Claude Certified Developer Foundations CCDV-F Exam Questions
Your Claude application's outputs are inconsistent in format. The team’s instructions are scattered across the system prompt and user messages, with some instructions stated only once and others repeated.
How would you fix the inconsistency?
Correct Answer: B
Option B creates a clear separation between persistent application instructions and per-request user content. Stable behavioral rules—role, output conventions, formatting constraints, policies, and other instructions intended to apply across requests—belong in the system-level instruction layer. User messages should primarily carry task-specific input and requirements that vary from interaction to interaction.
Anthropic’s Messages API defines the system prompt specifically as the mechanism for providing overarching context and instructions to Claude. Current guidance likewise recommends the top-level system field for instructions that should apply from the beginning of the conversation, while more transient information belongs in conversation messages.
A mixes persistent application behavior with user-controlled content and weakens separation of concerns. C preserves the inconsistent architecture responsible for the problem. D duplicates instructions unnecessarily, wastes context tokens, and increases the possibility that future edits create conflicting versions of the same rule.
Consolidating stable instructions also makes prompts easier to version, evaluate, review, and maintain. Therefore, B is the correct design. Relevant Study Guide topics: system prompts, instruction hierarchy, prompt organization, formatting consistency, separation of concerns, and maintainable prompt construction.