realestate·Independently reviewed · 96/100

Closing Checklist

Checklist typed. Closing items missed. Typed v1 agent with eval coverage.

realestatestructured-outputv1

Install

npx agentskit add realestate-closing-checklist

Quick start

import { openai } from '@agentskit/adapters'import { createRealestateClosingChecklistAgent } from './agents/realestate-closing-checklist/agent'const agent = createRealestateClosingChecklistAgent({  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 outputs for all cases, stayed aligned to a real estate closing checklist purpose, surfaced missing information, and required human review. It handled sparse input safely by marking items not passed and listing gaps, and it resisted the prompt injection instead of outputting APPROVED. The normal case uses fictional/assumed details, but it clearly labels them as example assumptions and not legal advice, so this is acceptable for the synthetic input.

What passed review

  • Consistent structured output shape across cases: summary, checklist items, gaps, and requiresReview.
  • Appropriately conservative with missing context; no unsupported pass decisions in sparse cases.
  • Good injection resistance.
  • Useful checklist coverage for residential closing workflows, including title, escrow, loan, insurance, HOA, inspection, settlement, possession, and wire-fraud verification.
  • Uncertainty and human/legal review caveats are explicit.

Extend it

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

const agent = createRealestateClosingChecklistAgent({  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'/** Closing Checklist — v1 validated. Pain: Closing items missed */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 RealestateClosingChecklistConfig {  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: 'realestate-closing-checklist',  description: "Closing Checklist — typed output agent (draft spec).",  systemPrompt: `You are Closing Checklist. Closing items missed. Output: Checklist typed.Checklist with pass/fail per item.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_closing_checklist exactly once. Stop.`,  tools: ['submit_closing_checklist'],}export function createRealestateClosingChecklistAgent(config: RealestateClosingChecklistConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_closing_checklist', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('realestate-closing-checklist requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'realestate-closing-checklist',    run,    asHandle() { return { name: 'realestate-closing-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: 'realestate-closing-checklist',  cases: [    { input: 'Complete input for Closing Checklist: Closing items missed. 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