AIF-C01 Fundamentals of Generative AI Practice Question

Exhibit

Refer to the exhibit.
```yaml
Resources:
  MyGuardrail:
    Type: AWS::Bedrock::Guardrail
    Properties:
      Name: my-guardrail
      TopicPolicy:
        Topics:
          - Name: sensitive-topic
            Definition: "Do not discuss sensitive topics."
            Type: DENY
      ContentPolicy:
        Filters:
          - Type: SEXUAL
            InputStrength: HIGH
            OutputStrength: HIGH
```

A developer deployed this guardrail to block sensitive topics and sexual content. However, the model still generates responses about a specific sensitive topic that is not in the TopicPolicy. What should the developer do to prevent this?

⚠ Common exam trap

AWS often tests the distinction between guardrail components—candidates may confuse content filters (which handle broad harmful categories) with topic policies (which handle custom, specific topics) and incorrectly choose to adjust content filter strength instead of updating the topic list.

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

✓

Add the specific topic to the TopicPolicy list

The guardrail's TopicPolicy is designed to block specific topics by listing them. Since the model is generating responses about a sensitive topic not currently in the policy, adding that topic to the list directly extends the policy's coverage to prevent those responses. This is the precise mechanism for blocking new unwanted topics without altering other guardrail components.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Add a SensitiveInformationPolicy to filter PII
Why it's wrong here
A SensitiveInformationPolicy filters personally identifiable information such as names and addresses, not arbitrary sensitive topics. It is tempting because it adds another guardrail layer, but the unlisted topic must be defined in the TopicPolicy for the guardrail to block those responses.
✗
Increase the InputStrength of the content filter to MAX
Why it's wrong here
InputStrength governs filtering of prompts, so raising it to MAX does not block the model's generated output about an unlisted topic. It is tempting because it hardens the filter, but the missing topic must be added to the TopicPolicy so the guardrail recognises and blocks it.
✗
Change the TopicPolicy Type from DENY to ALLOW
Why it's wrong here
Flipping the TopicPolicy Type to ALLOW permits the sensitive topic rather than blocking it, since DENY is what filters content. ALLOW is used when a topic should be explicitly permitted despite broader filters, so it cannot suppress the unlisted topic the model still discusses.
✓
Add the specific topic to the TopicPolicy list
Why this is correct
The guardrail only blocks topics enumerated in TopicPolicy, so an unlisted sensitive topic passes through unfiltered. Adding that specific topic to the policy list makes the filter match it, directly closing the gap without altering model weights or prompts.

Go deeper

AIF-C01 Fundamentals of Generative AI Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question