CCAO-F Prompting and Context Engineering Practice Question
A developer is using Claude to summarize legal contracts. The contracts can be very long, sometimes exceeding 100,000 tokens. The developer wants to ensure that Claude focuses on the most relevant sections, such as indemnification and termination clauses, while ignoring boilerplate. Which approach is best for managing the context window and improving summary accuracy?
⚠ Common exam trap
The trap here is assuming that Claude's large context window means you can always include the entire document, but focusing on relevant sections yields better accuracy and efficiency.
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
✓
Use a retrieval system to extract sections containing keywords like 'indemnification' and 'termination' and include only those in the prompt.
For very long documents, using a retrieval system to extract only the sections relevant to the summarization task is the most effective approach. It reduces the context size, ensuring Claude can process the entire input within token limits, and focuses attention on critical clauses. This method improves accuracy by filtering out boilerplate and irrelevant text, allowing Claude to generate a concise and relevant summary.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the temperature to encourage Claude to explore different parts of the contract.
Why it's wrong here
Higher temperature increases randomness and creativity, which is undesirable for legal summarization where precision is paramount. It does not help manage context length or focus on relevant sections. In fact, it may lead to inconsistent and less accurate summaries. Temperature should be kept low for factual tasks.
- ✓
Use a retrieval system to extract sections containing keywords like 'indemnification' and 'termination' and include only those in the prompt.
Why this is correct
Retrieving and including only the relevant sections reduces the context size and focuses Claude's attention on the most important clauses. This approach improves summarization accuracy by eliminating boilerplate and ensuring the model processes the critical parts. It also helps stay within token limits, making it the best strategy for long contracts.
- ✗
Ask Claude to first summarize each page of the contract and then combine the summaries.
Why it's wrong here
This multi-step approach can work but is more complex and may lose context between pages. Summarizing page-by-page might miss cross-references or clauses that span multiple pages. It also increases the number of API calls and potential for error accumulation. Directly providing relevant sections is simpler and more accurate.
- ✗
Place the entire contract in the prompt and ask Claude to summarize the key clauses.
Why it's wrong here
While Claude can handle large contexts, placing the entire contract may exceed the context window or dilute attention. The model might overlook important clauses buried in boilerplate. Without guidance to focus on specific sections, the summary may be less accurate and miss critical details. This approach is inefficient for very long documents.
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.