CCDV-F Prompt and Context Engineering Practice Question
A developer is building a customer-support agent on the Claude Messages API. The agent receives a long conversation history plus a retrieved knowledge-base article, and the developer wants Claude to answer only from the retrieved article while still seeing the full chat for tone. The developer wants the retrieved article treated as the most authoritative source, even if earlier turns contain outdated policy statements. Where should the retrieved article be placed, and how should it be marked?
⚠ Common exam trap
The trap here is assuming that simply placing important content first or last in the message list, rather than in the system prompt, gives it precedence over conflicting instructions.
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
✓
Place the retrieved article inside the system prompt, wrapped in <policy> tags, and instruct Claude that <policy> content overrides any conflicting statements in the conversation.
The system prompt is the operator-controlled channel and carries more weight than user or assistant turns, making it the right place to establish that the retrieved article is authoritative. Tagging the article with XML-style delimiters gives Claude an unambiguous boundary for the trusted content, so outdated policy in earlier conversation turns does not win.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Place the retrieved article inside the system prompt, wrapped in <policy> tags, and instruct Claude that <policy> content overrides any conflicting statements in the conversation.
Why this is correct
System-prompt content is treated as operator-level instruction and outranks user and assistant turns, so wrapping the article in <policy> tags and declaring it authoritative gives it precedence over stale chat turns. This directly satisfies the requirement that the retrieved article be the most trusted source while the conversation still supplies tone.
- ✗
Insert the retrieved article into a tool_result block from a search tool and instruct Claude to prefer tool results over all other content.
Why it's wrong here
Tool results are inputs the model reasons over, not a higher-priority instruction channel, and the model will not automatically treat them as overriding contradictory user turns. The developer would still need an authoritative instruction, which is better expressed in the system prompt than in a tool_result block.
- ✗
Place the retrieved article as the first user turn, followed by the conversation history, and rely on Claude's recency bias to prefer the article.
Why it's wrong here
Putting the article as the first user turn makes it an ordinary user message with no elevated authority, and it is the oldest content in the window. Later user turns containing outdated policy can easily override it, so this does not make the article the authoritative source the developer requires.
- ✗
Append the retrieved article as the final assistant turn so Claude treats it as its own prior statement and repeats it verbatim.
Why it's wrong here
Pre-filling an assistant turn constrains the model's continuation, but it does not grant the article operator-level authority. It also risks the model parroting the article instead of answering, and any conflicting system or user instruction still takes precedence over an assistant turn.
About these practice questions
One of 257 original CCDV-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 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.