Amazon AWS Certified AI Practitioner AIF-C01 Practice Test 98

Question 970

An industrial maintenance proof of concept is intended to reduce unsupported answers by providing approved source documents at inference. Which concept is most applicable to the stated goal?

  1. Dataset lineage
  2. Data checksum verification
  3. RAG factual grounding
  4. Data cataloging

Explanation

Correct Answer

C:

This is the choice aligned with the industrial maintenance requirement to reduce unsupported answers by providing approved source documents at inference: grounding gives the model retrieved evidence relevant to the question. A realistic pilot must still check the qualification that retrieving a passage does not assure that every sentence in the response is correct, especially where that could affect the acceptance criterion.

Incorrect Answers

A:

For the industrial maintenance objective to reduce unsupported answers by providing approved source documents at inference, Dataset lineage addresses a different task—explain which source and transformation produced a feature used in evaluation. Its operating mechanism differs from that of RAG factual grounding: lineage records the path from original data through processing to model use; this does not satisfy the requested outcome.

B:

For the industrial maintenance objective to reduce unsupported answers by providing approved source documents at inference, Data checksum verification addresses a different task—detect unexpected changes to model-training objects during transfer. Its operating mechanism differs from that of RAG factual grounding: checksums provide an integrity signal when expected hashes match the received object; this does not satisfy the requested outcome.

D:

For the industrial maintenance objective to reduce unsupported answers by providing approved source documents at inference, Data cataloging addresses a different task—help data owners find the approved source and owner of each dataset. Its operating mechanism differs from that of RAG factual grounding: a catalog records metadata, ownership and classification of data assets; this does not satisfy the requested outcome.

Question 971

The travel services acceptance criterion is to establish private connectivity from an application VPC to supported AWS services. Which of these choices should be shortlisted first?

  1. AWS PrivateLink
  2. Amazon VPC network isolation
  3. Output validation
  4. IAM least privilege

Explanation

Correct Answer

A:

This is the choice aligned with the travel services requirement to establish private connectivity from an application VPC to supported AWS services: privateLink uses private endpoint connectivity without requiring public internet traversal. A realistic pilot must still check the qualification that private transport does not replace service-level IAM authorization, especially where that could affect the acceptance criterion.

Incorrect Answers

B:

For the travel services objective to establish private connectivity from an application VPC to supported AWS services, Amazon VPC network isolation addresses a different task—segregate compute resources used by an internal AI system. Its operating mechanism differs from that of AWS PrivateLink: vPC networking controls subnets, routing and network exposure for workloads; this does not satisfy the requested outcome.

C:

For the travel services objective to establish private connectivity from an application VPC to supported AWS services, Output validation addresses a different task—block model-generated fields that break a permitted-data schema. Its operating mechanism differs from that of AWS PrivateLink: output validation checks generated data against field rules before downstream use; this does not satisfy the requested outcome.

D:

For the travel services objective to establish private connectivity from an application VPC to supported AWS services, IAM least privilege addresses a different task—limit an application's Bedrock model calls to only necessary AWS permissions. Its operating mechanism differs from that of AWS PrivateLink: IAM permissions authorize specific service actions and resources for a principal; this does not satisfy the requested outcome.

Question 972

A public-sector support team must confirm that evidence used in an answer comes from an approved current policy source. Which listed concept or AWS capability directly matches that requirement?

  1. Data cataloging
  2. Confidence-based escalation
  3. Document provenance checks
  4. Dataset lineage

Explanation

Correct Answer

C:

This is the choice aligned with the public-sector support requirement to confirm that evidence used in an answer comes from an approved current policy source: provenance metadata identifies author, revision and authorized origin of documents. A realistic pilot must still check the qualification that the most semantically similar paragraph might be an obsolete or unauthorized copy, especially where that could affect the acceptance criterion.

Incorrect Answers

A:

For the public-sector support objective to confirm that evidence used in an answer comes from an approved current policy source, Data cataloging addresses a different task—help data owners find the approved source and owner of each dataset. Its operating mechanism differs from that of Document provenance checks: a catalog records metadata, ownership and classification of data assets; this does not satisfy the requested outcome.

B:

For the public-sector support objective to confirm that evidence used in an answer comes from an approved current policy source, Confidence-based escalation addresses a different task—send uncertain model recommendations to review instead of acting automatically. Its operating mechanism differs from that of Document provenance checks: confidence thresholds and escalation rules reduce unattended decisions under uncertainty; this does not satisfy the requested outcome.

D:

For the public-sector support objective to confirm that evidence used in an answer comes from an approved current policy source, Dataset lineage addresses a different task—explain which source and transformation produced a feature used in evaluation. Its operating mechanism differs from that of Document provenance checks: lineage records the path from original data through processing to model use; this does not satisfy the requested outcome.

Question 973

A new healthcare administration initiative has one measurable requirement: protect stored embeddings and documents against exposure of underlying storage media. What should the team select?

