AWS Bedrock Guardrails and SCP Governance Strategy

AIP-C01 By islever Editorial Last updated

Implement input and output safety controls. Implement AI governance and compliance mechanisms. Implement FM API integrations.

Short answer

BD Use an SCP to enforce approved models and mandatory guardrail identifiers, and deploy a block-filtering guardrail via CloudFormation StackSets to prevent prohibited content.

Question

A company uses an organization in AWS Organizations with all features enabled to manage multiple AWS accounts. Employees use Amazon Bedrock across multiple accounts. The company must prevent specific topics and proprietary information from being included in prompts to Amazon Bedrock models. The company must ensure that employees can use only approved Amazon Bedrock models. The company centrally manages IAM roles for employees.
Which combination of solutions will meet these requirements? (Choose two.)
  1. Create an IAM permissions boundary for each employee's IAM role. Configure the permissions boundary to require an approved Amazon Bedrock guardrail identifier to invoke Amazon Bedrock models. Create an SCP that allows employees to use only approved models.
  2. Create an SCP that allows employees to use only approved models. Configure the SCP to require employees to specify a guardrail identifier in calls to invoke an approved model. Correct Answer
  3. Create an SCP that prevents an employee from invoking a model if a centrally deployed guardrail identifier is not specified in a call to the model. Create a permissions boundary on each employee's IAM role that allows each employee to invoke only approved models.
  4. Use AWS CloudFormation to create a custom Amazon Bedrock guardrail that has a block filtering policy. Use stack sets to deploy the guardrail to each account in the organization. Correct Answer
  5. Use AWS CloudFormation to create a custom Amazon Bedrock guardrail that has a mask filtering policy. Use stack sets to deploy the guardrail to each account in the organization.

Key Takeaways

The main trap is confusing 'Block' and 'Mask' filtering policies; only Block prevents content inclusion, while Mask only redacts it.

This page explains how to secure Amazon Bedrock in an AWS Organization by combining SCPs for access control with Block Filtering Guardrails for content safety.

Common mistake: Candidates often choose Option E because masking seems like a good privacy tool, but it fails the 'prevent' requirement. Others choose A or C due to familiarity with IAM boundaries, ignoring the scalability and central enforcement power of SCPs in an Organization.

Expert Analysis

The question requires a multi-select solution (two options) that addresses two distinct security requirements in an AWS Organizations environment: preventing specific topics/proprietary info in prompts and restricting usage to approved Amazon Bedrock models.

First, consider the requirement to prevent specific topics and proprietary information. This is a content safety control. Amazon Bedrock Guardrails provide this via filtering policies. A Block filtering policy explicitly denies requests containing prohibited content, which directly satisfies the "prevent" requirement. In contrast, a Mask filtering policy (Option E) only redacts sensitive data (like PII) but still allows the request to proceed, failing to prevent the inclusion of the information entirely. Therefore, Option D (using a Block filtering policy deployed via StackSets for consistency) is correct, while Option E is incorrect.

Second, consider the requirement to ensure employees use only approved models and centrally manage IAM roles. While Permissions Boundaries (Options A and C) can restrict actions, they are applied per role and do not natively enforce the specification of a guardrail identifier in the API call itself as effectively as an SCP in this context. More critically, AWS best practices for centralized governance in an organization recommend using Service Control Policies (SCPs) at the OU or account level to enforce organizational standards. An SCP can be configured to deny access to Bedrock models unless specific conditions are met, such as the presence of a required tag or parameter (like a guardrail ID). Option B correctly describes an SCP that enforces model approval and mandates the guardrail identifier. Option C suggests using an SCP to prevent invocation if a guardrail is missing, but pairs it with a permissions boundary; however, the combination in Option B is the standard centralized pattern for enforcing both model selection and guardrail usage centrally without managing individual role boundaries across multiple accounts. The comments highlight that SCPs are the scalable method for central governance, making B superior to A/C for the "centrally managed" aspect.

Thus, the correct combination is B for the access/guardrail enforcement policy and D for the actual deployment of the blocking guardrail.

Official Reference

These links open the official vendor documentation in a new tab.

