Which Prompt Technique Asks the Model to Show Its Work Step by Step?

Prompt Engineering on Amazon Bedrock

An AI practitioner is developing a prompt for an Amazon Titan model. The model is hosted on Amazon Bedrock. The AI practitioner is using the model to solve numerical reasoning challenges. The AI practitioner adds the following phrase to the end of the prompt: “Ask the model to show its work by explaining its reasoning step by step.” Which prompt engineering technique is the AI practitioner using?

  1. Chain-of-thought prompting Source Reference Answer
  2. Prompt injection
  3. Few-shot prompting
  4. Prompt templating

Community Votes

A
100%

100% of anonymous learners picked answer A. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

The test checks your ability to identify chain-of-thought prompting by its signature request for step-by-step reasoning; the trap is confusing it with few-shot prompting, which uses examples.

Learn how asking an Amazon Titan model on Bedrock to 'show its work' exemplifies chain-of-thought prompting, a key technique for numerical reasoning. Community consensus strongly confirms option A.

Choosing C. Few-shot prompting, because the phrase 'show its work' might sound like providing an example, but it actually asks for intermediate reasoning steps, not examples in the prompt.

Community Discussion (4 comments)

kopper2019 👍 2 Selected: A
A. Chain-of-thought prompting step by step
Jessiii 👍 1 Selected: A
This technique encourages the model to reason through a problem step by step, which is exactly what the AI practitioner is doing by asking the model to "show its work by explaining its reasoning step by step."
ajey255 👍 1 Selected: A
CoT prompting involves structuring prompts so that the LLM breaks down complex problems into a series of logical, intermediate steps, similar to how a human would when thinking through a problem.
chris_spencer 👍 1 Selected: A
Chain-of-thought prompting Chain-of-thought prompting improves the reasoning ability of large language models by prompting them to generate a series of intermediate steps that lead to the final answer of a multi-step problem.

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

Submitted for moderation before publishing. Keep it helpful and respectful.

Expert Analysis

Why the Answer Is Correct

Chain-of-thought (CoT) prompting explicitly instructs the model to produce intermediate reasoning steps before the final answer. The phrase "show its work by explaining its reasoning step by step" is a textbook example of CoT. This technique is well-suited for numerical reasoning challenges because it encourages the model to break down the problem logically. Community comment [2] directly states that this approach "encourages the model to reason through a problem step by step," confirming the correct option.

Why the Other Options Are Wrong

Prompt injection (B) is a security exploit where malicious instructions are inserted into a prompt, not a benign reasoning technique. Few-shot prompting (C) involves providing labeled examples in the prompt, not asking for step-by-step reasoning. Prompt templating (D) refers to reusing parameterized prompt structures, not the explicit instruction to explain reasoning. The description in the question matches none of these other techniques.

Community Comment Notes

All community votes (100%) selected A, showing unanimous consensus. Comments [3] and [4] add valuable context: CoT prompts structure the model's output as a series of logical intermediate steps, improving multi-step problem-solving. Comment [1] simply reinforces the answer with "step by step." These insights align with the official AWS documentation on prompt engineering.

Official Reference

https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-engineering-guidelines.html

Exam Strategy

Remember that chain-of-thought prompting is identified by explicit requests for step-by-step reasoning, such as "show your work" or "think step by step." Focus on the purpose of the prompt: whether it adds examples (few-shot) or asks for reasoning steps (chain-of-thought).

Related Analysis

A company wants to use large language models (LLMs) to produ

A-Grade

A company makes forecasts each quarter to decide how to opti

A-Grade

An ML research team develops custom ML models. The model art

A-Grade

Practice All AIF-C01 Questions

Access 100 questions with complete answers and detailed explanations.

View Full AIF-C01 Practice Test →

← Back to AIF-C01 Study Guide