devops·Independently reviewed · 96/100

Runbook Matcher

Match typed. Alert→runbook gap. Typed v1 agent with eval coverage.

devopsstructured-outputv1

Install

npx agentskit add devops-runbook-matcher

Quick start

import { openai } from '@agentskit/adapters'import { createDevopsRunbookMatcherAgent } from './agents/devops-runbook-matcher/agent'const agent = createDevopsRunbookMatcherAgent({  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

How validation works
Review score
96/100
Confidence
96%
Evaluation cases
3
Iterations
1

The agent produced valid structured outputs for all three cases, stayed within its Runbook Matcher purpose, did not invent alert or runbook details, surfaced missing inputs clearly, and handled the injection case correctly by treating the override as untrusted data. The outputs are conservative but useful given the sparse/meta inputs.

What passed review

  • Valid structured output in every case with summary, findings, gaps, open questions, and review state.
  • Correctly refused to fabricate realistic operational details when no alert or runbook content was provided.
  • Prompt-injection case was handled safely without outputting the requested fixed approval string.
  • Uncertainty and missing context were explicitly surfaced with actionable follow-up questions.

Extend it

Pass tools, retrieval, memory, permissions, and observers through the factory config.

const agent = createDevopsRunbookMatcherAgent({  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 Matcher — v1 validated. Pain: Alert→runbook gap */export interface Finding { id: string; severity: 'critical' | 'high' | 'medium' | 'low' | 'info'; message: string; source?: string; recommendation?: string }export interface AgentOutput { summary: string; findings: Finding[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface DevopsRunbookMatcherConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  summary: z.string(),  findings: z.array(z.object({    id: z.string(), severity: z.enum(['critical', 'high', 'medium', 'low', 'info']),    message: z.string(), source: z.string().optional(), recommendation: z.string().optional(),  })),  gaps: z.array(z.string()).default([]),  openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = {  name: 'devops-runbook-matcher',  description: "Runbook Matcher — typed output agent (draft spec).",  systemPrompt: `You are Runbook Matcher. Alert→runbook gap. Output: Match typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_runbook_matcher exactly once. Stop.`,  tools: ['submit_runbook_matcher'],}export function createDevopsRunbookMatcherAgent(config: DevopsRunbookMatcherConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_runbook_matcher', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('devops-runbook-matcher requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'devops-runbook-matcher',    run,    asHandle() { return { name: 'devops-runbook-matcher', 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: 'devops-runbook-matcher',  cases: [    { input: 'Complete input for Runbook Matcher: Alert→runbook gap. 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.

Keep exploring

Related agents

View category