CCDV-F Prompt and Context Engineering Practice Question
A developer is writing a support-triage prompt for Claude. The prompt contains a 12-page product manual followed by the customer's question. Testing shows Claude sometimes answers using general knowledge about competing products instead of the manual. The developer wants Claude to ground every answer in the manual and to say 'not covered' when the manual lacks the answer. Which change best achieves this?
⚠ Common exam trap
The trap here is treating a generic 'do not hallucinate' instruction as equivalent to requiring a supporting quote and a defined refusal response.
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
✓
Instruct Claude to quote the relevant manual passage before answering, and to reply 'not covered' if no passage supports the answer.
Grounding improves when the model must produce evidence before its conclusion, because the quoted passage anchors the answer in the manual. Giving an explicit 'not covered' response removes the pressure to invent an answer, which is what allows general knowledge to leak in. Together these two elements address both the sourcing and the fallback behavior.
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 manual to its first two pages so the context is easier for Claude to process.
Why it's wrong here
Truncating the manual removes the very content needed to answer many questions, which increases rather than decreases unsupported answers. It also guarantees that legitimate questions about later sections will be answered from general knowledge or refused, so it fails the requirement.
- ✗
Move the customer question to the top of the prompt so Claude reads the question before the manual.
Why it's wrong here
Reordering changes what the model attends to first but does not create an evidentiary requirement. Claude can still answer from general knowledge after reading the manual, so this reordering alone does not stop the unsupported answers the developer is seeing.
- ✗
Add the sentence 'Be accurate and do not hallucinate' to the end of the prompt.
Why it's wrong here
A generic accuracy instruction gives the model no procedural step and no permitted fallback, so it does not change behavior when the manual lacks an answer. The model still has no mechanism to distinguish supported from unsupported claims, so competing-product knowledge can still surface.
- ✓
Instruct Claude to quote the relevant manual passage before answering, and to reply 'not covered' if no passage supports the answer.
Why this is correct
Requiring a supporting quote before the answer forces the model to locate evidence in the manual, and the explicit 'not covered' escape hatch gives it a legitimate response when evidence is absent. This directly reduces answers drawn from general knowledge about competing products.
About these practice questions
Courseiva writes every CCDV-F question from scratch — 257 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.