> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getbindu.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 3.8 Quiz Generator Agent

> A TypeScript-based agent that generates educational quizzes using LangChain and OpenRouter

A TypeScript-based agent that generates educational quizzes using LangChain and OpenRouter.

## Code

Create `quiz-generator-agent.ts` with the code below, or save it directly from your editor.

```typescript theme={null}
/**
 * Quiz Generator Agent (TypeScript + LangChain + OpenRouter + Bindu)
 */

import { bindufy, ChatMessage } from "@bindu/sdk";
import { ChatOpenAI } from "@langchain/openai";
import * as dotenv from "dotenv";

dotenv.config();

/**
 * LLM Setup (OpenRouter)
 * IMPORTANT: OpenRouter works via baseURL override
 */
const llm = new ChatOpenAI({
  model: "openai/gpt-oss-120b", // same as your Python version
  temperature: 0.3,
  configuration: {
    baseURL: "https://openrouter.ai/api/v1",
    apiKey: process.env.OPENROUTER_API_KEY,
  },
});

/**
 * System Prompt (your original instructions)
 */
const SYSTEM_PROMPT = `
You are a professional teacher. Your task is to generate a quiz based on the provided text.

1. Create exactly 10 Multiple Choice Questions (MCQs).
2. For each question, provide 4 options: A, B, C, and D.
3. Ensure only one answer is correct.
4. Provide a 1-sentence explanation for why the correct answer is right.
5. Keep language clear and academic.

Output format:

# 📝 Quiz: Knowledge Check

---

### Question 1
[Question text here]
A) [Option A]
B) [Option B]
C) [Option C]
D) [Option D]

**Correct Answer:** [A/B/C/D]
**Explanation:** [Brief explanation]

---

(Repeat for questions 2 through 10)
`;

/**
 * bindufy — converts into full microservice
 */
bindufy(
  {
    author: "your.email@example.com",
    name: "quiz-generator-agent",
    description: "Educational assessment expert for MCQ generation",
    version: "1.0.0",
    deployment: {
      url: "http://localhost:3773",
      expose: true,
      cors_origins: ["http://localhost:5173"],
    },
    skills: ["skills/quiz-generation"],
    capabilities: {
      streaming: false,
      push_notifications: false,
    },
  },

  /**
   * Handler
   */
  async (messages: ChatMessage[]) => {
    try {
      if (!messages || messages.length === 0) {
        return "Error: No input provided.";
      }

      // Extract latest user input (better than passing full history blindly)
      const userInput = messages[messages.length - 1].content;

      // Construct LangChain messages
      const langchainMessages = [
        { role: "system", content: SYSTEM_PROMPT },
        { role: "user", content: userInput },
      ];

      // Call LLM
      const response = await llm.invoke(langchainMessages);

      // Return response
      return typeof response.content === "string"
        ? response.content
        : JSON.stringify(response.content);
    } catch (error: any) {
      return `Error: ${error.message}`;
    }
  }
);
```

## Skill Configuration

Create `skills/quiz-generation/skill.yaml`:

```yaml theme={null}
id: quiz-generation
name: Quiz Generation Skill
version: 1.0.0
author: your.email@example.com
description: |
  Advanced educational assessment skill that generates professional
  multiple-choice quizzes from any provided text or topic.

  Features:
  - Generates exactly 10 MCQs per request
  - 4 options per question (A, B, C, D)
  - One correct answer per question
  - Brief explanations for each correct answer
  - Academic language and clear formatting
  - Structured output with markdown

  Uses LangChain with OpenRouter's GPT-OSS-120b model
  for high-quality educational content generation.
tags:
  - education
  - quiz
  - assessment
  - mcq
  - learning
  - teaching
  - evaluation
input_modes:
  - application/json
output_modes:
  - application/json
examples:
  - "Generate a quiz about World War II"
  - "Create a quiz based on this chapter about photosynthesis"
  - "Make a quiz about basic mathematics concepts"
  - "Generate assessment questions for this programming tutorial"
capabilities_detail:
  quiz_generation:
    supported: true
    description: "Generates 10-question multiple-choice quizzes"
    features:
      - structured_formatting
      - academic_language
      - answer_explanations
  educational_assessment:
    supported: true
    description: "Creates professional educational assessments"
    methodology: "MCQ format with 4 options and explanations"
  content_processing:
    supported: true
    description: "Processes provided text to generate relevant questions"
  output_formatting:
    supported: true
    description: "Structured markdown output with clear formatting"
```

## How It Works

**TypeScript Integration**

* Uses `@bindu/sdk` for Bindu protocol compliance
* LangChain integration with `@langchain/openai`
* Type-safe development with TypeScript

**LLM Configuration**

* OpenRouter API via baseURL override
* GPT-OSS-120b model for high-quality output
* Low temperature (0.3) for consistent quiz generation

**Quiz Generation**

* System prompt with detailed formatting instructions
* Exactly 10 MCQs per request
* 4 options per question (A, B, C, D)
* One correct answer with explanation
* Academic language and structured markdown output

**Error Handling**

* Graceful error handling with descriptive messages
* Input validation for message arrays
* Response type checking and formatting

## Dependencies

```bash theme={null}
# Initialize TypeScript project
npm init -y

# Install dependencies
npm install @bindu/sdk @langchain/openai dotenv

# Install TypeScript and development dependencies
npm install -D typescript @types/node ts-node
```

## Environment Setup

Create `.env` file:

```bash theme={null}
OPENROUTER_API_KEY=your_openrouter_api_key_here
```

## Run

```bash theme={null}
# Compile and run TypeScript
npx ts-node quiz-generator-agent.ts

# Or compile first then run
npx tsc quiz-generator-agent.ts
node quiz-generator-agent.js
```

**Examples:**

* "Generate a quiz about World War II"
* "Create a quiz based on this chapter about photosynthesis"
* "Make a quiz about basic mathematics concepts"
* "Generate assessment questions for this programming tutorial"

## Example API Calls

<AccordionGroup>
  <Accordion title="Message Send Request">
    ```json theme={null}
    {
      "jsonrpc": "2.0",
      "method": "message/send",
      "params": {
        "message": {
          "role": "user",
          "kind": "message",
          "messageId": "9f11c870-5616-49ad-b187-d93cbb100001",
          "contextId": "9f11c870-5616-49ad-b187-d93cbb100002",
          "taskId": "9f11c870-5616-49ad-b187-d93cbb100003",
          "parts": [
            {
              "kind": "text",
              "text": "Generate a quiz about World War II"
            }
          ]
        },
         "skillId": "quiz-generation",
        "configuration": {
          "acceptedOutputModes": ["application/json"]
        }
      },
      "id": "9f11c870-5616-49ad-b187-d93cbb100003"
    }
    ```
  </Accordion>

  <Accordion title="Task get Request">
    ```json theme={null}
    {
      "jsonrpc": "2.0",
      "method": "tasks/get",
      "params": {
        "taskId": "9f11c870-5616-49ad-b187-d93cbb100003"
      },
      "id": "9f11c870-5616-49ad-b187-d93cbb100004"
    }
    ```
  </Accordion>
</AccordionGroup>

## Frontend Setup

```bash theme={null}
# Clone the Bindu repository
git clone https://github.com/GetBindu/Bindu

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

# Start frontend development server
npm run dev
```

Open [http://localhost:5173](http://localhost:5173) and try to chat with the quiz generator agent