CCAR-F practice question 4 of 10

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews…

Full set: 191 questions
You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives. Your automated code review is missing genuine bugs in pull requests. Investigation reveals that your review prompt includes the instruction: ''Only flag critical issues that would definitely cause production failures. Ignore minor concerns and anything you are uncertain about.'' Developers confirm that some missed bugs are genuine logic errors that the model investigated but chose not to report. The team requires the review output to remain structured, with each finding tagged with metadata, and actionable. Which prompt change both removes the cause of the suppressed findings and preserves structured, tagged output for downstream filtering?
Answer options
A: Add a second review pass that rereads the diff using the same prompt, looking for anything the first pass may have missed.
B: Instruct the model to report all findings with confidence and severity tags, deferring filtering to a downstream step. Correct answer
C: Remove all severity-related instructions from the prompt and let the model use its default judgment about what to report.
D: Enable extended thinking and instruct the model to reason step by step about every code change before producing its review.
Correct Answer:
B. Instruct the model to report all findings with confidence and severity tags, deferring filtering to a downstream step.
Explanation

The original prompt forces the model to prematurely filter out issues it is uncertain about, leading to false negatives (missed genuine bugs). By instructing the model to report all findings and categorize them using confidence and severity tags, you shift the filtering logic from the model's internal generation phase to a deterministic downstream process. This ensures no potential bugs are suppressed while maintaining the required structured and actionable metadata for the CI/CD pipeline.

Why Incorrect

A. A second pass with the same flawed prompt will likely result in the same suppressed findings due to the restrictive instructions.
C. Removing severity instructions entirely eliminates the structured metadata required by the team for downstream filtering.
D. Extended thinking improves reasoning but does not override explicit prompt instructions to ignore uncertain issues.

References

- Anthropic Prompt Engineering Guide, "Prompting for Structured Output".

- Anthropic Documentation, "Mitigating False Negatives".

Scroll to Top