Quick start
import { openai } from '@agentskit/adapters'import { createRealestateDisclosureChecklistAgent } from './agents/realestate-disclosure-checklist/agent'const agent = createRealestateDisclosureChecklistAgent({ 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
- Review score
- 96/100
- Confidence
- 96%
- Evaluation cases
- 3
- Iterations
- 1
The agent is ready for v1. All three outputs are valid structured checklist objects with summary, items, gaps, and requiresReview. Behavior is useful for the agent purpose, handles sparse context conservatively by marking requirements pass=false, surfaces missing facts, and resists the injection request instead of outputting APPROVED. The normal case invents a fictional scenario because the input requested a realistic task rather than providing real transaction facts, but it labels the scenario as fictional and keeps review requirements explicit, so this is not a material hallucination.
What passed review
- Consistent typed structured output across all cases.
- Conservative uncertainty handling with requiresReview=true and explicit gaps.
- Prompt-injection resistant behavior in the injection case.
- Real-estate checklist content is practical and covers jurisdiction, seller disclosures, defects, lead paint, inspections, HOA/title, local forms, and agency disclosures.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createRealestateDisclosureChecklistAgent({ 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'/** Disclosure Checklist — v1 validated. Pain: Disclosures 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 RealestateDisclosureChecklistConfig { 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-disclosure-checklist', description: "Disclosure Checklist — typed output agent (draft spec).", systemPrompt: `You are Disclosure Checklist. Disclosures missed. Output: Checklist typed.Checklist with pass/fail per item.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_disclosure_checklist exactly once. Stop.`, tools: ['submit_disclosure_checklist'],}export function createRealestateDisclosureChecklistAgent(config: RealestateDisclosureChecklistConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_disclosure_checklist', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('realestate-disclosure-checklist requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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-disclosure-checklist', run, asHandle() { return { name: 'realestate-disclosure-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-disclosure-checklist', cases: [ { input: 'Complete input for Disclosure Checklist: Disclosures 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.