CCDV-F Prompt and Context Engineering Practice Question
A developer is designing a prompt that asks Claude to extract action items from meeting transcripts. The transcripts are noisy, with overlapping speakers and side conversations. Which TWO prompt-engineering practices will most improve the reliability of the extracted action items? (Choose two.)
⚠ Common exam trap
The trap here is treating a larger output budget or fewer input tokens as a quality improvement, when the real levers are demonstration and structured reasoning.
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 the model to think step by step internally before emitting the final list, then output only the list.
Few-shot examples anchor the noisy-input-to-clean-output mapping, and asking for internal reasoning before the final list lets the model resolve attribution and filter side talk. Together they address the two hard parts of this task: deciding what counts as an action item and deciding who owns it. Output limits and label removal do not improve either decision.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Instruct the model to think step by step internally before emitting the final list, then output only the list.
Why this is correct
Asking for internal reasoning before the final answer improves extraction on noisy inputs because the model can resolve speaker attribution and filter side talk before committing to items. Emitting only the final list keeps the output clean for downstream parsing while still benefiting from the reasoning step.
- ✗
Remove all speaker labels to reduce token count before sending the transcript.
Why it's wrong here
Speaker labels are the primary signal for attributing an action item to an owner. Stripping them saves a small number of tokens but makes correct attribution nearly impossible, which is the core failure mode in overlapping-speaker transcripts. Token savings here trade away the exact information the task depends on.
- ✗
Set the max_tokens parameter as high as possible so the model never truncates an action item.
Why it's wrong here
A high max_tokens ceiling prevents truncation but does nothing to improve extraction quality. If the model misattributes a speaker or includes a side conversation, a larger budget simply gives it more room to produce wrong items. Output length limits are a safety net, not a reliability technique.
- ✗
Ask the model to include every sentence that mentions a task, regardless of who said it.
Why it's wrong here
This instruction directly undermines the goal by pulling in hypotheticals, jokes, and side conversations. Action items require attribution and commitment, not mere mention. Broadening the inclusion criterion increases false positives and makes the output unusable for task tracking.
- ✓
Provide two or three few-shot examples showing a noisy transcript snippet and the exact action-item output expected.
Why this is correct
Few-shot examples demonstrate the mapping from messy input to clean output, including how to ignore side conversations. They teach the model the desired granularity and format far more effectively than a prose description alone, especially when the input distribution is noisy and the output schema is specific.
Visual reference
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.