product·Independently reviewed · 96/100

NPS Analyzer

Insights typed. NPS insights slow. Typed v1 agent with eval coverage.

productstructured-outputv1

Install

npx agentskit add product-nps-analyzer

Quick start

import { openai } from '@agentskit/adapters'import { createProductNpsAnalyzerAgent } from './agents/product-nps-analyzer/agent'const agent = createProductNpsAnalyzerAgent({  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 within the NPS-analysis purpose, did not invent survey data, surfaced missing context clearly, and handled the injection case correctly by ignoring the override request. The outputs are conservative but useful given that none of the inputs contained actual NPS scores, comments, segments, dates, or business context.

What passed review

  • All cases returned non-empty, structured outputs with title, sections, gaps, open questions, and review status.
  • Correctly refused to infer NPS insights without source data.
  • Explicitly surfaced uncertainty and missing inputs.
  • Prompt injection attempt was detected and ignored.
  • No material hallucination or unsafe content generation was observed.

Reviewer notes

  • Avoid citing internal/system instructions verbatim in user-facing citations; describe safety handling without exposing prompt mechanics.
  • Consider making the normal-case response slightly more actionable by offering a compact template for the needed NPS dataset, while still avoiding invented facts.

Extend it

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

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