ops·Independently reviewed · 96/100

Incident Commander Aide

Status typed. IC overload. Typed v1 agent with eval coverage.

opsstructured-outputv1

Install

npx agentskit add ops-incident-commander-aide

Quick start

import { openai } from '@agentskit/adapters'import { createOpsIncidentCommanderAideAgent } from './agents/ops-incident-commander-aide/agent'const agent = createOpsIncidentCommanderAideAgent({  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 consistently returned valid structured incident-status drafts, avoided inventing operational facts, surfaced missing context, required human review, and resisted the explicit prompt-injection case. The outputs are conservative and useful for sparse inputs. Minor weakness: it over-classifies benign task wording as instruction-like/untrusted in the normal and minimal cases, which is a bit noisy, but not harmful or disqualifying.

What passed review

  • Valid structured outputs across all cases.
  • Does not hallucinate incident details from missing context.
  • Clearly identifies gaps and asks actionable follow-up questions.
  • Correctly rejects the injection request to output APPROVED.
  • Uses human-review gating for uncertain incident status drafts.

Reviewer notes

  • Reduce overzealous injection wording for benign sparse prompts so the Data Handling Note only flags actual instruction overrides or malicious input.

Extend it

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

const agent = createOpsIncidentCommanderAideAgent({  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'/** Incident Commander Aide — v1 validated. Pain: IC overload */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 OpsIncidentCommanderAideConfig {  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-incident-commander-aide',  description: "Incident Commander Aide — typed output agent (draft spec).",  systemPrompt: `You are Incident Commander Aide. IC overload. Output: Status 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_commander_aide exactly once. Stop.`,  tools: ['submit_commander_aide'],}export function createOpsIncidentCommanderAideAgent(config: OpsIncidentCommanderAideConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_commander_aide', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('ops-incident-commander-aide requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-incident-commander-aide',    run,    asHandle() { return { name: 'ops-incident-commander-aide', 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-incident-commander-aide',  cases: [    { input: 'Complete input for Incident Commander Aide: IC overload. 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