Build It: Terminal Quiz Bot Powered by Claude

A CLI quiz app: Claude generates questions on any topic, you answer, it grades. Teaches prompts, loops, and keeping state.

45 min · Reviewed 2026

What we're building

A terminal script that asks for a topic, calls Claude to get 5 multiple-choice questions, asks them one at a time, tracks your score, and shows the final result. Real code, ~80 lines.

# pyproject.toml: anthropic, pydantic

import json
from pydantic import BaseModel, Field
from anthropic import Anthropic

class Question(BaseModel):
    prompt: str
    options: list[str] = Field(min_length=4, max_length=4)
    correct_index: int = Field(ge=0, le=3)
    explanation: str

class QuizSet(BaseModel):
    topic: str
    questions: list[Question]Pydantic models define the exact shape we expect from the LLM.

client = Anthropic()

def generate_quiz(topic: str, n: int = 5) -> QuizSet:
    prompt = f"""Generate exactly {n} multiple-choice questions about: {topic}

Return ONLY valid JSON, no markdown fence, matching this shape:
{{
  "topic": "...",
  "questions": [
    {{"prompt": "...", "options": ["a","b","c","d"], "correct_index": 0, "explanation": "..."}}
  ]
}}

Target middle-school difficulty. No trick questions."""
    response = client.messages.create(
        model="claude-opus-4-7",
        max_tokens=2000,
        messages=[{"role": "user", "content": prompt}],
    )
    raw = response.content[0].text.strip()
    if raw.startswith("```"):
        raw = raw.strip("`").split("\n", 1)[1].rsplit("\n", 1)[0]
    return QuizSet.model_validate_json(raw)One LLM call returns the whole quiz. Pydantic will reject malformed output.

def run_quiz(quiz: QuizSet) -> int:
    score = 0
    for i, q in enumerate(quiz.questions, start=1):
        print(f"\n--- Question {i}/{len(quiz.questions)} ---")
        print(q.prompt)
        for idx, opt in enumerate(q.options):
            print(f"  {idx+1}. {opt}")
        while True:
            raw = input("Your answer (1-4): ").strip()
            if raw in {"1","2","3","4"}:
                break
            print("Please enter 1, 2, 3, or 4.")
        chosen = int(raw) - 1
        if chosen == q.correct_index:
            print("Correct!")
            score += 1
        else:
            correct = q.options[q.correct_index]
            print(f"Nope — answer was: {correct}")
        print(f"Why: {q.explanation}")
    return score

def main():
    topic = input("Topic? ").strip() or "the solar system"
    print(f"Generating quiz about {topic}...")
    try:
        quiz = generate_quiz(topic)
    except Exception as e:
        print(f"Quiz generation failed: {e}")
        return
    final = run_quiz(quiz)
    print(f"\nFinal score: {final}/{len(quiz.questions)}")

if __name__ == "__main__":
    main()The main loop: ask, validate input, score, report.

Mini-exercise

Run the quiz on three different topics
Add a --difficulty flag (easy/medium/hard) and wire it into the prompt
After the quiz, ask Claude to explain one question in simpler terms
Save results to quiz_history.json

Ad-hoc JSON parse	Pydantic schema
Crashes on bad output	Raises ValidationError with field path
Easy to write	Slightly more setup
Good for: throwaway scripts	Good for: anything you run twice

Big idea: an LLM + a typed schema + a simple loop is a stunningly powerful base for any interactive tool. You've now built the skeleton every AI tutor app shares.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-prog-python-quiz-bot-builders

