A developer is designing a prompt for a customer support chatbot. They want to ensure the model does not provide harmful or inappropriate responses. Which best practice should they apply?

Use a longer context to overwhelm the model with information

Remove all instructions to avoid confusing the model

Add guardrails that specify boundaries and safe responses

Increase the temperature to the maximum to get varied responses

A company is building a customer-facing chatbot that answers questions from a knowledge base. They are concerned about prompt injection attacks where users try to make the chatbot reveal system prompts or ignore instructions. They want to mitigate this risk while maintaining response quality. Which combination of measures is most effective?

Add a negative prompt telling the model not to reveal system prompts and use a stronger model

Use a longer system prompt with more detailed instructions

Use input validation to filter out suspicious prompts and add a system prompt that emphasizes following only the provided context

Disable the chatbot's ability to process user input

AWSCertified AI Practitioner

Domain 3Objective 2

Task Statement 3.2: Choose Effective Prompt Engineering Techniques. AIF-C01 Practice Questions (Page 3)

Part of the Content Domain 3: Applications of Foundation Models domain, which makes up ~32% of our current practice bank. AWS does not publish an official question count, but from its 90-minute exam (~35–60 total, ~11–19 in this domain), expect 3–5 from this objective — we provide 20 practice questions to prepare you well beyond it. (estimate)

20questions here

4free pages

5concepts

Questions 11–15

11foundation · easy
A developer is designing a prompt for a customer support chatbot. They want to ensure the model does not provide harmful or inappropriate responses. Which best practice should they apply?
Select an answer first
12foundation · easy
A developer wants the model to solve a math word problem. They add the instruction 'Think step by step before giving the final answer.' Which prompt engineering technique is this?
Select an answer first
13foundation · easy
An attacker inserts hidden instructions into a prompt that cause the model to output sensitive data from its training set. Which risk is this an example of?
Select an answer first
14foundation · easy
A malicious user crafts a prompt that causes a model to ignore its safety instructions and reveal confidential information. Which risk is this an example of?
Select an answer first
15expert · hard
A company is building a customer-facing chatbot that answers questions from a knowledge base. They are concerned about prompt injection attacks where users try to make the chatbot reveal system prompts or ignore instructions. They want to mitigate this risk while maintaining response quality. Which combination of measures is most effective?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AIF-C01

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by AWS. “AIF-C01” is a trademark of its owner, used for identification only.

Task Statement 3.2: Choose Effective Prompt Engineering Techniques. AIF-C01 Practice Questions (Page 3)

Questions 11–15

A developer is designing a prompt for a customer support chatbot. They want to ensure the model does not provide harmful or inappropriate responses. Which best practice should they apply?

A developer wants the model to solve a math word problem. They add the instruction 'Think step by step before giving the final answer.' Which prompt engineering technique is this?

An attacker inserts hidden instructions into a prompt that cause the model to output sensitive data from its training set. Which risk is this an example of?

A malicious user crafts a prompt that causes a model to ignore its safety instructions and reveal confidential information. Which risk is this an example of?

Keep studying — Content Domain 3: Applications of Foundation Models