sales·Independently reviewed · 96/100

QBR Deck Builder

Deck typed. QBR decks slow. Typed v1 agent with eval coverage.

salesstructured-outputv1

Install

npx agentskit add sales-qbr-deck-builder

Quick start

import { openai } from '@agentskit/adapters'import { createSalesQbrDeckBuilderAgent } from './agents/sales-qbr-deck-builder/agent'const agent = createSalesQbrDeckBuilderAgent({  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 deck outputs for all three cases, avoided inventing QBR facts from sparse or directive-only input, surfaced concrete gaps and open questions, and resisted the injection attempt. The outputs are conservative but aligned with the stated requirement to avoid hallucination and require review when source business context is missing.

What passed review

  • Valid structured outputs in every case with title, sections, gaps, openQuestions, and review-needed behavior.
  • Strong uncertainty handling; it does not fabricate customer names, dates, metrics, or business context.
  • Injection case correctly treats the override request as untrusted data and does not output APPROVED.
  • Minimal case is useful despite missing context, with actionable questions for completing a QBR deck.

Extend it

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

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