What is the core idea behind "Build It: Terminal Quiz Bot Powered by Claude"?
1. A CLI quiz app: Claude generates questions on any topic, you answer, it grades. Teaches prompts, loops, and keeping state.
2. Classes let you bundle data with the behavior that operates on it.
3. Add a docstring
4. If divisible by both, print 'FizzBuzz'
Which term best describes a foundational idea in "Build It: Terminal Quiz Bot Powered by Claude"?
1. input loop
2. CLI
3. pydantic
4. LLM JSON
A learner studying Build It: Terminal Quiz Bot Powered by Claude would need to understand which concept?
1. CLI
2. pydantic
3. input loop
4. LLM JSON
Which of these is directly relevant to Build It: Terminal Quiz Bot Powered by Claude?
1. CLI
2. input loop
3. LLM JSON
4. pydantic
Which of the following is a key point about Build It: Terminal Quiz Bot Powered by Claude?
1. Run the quiz on three different topics
2. Add a --difficulty flag (easy/medium/hard) and wire it into the prompt
3. After the quiz, ask Claude to explain one question in simpler terms
4. Save results to quiz_history.json
Which of these does NOT belong in a discussion of Build It: Terminal Quiz Bot Powered by Claude?
1. Classes let you bundle data with the behavior that operates on it.
2. After the quiz, ask Claude to explain one question in simpler terms
3. Add a --difficulty flag (easy/medium/hard) and wire it into the prompt
4. Run the quiz on three different topics
What is the key insight about "Why a Pydantic schema matters" in the context of Build It: Terminal Quiz Bot Powered by Claude?
1. Classes let you bundle data with the behavior that operates on it.
2. Add a docstring
3. LLMs sometimes return 3 questions instead of 5, or put correct_index outside 0-3.
4. If divisible by both, print 'FizzBuzz'
What is the recommended tip about "Review before you run" in the context of Build It: Terminal Quiz Bot Powered by Claude?
1. Classes let you bundle data with the behavior that operates on it.
2. Add a docstring
3. If divisible by both, print 'FizzBuzz'
4. AI code is a first draft. Read through it, understand each line, and test on sample inputs before merging into real proj…
Which statement accurately describes an aspect of Build It: Terminal Quiz Bot Powered by Claude?
1. A terminal script that asks for a topic, calls Claude to get 5 multiple-choice questions, asks them one at a time, tracks your score, and sh…
2. Classes let you bundle data with the behavior that operates on it.
3. Add a docstring
4. If divisible by both, print 'FizzBuzz'
What does working with Build It: Terminal Quiz Bot Powered by Claude typically involve?
1. Classes let you bundle data with the behavior that operates on it.
2. Big idea: an LLM + a typed schema + a simple loop is a stunningly powerful base for any interactive tool.
3. Add a docstring
4. If divisible by both, print 'FizzBuzz'
Which best describes the scope of "Build It: Terminal Quiz Bot Powered by Claude"?
1. It is unrelated to ai-coding workflows
2. It applies only to the opposite beginner tier
3. It focuses on A CLI quiz app: Claude generates questions on any topic, you answer, it grades. Teaches prompts, loo
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Build It: Terminal Quiz Bot Powered by Claude?
1. Classes let you bundle data with the behavior that operates on it.
2. Add a docstring
3. If divisible by both, print 'FizzBuzz'
4. Mini-exercise
Which of the following is a concept covered in Build It: Terminal Quiz Bot Powered by Claude?
1. CLI
2. input loop
3. pydantic
4. LLM JSON
Which of the following is a concept covered in Build It: Terminal Quiz Bot Powered by Claude?
1. CLI
2. input loop
3. pydantic
4. LLM JSON
Which of the following is a concept covered in Build It: Terminal Quiz Bot Powered by Claude?
1. CLI
2. input loop
3. pydantic
4. LLM JSON

← Back to interactive lesson

Tendril · Builders · AI-Assisted Coding

Build It: Terminal Quiz Bot Powered by Claude

A CLI quiz app: Claude generates questions on any topic, you answer, it grades. Teaches prompts, loops, and keeping state.

45 min · Reviewed 2026

What we're building

A terminal script that asks for a topic, calls Claude to get 5 multiple-choice questions, asks them one at a time, tracks your score, and shows the final result. Real code, ~80 lines.

# pyproject.toml: anthropic, pydantic

import json
from pydantic import BaseModel, Field
from anthropic import Anthropic

class Question(BaseModel):
    prompt: str
    options: list[str] = Field(min_length=4, max_length=4)
    correct_index: int = Field(ge=0, le=3)
    explanation: str

class QuizSet(BaseModel):
    topic: str
    questions: list[Question]Pydantic models define the exact shape we expect from the LLM.

client = Anthropic()

def generate_quiz(topic: str, n: int = 5) -> QuizSet:
    prompt = f"""Generate exactly {n} multiple-choice questions about: {topic}

Return ONLY valid JSON, no markdown fence, matching this shape:
{{
  "topic": "...",
  "questions": [
    {{"prompt": "...", "options": ["a","b","c","d"], "correct_index": 0, "explanation": "..."}}
  ]
}}

Target middle-school difficulty. No trick questions."""
    response = client.messages.create(
        model="claude-opus-4-7",
        max_tokens=2000,
        messages=[{"role": "user", "content": prompt}],
    )
    raw = response.content[0].text.strip()
    if raw.startswith("```"):
        raw = raw.strip("`").split("\n", 1)[1].rsplit("\n", 1)[0]
    return QuizSet.model_validate_json(raw)One LLM call returns the whole quiz. Pydantic will reject malformed output.

def run_quiz(quiz: QuizSet) -> int:
    score = 0
    for i, q in enumerate(quiz.questions, start=1):
        print(f"\n--- Question {i}/{len(quiz.questions)} ---")
        print(q.prompt)
        for idx, opt in enumerate(q.options):
            print(f"  {idx+1}. {opt}")
        while True:
            raw = input("Your answer (1-4): ").strip()
            if raw in {"1","2","3","4"}:
                break
            print("Please enter 1, 2, 3, or 4.")
        chosen = int(raw) - 1
        if chosen == q.correct_index:
            print("Correct!")
            score += 1
        else:
            correct = q.options[q.correct_index]
            print(f"Nope — answer was: {correct}")
        print(f"Why: {q.explanation}")
    return score

def main():
    topic = input("Topic? ").strip() or "the solar system"
    print(f"Generating quiz about {topic}...")
    try:
        quiz = generate_quiz(topic)
    except Exception as e:
        print(f"Quiz generation failed: {e}")
        return
    final = run_quiz(quiz)
    print(f"\nFinal score: {final}/{len(quiz.questions)}")

if __name__ == "__main__":
    main()The main loop: ask, validate input, score, report.

