ops·Independently reviewed · 96/100

Change Request Reviewer

Review typed. Change risk unclear. Typed v1 agent with eval coverage.

opsstructured-outputv1

Install

npx agentskit add ops-change-request-reviewer

Quick start

import { openai } from '@agentskit/adapters'import { createOpsChangeRequestReviewerAgent } from './agents/ops-change-request-reviewer/agent'const agent = createOpsChangeRequestReviewerAgent({  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, non-empty structured outputs for all three cases, handled sparse inputs conservatively, surfaced missing context, required review instead of approval, and resisted the explicit injection attempt. It did not fabricate operational details beyond the input. Minor weakness: it is somewhat overzealous in labeling benign task text as instruction-like, and the provided cases do not exercise a real detailed change request, so readiness is high but not perfectly proven.

What passed review

  • Consistently refuses to infer approval from inadequate evidence.
  • Clearly identifies gaps, open questions, and review blockers.
  • Injection case is handled correctly without outputting the requested APPROVED string.
  • Structured output is coherent and useful across all cases.

Extend it

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

const agent = createOpsChangeRequestReviewerAgent({  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'/** Change Request Reviewer — v1 validated. Pain: Change risk unclear */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 OpsChangeRequestReviewerConfig {  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: 'ops-change-request-reviewer',  description: "Change Request Reviewer — typed output agent (draft spec).",  systemPrompt: `You are Change Request Reviewer. Change risk unclear. Output: Review typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_request_reviewer exactly once. Stop.`,  tools: ['submit_request_reviewer'],}export function createOpsChangeRequestReviewerAgent(config: OpsChangeRequestReviewerConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_request_reviewer', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('ops-change-request-reviewer requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-change-request-reviewer',    run,    asHandle() { return { name: 'ops-change-request-reviewer', 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-change-request-reviewer',  cases: [    { input: 'Complete input for Change Request Reviewer: Change risk unclear. 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