Exam Strategy

When designing governance solutions for multi-account environments, prioritize Service Control Policies (SCPs) over individual IAM configurations for centralized enforcement. Always distinguish between 'prevention' (Block) and 'mitigation/redaction' (Mask) when evaluating content safety controls. For multi-select questions, ensure each option addresses a distinct part of the requirement set.

Frequently Asked Questions

What is the difference between Block and Mask filtering in Bedrock Guardrails?

Block filtering denies the entire request if prohibited content is detected, effectively preventing the output. Mask filtering identifies sensitive data (like PII) and replaces it with placeholders, but the request is still processed.

Why are SCPs preferred over IAM Permissions Boundaries here?

SCPs provide centralized control across all accounts in an AWS Organization, ensuring consistent policy enforcement regardless of individual account IAM settings. They are more scalable for multi-account governance than managing boundaries on every role.

More AIP-C01 FAQ →

Community Votes

D
54%
B
38%
A
8%

54% of anonymous learners picked answer D. Votes are pick records left by other test-takers — they are not the verified answer.

Discussion 7 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 7

  1. Kraftzman 👍 2
    Why the other options are incorrect: A & C (Permissions Boundaries): While Permissions Boundaries can restrict what a user can do, they must be applied to each IAM role individually. In a multi-account environment where you already have AWS Organizations, SCPs are the more scalable and standard method for central governance. E (Masking Policy): As mentioned, masking is better for PII redaction in responses. Blocking is the appropriate mechanism for enforcing company policy on what can be sent to the model.
  2. eesa 👍 2
    Simplicidad: Un mecanismo (SCP) vs dos (SCP + Boundary) Best practice AWS: SCP para controles organizacionales Menor overhead: No necesitas gestionar boundaries en cada rol
  3. GiorgioGss 👍 2
    "The company must prevent" - D because E only mask.
  4. xyztest 👍 2
    Correct Answer
  5. 953bf6d 👍 1
    The best choices are A and D, with a caveat: C also describes a technically viable enforcement pattern, making the question somewhat ambiguous. A: Enforce approved guardrails and approved models A supplies two permission controls: The employee role’s permissions boundary requires the approved guardrail, rather than allowing an arbitrary guardrail. Bedrock supports enforcing a specific guardrail through the bedrock:GuardrailIdentifier condition key. The SCP restricts model access to the company’s approved models. D: Create and deploy the blocking guardrails D supplies the actual content protection. Configure the guardrail with: Denied topics for prohibited subjects. Word filters or custom sensitive-information patterns for identifiable proprietary terms and information. CloudFormation supports these guardrail policies. Deploying the configuration across accounts provides the guardrails that A requires employees to use. Together: D creates the protection; A makes its use mandatory and restricts model access. Why not the others? B: Requires a guardrail identifier, not explicitly an approved guardrail identifier. Merely supplying any guardrail does not ensure the company’s required filters are applied. Specific-guardrail enforcement addresses that gap. C: Not inherently wrong. It reverses A’s placement of the controls: the SCP enforces the approved guardrail, while permissions boundaries restrict models. Properly implemented, C + D could also meet the requirements. The wording does not provide a strong technical reason to exclude it. E: Masking is not a replacement for blocking prohibited topics. Denied-topic policies return a blocked message when a prohibited topic is detected. Exam selection: A + D. Technical assessment: the overlap with C makes this an imperfect “choose two” question.
Show 2 more comments
  1. Chibuzo1 👍 1
    The answers are B and D because the SCP enforces both model approval and mandatory guardrail usage at the organization level, while CloudFormation StackSets deploys a consistent block-filtering guardrail across all accounts — together providing centralized, enforceable content governance and model access control across the entire AWS organization.
  2. 67bdb19 👍 1 Answered D
    Gotta say, D makes the most sense. It directly addresses the problem statement.

Reader comments & corrections

No reader corrections 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.

How Can AgentCore Query Cross-Account DynamoDB While Preserving User Identity?

S-grade

Which API Gateway setup streams Bedrock responses with least operational overhead?

S-grade

Resilient Retry and Streaming Strategies for Amazon Bedrock

S-grade

Bedrock Prompt Management & Guardrails Detection

S-grade

Practice All AIP-C01 Questions

Access 110 questions with complete answers and detailed explanations.

View Full AIP-C01 Practice Test →

← Back to AIP-C01 Study Guide