CCAR-F Prompt Engineering and Structured Output Practice Question
A developer builds a Claude-powered assistant that answers questions over a 300-page policy manual. When the whole manual is placed in a single prompt, answers to questions about clauses in the middle of the document are frequently wrong or vague, while answers about the opening and closing sections are accurate. The manual must stay available in full, and the team wants to keep latency reasonable. Which technique most effectively improves accuracy for the mid-document clauses?
⚠ Common exam trap
The trap here is assuming that simply reordering the long document or enlarging the token budget fixes mid-context recall, when the real fix is reducing the prompt to retrieved, relevant passages.
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
✓
Split the manual into sections, embed each section, retrieve the most relevant sections for the question, and place only those retrieved sections in the prompt before the question.
Accuracy drops for material buried in the middle of a very long context because attention is spread thin across the document. Retrieving the sections most relevant to each question and placing only those in the prompt shrinks the context to on-topic passages, which restores accuracy for mid-document clauses while the full manual stays indexed for availability. Reordering or enlarging the same long context does not fix the attention problem.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Split the manual into sections, embed each section, retrieve the most relevant sections for the question, and place only those retrieved sections in the prompt before the question.
Why this is correct
Retrieval-augmented prompting addresses the mid-document weakness by selecting the passages most relevant to the question and placing them near the end of the prompt, where attention is strongest. The model reasons over a small, on-topic context instead of a long document, improving accuracy for clauses that previously sat in the poorly attended middle. Keeping the full manual in the index preserves availability while bounding prompt size and latency.
- ✗
Increase max_tokens substantially and instruct the model to think step by step before answering each question.
Why it's wrong here
Longer chain-of-thought can help with reasoning, but it does not fix the retrieval of facts that the model under-weights in a huge context. The mid-document clauses are still present in an oversized prompt, so the model may reason carefully over incomplete or fuzzy recall. Raising max_tokens also increases latency and cost without guaranteeing that the right clause is attended to.
- ✗
Ask the user to restate their question using exact phrases from the manual so the model can match keywords directly.
Why it's wrong here
Pushing the burden onto users degrades the experience and still relies on the model locating the clause inside a long prompt, which is the actual failure. Keyword overlap does not guarantee the relevant passage is attended to when hundreds of pages compete for attention. This option shifts responsibility without changing the underlying long-context limitation.
- ✗
Keep the full manual in the prompt but move it so the manual text appears after the question rather than before it.
Why it's wrong here
Reordering input does not change the fundamental problem that a very long context spreads the model's attention thin across hundreds of pages. Placing the whole manual after the question still buries mid-document clauses in a large block, so accuracy for those clauses remains unreliable. This option rearranges the same oversized context instead of reducing it to the relevant material.
About these practice questions
One of 271 original CCAR-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 CCAR-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 CCAR-F exam.