CCAO-F Claude Model Fundamentals Practice Question
A team is using Claude to summarize legal contracts. They need the summaries to reflect only the contract text, not any outside assumptions. Which prompting technique best reduces the chance that Claude introduces information not present in the source document?
⚠ Common exam trap
The trap here is assuming that a more capable model automatically avoids hallucination, when faithful summarization actually depends on explicit grounding instructions and a safe fallback for missing information.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Instruct Claude to answer only from the provided document and to say when the document does not contain the answer.
Grounding Claude in the provided document, and instructing it to say when the answer is absent, is the most direct way to keep summaries faithful to the source. It constrains the model to the supplied text and provides a safe response when information is missing. Raising temperature, relying on general legal knowledge, or removing the document all increase the risk of unsupported content rather than reducing it.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Ask Claude to summarize from its general knowledge of contract law first, then compare with the document.
Why it's wrong here
Prompting Claude to lean on general legal knowledge invites outside assumptions, which is exactly what the team wants to avoid. It can cause the model to blend boilerplate contract concepts with the actual text, producing summaries that are not faithful to the document. Grounding should restrict, not expand, the knowledge sources Claude may draw from.
- ✗
Remove the document entirely and ask Claude to generate a typical contract summary template.
Why it's wrong here
Without the document, Claude cannot summarize its actual contents and would instead produce a generic template based on pretraining patterns. This guarantees the output does not reflect the specific contract and would be useless or misleading for legal review. The source text must remain in context for any faithful summarization to occur.
- ✓
Instruct Claude to answer only from the provided document and to say when the document does not contain the answer.
Why this is correct
Explicitly constraining Claude to the supplied document and requiring it to acknowledge missing information is a direct, effective guard against unsupported claims. It sets a clear behavioral boundary in the prompt and gives Claude a safe fallback instead of inventing details. For legal summaries where fidelity to the source is critical, this grounding instruction materially reduces hallucination risk.
- ✗
Raise the temperature so Claude explores more possible interpretations of the contract.
Why it's wrong here
Higher temperature increases randomness and creativity, which is the opposite of what a faithful legal summary needs. It makes outputs less deterministic and more likely to drift from the source text. For a task requiring strict fidelity, raising temperature would increase, not decrease, the risk of unsupported statements and inconsistent summaries.
About these practice questions
One of 259 original CCAO-F practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Anthropic exam blueprint
This CCAO-F practice question is part of Courseiva's free Anthropic certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the CCAO-F exam.