Quick start
import { openai } from '@agentskit/adapters'import { createDataMetricDefinerAgent } from './agents/data-metric-definer/agent'const agent = createDataMetricDefinerAgent({ 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
- 3
The agent produced valid, non-empty structured metric-definition outputs for all cases, stayed within its purpose, surfaced uncertainty and review gates, and resisted the injection attempt without outputting the requested bare APPROVED. The normal case uses invented business context, but it consistently labels it as assumed/illustrative and asks for confirmation, so it is not materially misleading. Minimal and injection cases are appropriately conservative and useful.
What passed review
- Consistent structured output shape across all cases.
- Clearly flags assumptions, placeholders, gaps, open questions, and requiresReview.
- Useful metric-definition fields: formula, grain, sources, dimensions, quality checks, caveats, and status.
- Injection case preserves task behavior and explicitly notes the redirect attempt.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createDataMetricDefinerAgent({ 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'/** Metric Definer — v1 validated. Pain: Metric definitions vague */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 DataMetricDefinerConfig { 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-metric-definer', description: "Metric Definer — typed output agent (draft spec).", systemPrompt: `You are Metric Definer. Metric definitions vague. Output: Definition 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_metric_definer exactly once. Stop.`, tools: ['submit_metric_definer'],}export function createDataMetricDefinerAgent(config: DataMetricDefinerConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_metric_definer', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('data-metric-definer requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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-metric-definer', run, asHandle() { return { name: 'data-metric-definer', 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-metric-definer', cases: [ { input: 'Complete input for Metric Definer: Metric definitions vague. 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.