mediumMultiple Choice
AIF-C01 Practice Question: A team is using a prompt engineering technique…
A team is using a prompt engineering technique where they provide a few examples of desired input-output pairs in the prompt to guide the model's response. Which technique are they using?
⚠ Common exam trap
The AWS AI Practitioner exam often tests the distinction between few-shot and zero-shot prompting, where candidates mistakenly think that providing any instruction (like a system prompt) counts as a 'shot,' but the key is the explicit inclusion of input-output pairs as examples.
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
✓
Few-shot prompting
Few-shot prompting (Option C) is the correct technique because it involves providing a small number of input-output examples within the prompt to condition the model on the desired task format and pattern. This approach helps the model generalize from the examples to produce accurate responses for new inputs, without requiring fine-tuning.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
System prompting
Why it's wrong here
System prompting sets the model's overall role, tone and behavioural constraints; it does not supply worked input-output pairs. The described technique is few-shot prompting, where examples demonstrate the desired mapping. System prompts are correctly used to establish persona or guardrails, but they cannot teach a task format through demonstration the way embedded examples do.
- ✗
Zero-shot prompting
Why it's wrong here
Zero-shot prompting supplies instructions with no examples at all, so it cannot be the technique providing input-output pairs. Few-shot prompting is the correct term for embedding demonstrations in the prompt. Zero-shot is genuinely chosen when the task is simple or common enough that the model performs it from instructions alone, without needing exemplars.
- ✓
Few-shot prompting
Why this is correct
Supplying labelled input-output pairs directly in the prompt conditions the model on the desired pattern without weight updates, which is precisely few-shot prompting. This satisfies the stem's constraint of guiding responses through in-context examples rather than fine-tuning or zero-shot instruction.
- ✗
Chain-of-thought prompting
Why it's wrong here
Chain-of-thought prompting asks the model to reason step by step, typically via phrases like "think through this", not to imitate supplied input-output pairs. It is tempting because it also structures prompts and improves accuracy on arithmetic, logic and multi-step reasoning tasks where intermediate steps matter.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services 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 AIF-C01 exam.