CCAO-F Prompting and Context Engineering Practice Question
A developer is using Claude to summarize legal contracts. They notice that the summaries are sometimes too short and miss critical clauses. How should the developer adjust the prompt to ensure more comprehensive summaries?
⚠ Common exam trap
Candidates often assume that simply asking for a 'comprehensive' summary is sufficient. They fail to realize that without specific structural guidance or clause identification, the model may prioritize brevity over completeness.
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
✓
Ask the model to list all 'indemnification' and 'termination' clauses specifically.
Improving summary depth requires clear expectations and structural guidance. By specifying the types of clauses to look for and asking for a more detailed format, the developer can push the model to be more thorough. Encouraging the model to first identify key sections before summarizing them can also improve coverage and accuracy.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Simply add 'Make it longer' to the end of the prompt.
Why it's wrong here
Vague instructions like 'make it longer' do not provide the model with a clear understanding of what information is missing. This often results in the model adding fluff or repetitive text rather than identifying and including the critical legal clauses that were previously omitted.
- ✓
Ask the model to list all 'indemnification' and 'termination' clauses specifically.
Why this is correct
Providing specific categories of information to search for gives the model a clear checklist to follow. This targeted approach is much more effective than general instructions, as it directs the model's attention to specific legal concepts that are essential for a comprehensive and high-quality summary.
- ✗
Set the max_tokens to 4096 to force a longer response.
Why it's wrong here
Increasing the 'max_tokens' limit only increases the maximum possible length of the response; it does not compel the model to use that space. If the model believes it has completed the task, it will stop generating regardless of how much token budget remains available.
- ✗
Use a system prompt that says 'You are a very verbose lawyer'.
Why it's wrong here
While personas can influence style, being 'verbose' does not necessarily mean being more accurate or thorough. A verbose model might use more words to say the same thing without actually including the critical legal details that were missing from the original shorter 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.