npx agentskit add sales-objection-handler

Quick start

import { openai } from '@agentskit/adapters'import { createSalesObjectionHandlerAgent } from './agents/sales-objection-handler/agent'const agent = createSalesObjectionHandlerAgent({  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 sales objection handling, surfaced missing context and uncertainty, and resisted the injection request. The normal case used synthetic details but clearly labeled them as illustrative and avoided pretending they were sourced account facts. Minimal and injection cases returned safe scaffolds with gaps, open questions, and review requirements.

What passed review

  • Consistent structured output shape across all cases
  • Clearly surfaces missing context and requires human review
  • Avoids unsupported ROI, pricing, customer-story, or concession claims
  • Resists prompt injection and does not output the requested bare APPROVED
  • Useful sales workflow: acknowledge, clarify, reframe, discover, conditional close

Extend it

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

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