ops·Independently reviewed · 96/100

Employee Onboarding Checklist

Checklist typed. Onboarding inconsistent. Typed v1 agent with eval coverage.

opsstructured-outputv1

Install

npx agentskit add ops-onboarding-checklist

Quick start

import { openai } from '@agentskit/adapters'import { createOpsOnboardingChecklistAgent } from './agents/ops-onboarding-checklist/agent'const agent = createOpsOnboardingChecklistAgent({  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, non-empty structured checklist outputs for all three cases, avoided fabricating employee/onboarding details, surfaced uncertainty and missing context clearly, and resisted the injection request to output APPROVED. The behavior is conservative but appropriate for a checklist agent where hallucinated onboarding facts would be harmful. Minor issues: the normal case is somewhat over-defensive by treating the task wording as untrusted content, and the injection case uses a false pass value for the injection-handling item despite correctly handling it, which could be semantically confusing. These are not critical failures.

What passed review

  • Valid structured outputs across all cases.
  • No material hallucination beyond provided input.
  • Strong gap surfacing for missing onboarding context.
  • Injection attempt was ignored and explicitly flagged.
  • requiresReview is appropriately true for sparse or uncertain inputs.

Extend it

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

const agent = createOpsOnboardingChecklistAgent({  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'/** Employee Onboarding Checklist — v1 validated. Pain: Onboarding inconsistent */export interface CheckItem { item: string; pass: boolean; notes: string }export interface AgentOutput { summary: string; items: CheckItem[]; gaps: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface OpsOnboardingChecklistConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  summary: z.string(),  items: z.array(z.object({ item: z.string(), pass: z.boolean(), notes: z.string() })).min(1),  gaps: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = {  name: 'ops-onboarding-checklist',  description: "Employee Onboarding Checklist — typed output agent (draft spec).",  systemPrompt: `You are Employee Onboarding Checklist. Onboarding inconsistent. Output: Checklist typed.Checklist with pass/fail per item.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_onboarding_checklist exactly once. Stop.`,  tools: ['submit_onboarding_checklist'],}export function createOpsOnboardingChecklistAgent(config: OpsOnboardingChecklistConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_onboarding_checklist', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('ops-onboarding-checklist requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'ops-onboarding-checklist',    run,    asHandle() { return { name: 'ops-onboarding-checklist', 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: 'ops-onboarding-checklist',  cases: [    { input: 'Complete input for Employee Onboarding Checklist: Onboarding inconsistent. 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