CCDV-F Prompt and Context Engineering Practice Question
A developer is using Claude to review pull requests. The prompt includes a 4,000-line diff followed by the question 'List any security issues.' Claude's answers are vague and sometimes reference the wrong file. The developer wants more precise, file-specific findings without switching models. Which change is most likely to improve precision?
⚠ Common exam trap
The trap here is assuming that shortening the question or splitting the diff into tiny pieces increases precision, when the real fix is labeling files and requesting a structured, per-file output format.
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
✓
Restructure the diff so each file is wrapped in its own labeled tag, and ask for findings in a per-file structured list.
Precision improves when the prompt gives the model clear boundaries and a specific output structure. Wrapping each file in labeled tags lets the model attribute findings to the correct file, and requesting a per-file structured list enforces specificity. Vague questions, broad essays, or extreme splitting lose the context and attribution needed for accurate, file-specific security findings.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Shorten the question to 'Any issues?' so the model has more room to reason about the diff.
Why it's wrong here
Making the question vaguer removes the security focus and gives the model no format to follow, which tends to produce even less precise answers. Output length is not the bottleneck; attribution and task clarity are. This change would likely worsen the wrong-file references and vague findings rather than improve precision.
- ✓
Restructure the diff so each file is wrapped in its own labeled tag, and ask for findings in a per-file structured list.
Why this is correct
Labeling each file with its own tag gives the model clear boundaries to attribute findings to, and requesting a per-file structured list forces specificity rather than general commentary. This directly targets the wrong-file and vague-answer symptoms. It is a prompt-level restructuring that improves grounding without changing the model or the underlying diff content.
- ✗
Split the diff into 4,000 separate single-line prompts and merge the answers afterward.
Why it's wrong here
Per-line prompts destroy the surrounding context needed to judge security issues, since vulnerabilities often span multiple lines and functions. Merging thousands of responses is costly and error-prone. This approach also multiplies latency and token usage dramatically. It does not improve precision in a meaningful way and would likely miss issues that require cross-line reasoning.
- ✗
Ask Claude to produce a long free-form essay about the overall code quality before listing issues.
Why it's wrong here
Requesting a broad essay dilutes focus and consumes output budget on general commentary rather than security analysis. It also does not help the model attribute findings to specific files, since the task remains underspecified. Vague, non-file-specific output would likely persist, so this change does not address the precision problem the developer is facing.
About these practice questions
This CCDV-F question is part of Courseiva's 257-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. 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 CCDV-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 CCDV-F exam.