  1. AWS KMS encryption
  2. Confidence-based escalation
  3. PII minimization
  4. Encryption at rest
  5. Encryption in transit

Explanation

Correct Answer

D:

This is the choice aligned with the healthcare administration requirement to protect stored embeddings and documents against exposure of underlying storage media: at-rest encryption protects persisted data with managed cryptographic controls. A realistic pilot must still check the qualification that encrypted storage cannot prevent data leakage by an already-authorized application, especially where that could affect the acceptance criterion.

Incorrect Answers

A:

For the healthcare administration objective to protect stored embeddings and documents against exposure of underlying storage media, AWS KMS encryption addresses a different task—manage encryption keys protecting customer documents stored for an AI workflow. Its operating mechanism differs from that of Encryption at rest: AWS KMS helps create and control cryptographic keys used by AWS encryption features; this does not satisfy the requested outcome.

B:

For the healthcare administration objective to protect stored embeddings and documents against exposure of underlying storage media, Confidence-based escalation addresses a different task—send uncertain model recommendations to review instead of acting automatically. Its operating mechanism differs from that of Encryption at rest: confidence thresholds and escalation rules reduce unattended decisions under uncertainty; this does not satisfy the requested outcome.

C:

For the healthcare administration objective to protect stored embeddings and documents against exposure of underlying storage media, PII minimization addresses a different task—avoid sending unneeded customer identifiers to a third-party tool. Its operating mechanism differs from that of Encryption at rest: data minimization removes unnecessary personal information before processing; this does not satisfy the requested outcome.

E:

For the healthcare administration objective to protect stored embeddings and documents against exposure of underlying storage media, Encryption in transit addresses a different task—protect a customer's prompt while it travels between client and service. Its operating mechanism differs from that of Encryption at rest: tLS encrypts network communications and helps prevent interception in transit; this does not satisfy the requested outcome.

Question 974

In telecommunications, the planned workflow needs to avoid sending unneeded customer identifiers to a third-party tool. Which option is aligned with this outcome?

  1. Data leakage prevention
  2. Output validation
  3. PII minimization
  4. Amazon Macie

Explanation

Correct Answer

C:

This is the choice aligned with the telecommunications requirement to avoid sending unneeded customer identifiers to a third-party tool: data minimization removes unnecessary personal information before processing. A realistic pilot must still check the qualification that masking user-facing results alone cannot undo excess data transmitted upstream, especially where that could affect the acceptance criterion.

Incorrect Answers

A:

For the telecommunications objective to avoid sending unneeded customer identifiers to a third-party tool, Data leakage prevention addresses a different task—prevent a helpdesk assistant from disclosing restricted customer records. Its operating mechanism differs from that of PII minimization: combine permission-scoped retrieval, output checking and monitored tool access; this does not satisfy the requested outcome.

B:

For the telecommunications objective to avoid sending unneeded customer identifiers to a third-party tool, Output validation addresses a different task—block model-generated fields that break a permitted-data schema. Its operating mechanism differs from that of PII minimization: output validation checks generated data against field rules before downstream use; this does not satisfy the requested outcome.

D:

For the telecommunications objective to avoid sending unneeded customer identifiers to a third-party tool, Amazon Macie addresses a different task—discover potentially sensitive customer information stored in Amazon S3. Its operating mechanism differs from that of PII minimization: Macie analyzes S3 data to identify sensitive information and related risks; this does not satisfy the requested outcome.

Question 975

A stakeholder in customer operations asks how to send uncertain model recommendations to review instead of acting automatically. Which of the listed approaches fits that request?

  1. Dataset lineage
  2. Data cataloging
  3. Confidence-based escalation
  4. Document provenance checks

Explanation

Correct Answer

C:

This is the choice aligned with the customer operations requirement to send uncertain model recommendations to review instead of acting automatically: confidence thresholds and escalation rules reduce unattended decisions under uncertainty. A realistic pilot must still check the qualification that a self-reported confidence number needs calibration and does not prove accuracy, especially where that could affect the acceptance criterion.

Incorrect Answers

A:

For the customer operations objective to send uncertain model recommendations to review instead of acting automatically, Dataset lineage addresses a different task—explain which source and transformation produced a feature used in evaluation. Its operating mechanism differs from that of Confidence-based escalation: lineage records the path from original data through processing to model use; this does not satisfy the requested outcome.

B:

For the customer operations objective to send uncertain model recommendations to review instead of acting automatically, Data cataloging addresses a different task—help data owners find the approved source and owner of each dataset. Its operating mechanism differs from that of Confidence-based escalation: a catalog records metadata, ownership and classification of data assets; this does not satisfy the requested outcome.

D:

For the customer operations objective to send uncertain model recommendations to review instead of acting automatically, Document provenance checks addresses a different task—confirm that evidence used in an answer comes from an approved current policy source. Its operating mechanism differs from that of Confidence-based escalation: provenance metadata identifies author, revision and authorized origin of documents; this does not satisfy the requested outcome.

