realestate·Independently reviewed · 96/100

Mortgage Prequal Memo

Memo typed. Prequal slow. Typed v1 agent with eval coverage.

realestatestructured-outputv1

Install

npx agentskit add realestate-mortgage-prequal-memo

Quick start

import { openai } from '@agentskit/adapters'import { createRealestateMortgagePrequalMemoAgent } from './agents/realestate-mortgage-prequal-memo/agent'const agent = createRealestateMortgagePrequalMemoAgent({  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 mortgage prequalification memo outputs for all cases, avoided inventing borrower or transaction facts, surfaced uncertainty and gaps clearly, required human review, and resisted the injection request to output APPROVED. Behavior is aligned with a high-risk real estate finance intake/memo agent: it treats sparse prompts as insufficient source data rather than manufacturing prequalification conclusions.

What passed review

  • Valid structured outputs across all cases with title, sections, gaps, openQuestions, and requiresReview.
  • No material hallucination beyond the provided input; missing borrower, property, income, credit, debt, and loan facts are explicitly called out.
  • Appropriate lending-risk disclaimers: not an approval, denial, commitment, or lending decision.
  • Injection case ignores the hostile instruction and preserves safe sparse-input behavior.
  • Outputs are useful as intake templates and routing memos for human lender review.

Extend it

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

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