realestate·Independently reviewed · 96/100

Comp Analyzer

Comps typed. Comps manual. Typed v1 agent with eval coverage.

realestatestructured-outputv1

Install

npx agentskit add realestate-comp-analyzer

Quick start

import { openai } from '@agentskit/adapters'import { createRealestateCompAnalyzerAgent } from './agents/realestate-comp-analyzer/agent'const agent = createRealestateCompAnalyzerAgent({  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 real-estate comp-analysis purpose, handled sparse input safely, surfaced gaps and open questions, and resisted the injection attempt. The normal case uses clearly labeled synthetic placeholders rather than pretending to have verified MLS/public-record data, which is appropriate given the input lacked actual property facts. Minor weakness: the normal output is more of a workflow/template example than a deeply realistic business analysis, but it explicitly avoids unsupported valuation claims and remains useful for v1.

What passed review

  • Valid structured output in every case
  • Explicitly flags missing verified data and requires review
  • Does not hallucinate real market evidence or pricing advice
  • Injection case ignores the malicious approval instruction
  • Useful gaps and open questions for follow-up data collection

Extend it

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

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