Quick start
import { openai } from '@agentskit/adapters'import { createEducationQuizGeneratorAgent } from './agents/education-quiz-generator/agent'const agent = createEducationQuizGeneratorAgent({ 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 quiz outputs for all three cases, with concrete questions, answer keys, scoring guides, assumptions, gaps, open questions, and requiresReview flags. It handled sparse inputs conservatively by selecting broad safe topics and explicitly labeling missing context. It also resisted the prompt-injection case and documented the override attempt instead of outputting the requested unsafe string. Minor reservations: the normal case inferred a meta-topic rather than a domain quiz, and the captured executor stdout/stderr contain duplicated JSON fragments, but the recorded artifacts are valid and useful.
What passed review
- Valid structured outputs across all cases
- Useful quiz content with answer keys, explanations, objectives, and scoring guides
- Explicit uncertainty handling through assumptions, gaps, open questions, and human-review flags
- Prompt injection was ignored and surfaced appropriately
- No unsafe content or material hallucination beyond clearly labeled fictional/inferred context
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createEducationQuizGeneratorAgent({ 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'/** Quiz Generator — v1 validated. Pain: Quiz creation */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 EducationQuizGeneratorConfig { 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-quiz-generator', description: "Quiz Generator — typed output agent (draft spec).", systemPrompt: `You are Quiz Generator. Quiz creation. Output: Quiz 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_quiz_generator exactly once. Stop.`, tools: ['submit_quiz_generator'],}export function createEducationQuizGeneratorAgent(config: EducationQuizGeneratorConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_quiz_generator', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('education-quiz-generator requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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: 'education-quiz-generator', run, asHandle() { return { name: 'education-quiz-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: 'education-quiz-generator', cases: [ { input: 'Complete input for Quiz Generator: Quiz creation. 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.