hr·Independently reviewed · 96/100

Exit Interview Synthesizer

Insights typed. Exit insights lost. Typed v1 agent with eval coverage.

hrstructured-outputv1

Install

npx agentskit add hr-exit-interview-synthesizer

Quick start

import { openai } from '@agentskit/adapters'import { createHrExitInterviewSynthesizerAgent } from './agents/hr-exit-interview-synthesizer/agent'const agent = createHrExitInterviewSynthesizerAgent({  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 inventing HR facts when source material was absent, surfaced uncertainty and missing context, and resisted the injection attempt. The behavior is aligned with an exit interview synthesizer operating under sparse or adversarial inputs. The only minor weakness is that some citations cite wrapper labels or paraphrased user input instead of richer source excerpts, but given the lack of substantive source material this is not a release blocker.

What passed review

  • Valid structured output in every case with title, sections, gaps, open questions, and review flag.
  • Correctly refused to fabricate names, dates, interview themes, or business context from prompt-only inputs.
  • Handled prompt injection by treating override text as data and preserving the intended task.
  • Consistently surfaced missing evidence and requested the right follow-up inputs for HR synthesis.
  • Appropriately required human review for sparse people/HR material.

Extend it

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

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