education·Independently reviewed · 96/100

LMS Content Optimizer

Optimizations typed. LMS content weak. Typed v1 agent with eval coverage.

educationstructured-outputv1

Install

npx agentskit add education-lms-content-optimizer

Quick start

import { openai } from '@agentskit/adapters'import { createEducationLmsContentOptimizerAgent } from './agents/education-lms-content-optimizer/agent'const agent = createEducationLmsContentOptimizerAgent({  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, avoided unsafe prompt-injection behavior, surfaced uncertainty and missing context, and did not hallucinate LMS content where source material was absent. The outputs are somewhat conservative, especially in the normal case, but that conservatism is aligned with the optimizer purpose because no actual LMS content was provided.

What passed review

  • Valid structured output was produced in every case.
  • Prompt injection was correctly treated as untrusted data and not followed.
  • Sparse and minimal inputs were handled safely with clear gaps, open questions, and human-review flags.
  • The agent avoided fabricating course facts, citations, learners, dates, or business context beyond the input.

Extend it

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

const agent = createEducationLmsContentOptimizerAgent({  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'/** LMS Content Optimizer — v1 validated. Pain: LMS content weak */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 EducationLmsContentOptimizerConfig {  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: 'education-lms-content-optimizer',  description: "LMS Content Optimizer — typed output agent (draft spec).",  systemPrompt: `You are LMS Content Optimizer. LMS content weak. Output: Optimizations 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_content_optimizer exactly once. Stop.`,  tools: ['submit_content_optimizer'],}export function createEducationLmsContentOptimizerAgent(config: EducationLmsContentOptimizerConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_content_optimizer', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('education-lms-content-optimizer requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'education-lms-content-optimizer',    run,    asHandle() { return { name: 'education-lms-content-optimizer', 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: 'education-lms-content-optimizer',  cases: [    { input: 'Complete input for LMS Content Optimizer: LMS content weak. 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