def evaluate_end_to_end(query, generated_answer, correct_answer):
    prompt = f"""
…
    Is the Generated Answer correct based on the Correct Answer? You should pay attention to the substance of the answer, and ignore minute details that may differ.
…
    However, if there is any critical piece of information which is missing from the generated answer in comparison to the correct answer, then we should mark this as incorrect.

    Finally, if there are any direct contradictions between the correct answer and generated answer, we should deem the generated answer to be incorrect.

    Respond in the following XML format:
    <evaluation>
    <content>
    <explanation>Your explanation here</explanation>
    <is_correct>true/false</is_correct>
    </content>
    </evaluation>
    """

    client = Anthropic(api_key=os.environ.get("ANTHROPIC_API_KEY"))
    try:
        response = client.messages.create(
            model="claude-sonnet-4-6",
            max_tokens=1500,
            messages=[
                {"role": "user", "content": prompt},
                {"role": "assistant", "content": "<evaluation>"},
            ],
            temperature=0,
            stop_sequences=["</evaluation>"],
        )
…
        is_correct_match = re.search(r"<is_correct>(.*?)</is_correct>", response_text, re.DOTALL)
…
    except Exception as e:
        print(f"Unexpected error: {e}")
        result = {
            "question": query,
            "correct_answer": correct_answer,
            "generated_answer": generated_answer,
            "is_correct": False,
            "explanation": f"Unexpected error: {str(e)}",
        }

Warm-up