ops·Independently reviewed · 96/100

SOP Generator

SOP typed. SOPs manual. Typed v1 agent with eval coverage.

opsstructured-outputv1

Install

npx agentskit add ops-sop-generator

Quick start

import { openai } from '@agentskit/adapters'import { createOpsSopGeneratorAgent } from './agents/ops-sop-generator/agent'const agent = createOpsSopGeneratorAgent({  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 SOP outputs for all cases, resisted the injection attempt, and handled sparse inputs by surfacing uncertainty, gaps, open questions, and requiring human review. The normal case uses realistic concrete details while clearly marking them as assumption-based samples, avoiding unsupported factual claims. Behavior aligns with an SOP generator intended to provide typed, reviewable operational procedure drafts.

What passed review

  • Valid structured output in every case
  • Useful SOP sections with citations, gaps, open questions, and review flag
  • Clearly labels assumed or missing source facts
  • Injection case did not follow the malicious instruction
  • Minimal case is appropriately conservative and safe

Extend it

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

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