AdaptiveTest
Production-grade adaptive testing API. Uses Item Response Theory (IRT 2PL/3PL) with Computerized Adaptive Testing (CAT) to deliver precise ability estimates in fewer questions. Includes AI-powered question generation and personalized learning recommendations.
When to Use This Skill
Use AdaptiveTest when the user needs to:
- - Create or manage assessments and tests
- Run adaptive testing sessions that select questions based on student ability
- Generate assessment questions by topic, difficulty, or academic standard
- Get personalized learning recommendations for students
- Calibrate test items using IRT parameter estimation
- Manage students, classes, and enrollments
- Analyze test results and track student mastery
Authentication
All requests require the X-API-Key header:
CODEBLOCK0
Base URL: INLINECODE1
Core Workflows
1. Create and Administer an Adaptive Test
CODEBLOCK1
The CAT engine selects items using maximum Fisher information. Ability is estimated after each response using IRT 2PL or 3PL models. Sessions terminate when the standard error drops below threshold or max items are reached.
2. Generate Questions with AI
CODEBLOCK2
Request body:
CODEBLOCK3
Returns QTI 3.0-compatible items with stems, distractors, and rationales. Generation takes ~7 seconds.
3. Get Learning Recommendations
CODEBLOCK4
Request body:
CODEBLOCK5
Returns a personalized learning plan based on the student's ability profile and assessment history. Generation takes ~25 seconds.
4. Calibrate Test Items
CODEBLOCK6
Requires sufficient response data (minimum 30 responses per item recommended). Returns IRT parameters: difficulty (b), discrimination (a), and guessing (c) for 3PL.
5. Manage Students and Classes
CODEBLOCK7
OneRoster 1.2 compatible for SIS integration.
6. View Results and Analytics
CODEBLOCK8
Rate Limits
Rate limits depend on your API key tier. Check X-RateLimit-Remaining header on each response.
Error Handling
All errors return JSON with a detail field:
CODEBLOCK9
Common status codes: 400 (validation), 401 (auth), 403 (limit exceeded), 404 (not found), 429 (rate limited).
Reference Documentation
For detailed endpoint specifications, request/response shapes, and IRT/CAT concepts, see the references/ directory:
- -
references/api-endpoints.md -- Full endpoint reference - INLINECODE6 -- IRT and CAT concepts
- INLINECODE7 -- Item calibration guide
AdaptiveTest
生产级自适应测试API。采用项目反应理论(IRT 2PL/3PL)结合计算机自适应测试(CAT),以更少的题目提供精确的能力评估。包含AI驱动的题目生成和个性化学习推荐。
何时使用此技能
当用户需要以下功能时,请使用AdaptiveTest:
- - 创建或管理评估和测试
- 运行自适应测试会话,根据学生能力选择题目
- 按主题、难度或学术标准生成评估题目
- 为学生获取个性化学习推荐
- 使用IRT参数估计校准测试项目
- 管理学生、班级和注册信息
- 分析测试结果并追踪学生掌握情况
身份验证
所有请求都需要包含X-API-Key头信息:
X-API-Key: ${ADAPTIVETESTAPIKEY}
基础URL:https://adaptivetest-platform-production.up.railway.app/api
核心工作流程
1. 创建并管理自适应测试
POST /tests -- 创建测试(设置cat_enabled: true)
POST /tests/{id}/items -- 向测试添加题目
POST /tests/{id}/sessions -- 为学生启动自适应会话
GET /sessions/{id}/next-item -- 获取下一个CAT选择的题目
POST /sessions/{id}/responses -- 提交学生作答
GET /sessions/{id}/results -- 获取能力评估和结果
CAT引擎使用最大费舍尔信息量选择题目。每次作答后使用IRT 2PL或3PL模型评估能力。当标准误差低于阈值或达到最大题目数时,会话终止。
2. 使用AI生成题目
POST /gen-q -- 按主题、难度和标准生成题目
请求体:
json
{
topic: 二次方程,
difficulty: 中等,
count: 5,
standard: CCSS.MATH.CONTENT.HSA.REI.B.4,
format: multiple_choice
}
返回兼容QTI 3.0的题目,包含题干、干扰项和解析。生成时间约7秒。
3. 获取学习推荐
POST /recs -- 为学生获取个性化学习推荐
请求体:
json
{
student_id: student-uuid,
subject: 数学,
include_resources: true
}
基于学生的能力档案和评估历史返回个性化学习计划。生成时间约25秒。
4. 校准测试题目
POST /tests/{id}/calibrate -- 对收集的作答数据运行IRT校准
需要足够的作答数据(建议每个题目至少30个作答)。返回IRT参数:难度(b)、区分度(a)和猜测系数(c),适用于3PL模型。
5. 管理学生和班级
POST /students -- 创建学生
GET /students -- 列出学生
POST /classes -- 创建班级
POST /classes/{id}/enroll -- 将学生注册到班级
兼容OneRoster 1.2,支持SIS集成。
6. 查看结果和分析
GET /sessions/{id}/results -- 详细会话结果及能力评估
GET /students/{id}/history -- 学生的评估历史
GET /tests/{id}/analytics -- 测试的题目级分析
速率限制
速率限制取决于您的API密钥等级。请检查每个响应中的X-RateLimit-Remaining头信息。
错误处理
所有错误均返回包含detail字段的JSON:
json
{detail: 人类可读的错误信息}
常见状态码:400(验证错误)、401(认证错误)、403(超出限制)、404(未找到)、429(速率受限)。
参考文档
有关详细的端点规范、请求/响应格式以及IRT/CAT概念,请参阅references/目录:
- - references/api-endpoints.md -- 完整端点参考
- references/adaptive-testing.md -- IRT和CAT概念
- references/calibration.md -- 题目校准指南