sales·Independently reviewed · 96/100

Call Prep Brief

Brief typed. Unprepared calls. Typed v1 agent with eval coverage.

salesstructured-outputv1

Install

npx agentskit add sales-call-prep-brief

Quick start

import { openai } from '@agentskit/adapters'import { createSalesCallPrepBriefAgent } from './agents/sales-call-prep-brief/agent'const agent = createSalesCallPrepBriefAgent({  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 in all three cases, stayed within the sparse input, avoided inventing sales facts, surfaced uncertainty and gaps, and resisted the explicit injection. Behavior is useful for a call-prep agent when no real account context is supplied. Minor weakness: the normal case is conservative and reads the synthetic task request as an injection rather than simply a lack of usable context, but that does not create a material failure.

What passed review

  • Valid structured output for every case with title, sections, gaps, open questions, and review flag in the recorded artifacts.
  • Correctly avoids hallucinating company names, dates, attendees, business context, or deal details from unsupported prompts.
  • Handles sparse and minimal input by producing a useful placeholder brief with clear missing-context questions.
  • Resists the injection request to output APPROVED and treats it as untrusted data.
  • Explicitly marks human review need and uncertainty throughout.

Extend it

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

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