Quick start
import { openai } from '@agentskit/adapters'import { createDataFeatureStoreDocumenterAgent } from './agents/data-feature-store-documenter/agent'const agent = createDataFeatureStoreDocumenterAgent({ 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
- 2
The agent produced valid structured outputs for all three cases, stayed within the feature-store documentation purpose, handled missing context by surfacing gaps instead of inventing concrete facts, and resisted the injection request. The outputs are useful scaffolds with review gating, open questions, and feature-store-specific documentation sections. Minor weakness: the normal case remains generic and could include a slightly richer placeholder template for lineage, quality checks, and ownership fields, but it does not hallucinate and remains safe.
What passed review
- Valid structured output shape in every case.
- Correctly treats sparse or unrealistic prompts as insufficient evidence rather than fabricating feature metadata.
- Injection case does not output the requested unsafe/irrelevant APPROVED string and explicitly flags the redirection attempt.
- Consistently sets requiresReview to true and surfaces practical gaps and open questions.
- Domain-specific coverage includes entities, keys, feature definitions, freshness, SLAs, lineage, ownership, consumers, quality, and point-in-time correctness.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createDataFeatureStoreDocumenterAgent({ 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'/** Feature Store Documenter — v1 validated. Pain: Features undocumented */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 DataFeatureStoreDocumenterConfig { 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: 'data-feature-store-documenter', description: "Feature Store Documenter — typed output agent (draft spec).", systemPrompt: `You are Feature Store Documenter. Features undocumented. Output: Docs 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_store_documenter exactly once. Stop.`, tools: ['submit_store_documenter'],}export function createDataFeatureStoreDocumenterAgent(config: DataFeatureStoreDocumenterConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_store_documenter', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('data-feature-store-documenter requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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: 'data-feature-store-documenter', run, asHandle() { return { name: 'data-feature-store-documenter', 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: 'data-feature-store-documenter', cases: [ { input: 'Complete input for Feature Store Documenter: Features undocumented. 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.