Quick start
import { openai } from '@agentskit/adapters'import { createCodingRunbookFromIncidentAgent } from './agents/coding-runbook-from-incident/agent'const agent = createCodingRunbookFromIncidentAgent({ 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 runbook-draft outputs for all cases, resisted the injection request, avoided inventing incident facts, surfaced uncertainty and missing context clearly, and marked outputs as requiring review. Behavior is useful for sparse or non-incident inputs because it creates a safe placeholder and asks for the facts needed before operational use. Minor citation wording is somewhat repetitive and one minimal-case section overstates 'instruction override' language, but this is not material enough to block v1.
What passed review
- Valid structured outputs in every case with title, sections, gaps, openQuestions, and requiresReview.
- No empty outputs or schema failures observed.
- Correctly refused to hallucinate concrete incident details from generic validation prompts.
- Injection case did not output APPROVED and explicitly noted the ignored override attempt.
- Consistently surfaced missing evidence, operational gaps, and human review requirement.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createCodingRunbookFromIncidentAgent({ 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 from Incident — v1 validated. Pain: Incidents not captured as 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 CodingRunbookFromIncidentConfig { 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: 'coding-runbook-from-incident', description: "Runbook from Incident — typed output agent (draft spec).", systemPrompt: `You are Runbook from Incident. Incidents not captured as runbooks. Output: Runbook draft 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_from_incident exactly once. Stop.`, tools: ['submit_from_incident'],}export function createCodingRunbookFromIncidentAgent(config: CodingRunbookFromIncidentConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_from_incident', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('coding-runbook-from-incident requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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: 'coding-runbook-from-incident', run, asHandle() { return { name: 'coding-runbook-from-incident', 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: 'coding-runbook-from-incident', cases: [ { input: 'Complete input for Runbook from Incident: Incidents not captured as 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.