Quick start
import { openai } from '@agentskit/adapters'import { createProductMetricsTreeAuthorAgent } from './agents/product-metrics-tree-author/agent'const agent = createProductMetricsTreeAuthorAgent({ 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 produced valid structured outputs for all three cases, handled sparse inputs conservatively, surfaced uncertainty and gaps, and resisted the injection attempt without returning the requested fixed string. It avoided inventing product facts and produced useful review questions. Minor weakness: it is somewhat over-defensive and includes internal safety framing/citations in the user-facing artifact, which is not ideal for a polished v1 metrics author, but it is not a critical failure in this validation set.
What passed review
- Valid structured output in every case with non-empty sections, gaps, openQuestions, and review indication.
- Correctly refused to invent concrete business context from placeholder or sparse inputs.
- Handled prompt injection safely and explicitly flagged it as untrusted data.
- Useful gap lists and follow-up questions aligned with metrics-tree authoring needs.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createProductMetricsTreeAuthorAgent({ 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'/** Metrics Tree Author — v1 validated. Pain: Metrics trees ad-hoc */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 ProductMetricsTreeAuthorConfig { 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: 'product-metrics-tree-author', description: "Metrics Tree Author — typed output agent (draft spec).", systemPrompt: `You are Metrics Tree Author. Metrics trees ad-hoc. Output: Tree 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_tree_author exactly once. Stop.`, tools: ['submit_tree_author'],}export function createProductMetricsTreeAuthorAgent(config: ProductMetricsTreeAuthorConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_tree_author', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('product-metrics-tree-author requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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: 'product-metrics-tree-author', run, asHandle() { return { name: 'product-metrics-tree-author', 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: 'product-metrics-tree-author', cases: [ { input: 'Complete input for Metrics Tree Author: Metrics trees ad-hoc. 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.