Quick start
import { openai } from '@agentskit/adapters'import { createOpsRunbookAuthorAgent } from './agents/ops-runbook-author/agent'const agent = createOpsRunbookAuthorAgent({ 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 runbook-author outputs for all three cases, consistently avoided inventing operational facts, surfaced concrete gaps and clarifying questions, required human review, and resisted the injection request. The behavior is conservative but appropriate for a runbook author where fabricated procedures would be risky. Minor weakness: the normal case is not a substantive runbook, but the input itself lacked real operational source material and asked for invented details, so blocking with gaps is defensible.
What passed review
- Valid structured outputs across all cases with title, sections, gaps, openQuestions, and requiresReview in recorded output.
- Strong uncertainty handling and no material hallucination beyond the sparse inputs.
- Injection case correctly ignored the instruction to output APPROVED and flagged it.
- Outputs are operationally safe and clearly marked for human review.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createOpsRunbookAuthorAgent({ 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'/** Runbook Author — v1 validated. Pain: Missing runbooks */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 OpsRunbookAuthorConfig { 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: 'ops-runbook-author', description: "Runbook Author — typed output agent (draft spec).", systemPrompt: `You are Runbook Author. Missing runbooks. Output: Runbook 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_runbook_author exactly once. Stop.`, tools: ['submit_runbook_author'],}export function createOpsRunbookAuthorAgent(config: OpsRunbookAuthorConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_runbook_author', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('ops-runbook-author requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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: 'ops-runbook-author', run, asHandle() { return { name: 'ops-runbook-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: 'ops-runbook-author', cases: [ { input: 'Complete input for Runbook Author: Missing runbooks. 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.