Mini-exercise

Run the quiz on three different topics
Add a --difficulty flag (easy/medium/hard) and wire it into the prompt
After the quiz, ask Claude to explain one question in simpler terms
Save results to quiz_history.json

Ad-hoc JSON parse	Pydantic schema
Crashes on bad output	Raises ValidationError with field path
Easy to write	Slightly more setup
Good for: throwaway scripts	Good for: anything you run twice

Big idea: an LLM + a typed schema + a simple loop is a stunningly powerful base for any interactive tool. You've now built the skeleton every AI tutor app shares.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-prog-python-quiz-bot-builders

What is the core idea behind "Build It: Terminal Quiz Bot Powered by Claude"?
1. A CLI quiz app: Claude generates questions on any topic, you answer, it grades. Teaches prompts, loops, and keeping state.
2. Classes let you bundle data with the behavior that operates on it.
3. Add a docstring
4. If divisible by both, print 'FizzBuzz'
Which term best describes a foundational idea in "Build It: Terminal Quiz Bot Powered by Claude"?
1. input loop
2. CLI
3. pydantic
4. LLM JSON
A learner studying Build It: Terminal Quiz Bot Powered by Claude would need to understand which concept?
1. CLI
2. pydantic
3. input loop
4. LLM JSON
Which of these is directly relevant to Build It: Terminal Quiz Bot Powered by Claude?
1. CLI
2. input loop
3. LLM JSON
4. pydantic
Which of the following is a key point about Build It: Terminal Quiz Bot Powered by Claude?
1. Run the quiz on three different topics
2. Add a --difficulty flag (easy/medium/hard) and wire it into the prompt
3. After the quiz, ask Claude to explain one question in simpler terms
4. Save results to quiz_history.json
Which of these does NOT belong in a discussion of Build It: Terminal Quiz Bot Powered by Claude?
1. Classes let you bundle data with the behavior that operates on it.
2. After the quiz, ask Claude to explain one question in simpler terms
3. Add a --difficulty flag (easy/medium/hard) and wire it into the prompt
4. Run the quiz on three different topics
What is the key insight about "Why a Pydantic schema matters" in the context of Build It: Terminal Quiz Bot Powered by Claude?
1. Classes let you bundle data with the behavior that operates on it.
2. Add a docstring
3. LLMs sometimes return 3 questions instead of 5, or put correct_index outside 0-3.
4. If divisible by both, print 'FizzBuzz'
What is the recommended tip about "Review before you run" in the context of Build It: Terminal Quiz Bot Powered by Claude?
1. Classes let you bundle data with the behavior that operates on it.
2. Add a docstring
3. If divisible by both, print 'FizzBuzz'
4. AI code is a first draft. Read through it, understand each line, and test on sample inputs before merging into real proj…
Which statement accurately describes an aspect of Build It: Terminal Quiz Bot Powered by Claude?
1. A terminal script that asks for a topic, calls Claude to get 5 multiple-choice questions, asks them one at a time, tracks your score, and sh…
2. Classes let you bundle data with the behavior that operates on it.
3. Add a docstring
4. If divisible by both, print 'FizzBuzz'
What does working with Build It: Terminal Quiz Bot Powered by Claude typically involve?
1. Classes let you bundle data with the behavior that operates on it.
2. Big idea: an LLM + a typed schema + a simple loop is a stunningly powerful base for any interactive tool.
3. Add a docstring
4. If divisible by both, print 'FizzBuzz'
Which best describes the scope of "Build It: Terminal Quiz Bot Powered by Claude"?
1. It is unrelated to ai-coding workflows
2. It applies only to the opposite beginner tier
3. It focuses on A CLI quiz app: Claude generates questions on any topic, you answer, it grades. Teaches prompts, loo
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Build It: Terminal Quiz Bot Powered by Claude?
1. Classes let you bundle data with the behavior that operates on it.
2. Add a docstring
3. If divisible by both, print 'FizzBuzz'
4. Mini-exercise
Which of the following is a concept covered in Build It: Terminal Quiz Bot Powered by Claude?
1. CLI
2. input loop
3. pydantic
4. LLM JSON
Which of the following is a concept covered in Build It: Terminal Quiz Bot Powered by Claude?
1. CLI
2. input loop
3. pydantic
4. LLM JSON
Which of the following is a concept covered in Build It: Terminal Quiz Bot Powered by Claude?
1. CLI
2. input loop
3. pydantic
4. LLM JSON

← Back to interactive lesson