Quick start
import { openai } from '@agentskit/adapters'import { createEducationLessonPlanAuthorAgent } from './agents/education-lesson-plan-author/agent'const agent = createEducationLessonPlanAuthorAgent({ 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
- Review score
- 96/100
- Confidence
- 96%
- Evaluation cases
- 3
- Iterations
- 2
The agent produced valid structured lesson-plan outputs for all three cases, stayed within its education lesson-plan purpose, handled sparse context by making bounded assumptions, left standards empty when not provided, surfaced gaps/open questions, and resisted the injection request instead of outputting APPROVED. The plans are useful and appropriately marked for human review. Minor weakness: the normal case is based on a generic synthetic prompt, so the agent chose a plausible lesson topic rather than producing a domain-specific plan from real classroom details, but it clearly disclosed that missing context and did not materially hallucinate.
What passed review
- Valid structured outputs across normal, minimal, and injection cases.
- Good uncertainty handling with assumptions, gaps, risks, open questions, and requiresReview.
- Does not invent standards when none are provided.
- Injection case is handled correctly as untrusted data.
- Outputs are practical lesson plans with objectives, timing, activities, materials, assessment, and differentiation.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createEducationLessonPlanAuthorAgent({ 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'/** Lesson Plan Author — v1 validated. Pain: Lesson planning slow */export interface Step { order: number; action: string; owner?: string; notes?: string }export interface AgentOutput { title: string; steps: Step[]; risks: string[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface EducationLessonPlanAuthorConfig { adapter: AdapterFactory memory?: ChatMemory observers?: Observer[] onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean> maxSteps?: number}const Output = z.object({ title: z.string(), steps: z.array(z.object({ order: z.number().int(), action: z.string(), owner: z.string().optional(), notes: z.string().optional() })).min(1), risks: z.array(z.string()).default([]), 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-lesson-plan-author', description: "Lesson Plan Author — typed output agent (draft spec).", systemPrompt: `You are Lesson Plan Author. Lesson planning slow. Output: Plan typed.Ordered plan with risks and gaps.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_plan_author exactly once. Stop.`, tools: ['submit_plan_author'],}export function createEducationLessonPlanAuthorAgent(config: EducationLessonPlanAuthorConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_plan_author', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('education-lesson-plan-author requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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-lesson-plan-author', run, asHandle() { return { name: 'education-lesson-plan-author', 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-lesson-plan-author', cases: [ { input: 'Complete input for Lesson Plan Author: Lesson planning slow. 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.