Question 976

A professional-services prototype calls for Prompt injection defense to keep a retrieved page from issuing unauthorized instructions to an assistant. Which description would accurately document the method?

  1. An approval checkpoint prevents high-impact tool invocations without explicit authorization.
  2. Audit logs retain identity, time, operation and relevant trace information under privacy rules.
  3. CloudWatch collects metrics and operational logs for supported services and applications.
  4. Vulnerability assessments and patching reduce exposure in software dependencies.
  5. Treat retrieved text as untrusted data and constrain tool actions with external checks.

Explanation

Correct Answer

E:

For the proposed professional-services use, the key operating principle is that treat retrieved text as untrusted data and constrain tool actions with external checks; that mechanism is what enables Prompt injection defense to keep a retrieved page from issuing unauthorized instructions to an assistant. The technical limitation—placing raw web content into a model prompt does not make it a trusted command—needs a separate check.

Incorrect Answers

A:

In this professional-services question about Prompt injection defense, the statement instead characterizes Tool-action approval gate: an approval checkpoint prevents high-impact tool invocations without explicit authorization. That can support a goal to require a person to confirm that an assistant may transfer funds or delete records, but does not explain the operation required for Prompt injection defense to keep a retrieved page from issuing unauthorized instructions to an assistant.

B:

In this professional-services question about Prompt injection defense, the statement instead characterizes Prompt and response audit trail: audit logs retain identity, time, operation and relevant trace information under privacy rules. That can support a goal to reconstruct which AI request and authorized tool call caused a disputed action, but does not explain the operation required for Prompt injection defense to keep a retrieved page from issuing unauthorized instructions to an assistant.

C:

In this professional-services question about Prompt injection defense, the statement instead characterizes Amazon CloudWatch monitoring: CloudWatch collects metrics and operational logs for supported services and applications. That can support a goal to observe model-backed application errors, latency and operating metrics, but does not explain the operation required for Prompt injection defense to keep a retrieved page from issuing unauthorized instructions to an assistant.

D:

In this professional-services question about Prompt injection defense, the statement instead characterizes Vulnerability management: vulnerability assessments and patching reduce exposure in software dependencies. That can support a goal to detect software flaws in infrastructure hosting an AI application, but does not explain the operation required for Prompt injection defense to keep a retrieved page from issuing unauthorized instructions to an assistant.

Question 977

To protect stored embeddings and documents against exposure of underlying storage media, an industrial maintenance project considers Encryption at rest. Which statement correctly describes its role?

  1. AWS KMS helps create and control cryptographic keys used by AWS encryption features.
  2. A catalog records metadata, ownership and classification of data assets.
  3. TLS encrypts network communications and helps prevent interception in transit.
  4. At-rest encryption protects persisted data with managed cryptographic controls.

Explanation

Correct Answer

D:

For the proposed industrial maintenance use, the key operating principle is that at-rest encryption protects persisted data with managed cryptographic controls; that mechanism is what enables Encryption at rest to protect stored embeddings and documents against exposure of underlying storage media. The technical limitation—encrypted storage cannot prevent data leakage by an already-authorized application—needs a separate check.

Incorrect Answers

A:

In this industrial maintenance question about Encryption at rest, the statement instead characterizes AWS KMS encryption: AWS KMS helps create and control cryptographic keys used by AWS encryption features. That can support a goal to manage encryption keys protecting customer documents stored for an AI workflow, but does not explain the operation required for Encryption at rest to protect stored embeddings and documents against exposure of underlying storage media.

B:

In this industrial maintenance question about Encryption at rest, the statement instead characterizes Data cataloging: a catalog records metadata, ownership and classification of data assets. That can support a goal to help data owners find the approved source and owner of each dataset, but does not explain the operation required for Encryption at rest to protect stored embeddings and documents against exposure of underlying storage media.

C:

In this industrial maintenance question about Encryption at rest, the statement instead characterizes Encryption in transit: tLS encrypts network communications and helps prevent interception in transit. That can support a goal to protect a customer's prompt while it travels between client and service, but does not explain the operation required for Encryption at rest to protect stored embeddings and documents against exposure of underlying storage media.

Question 978

The media publishing team is reviewing how Output validation works in a plan to block model-generated fields that break a permitted-data schema. Which statement gives the correct mechanism?

  1. Guardrails can help filter harmful content and sensitive information under configured policies.
  2. Combine permission-scoped retrieval, output checking and monitored tool access.
  3. Output validation checks generated data against field rules before downstream use.
  4. Macie analyzes S3 data to identify sensitive information and related risks.

Explanation

Correct Answer

C:

For the proposed media publishing use, the key operating principle is that output validation checks generated data against field rules before downstream use; that mechanism is what enables Output validation to block model-generated fields that break a permitted-data schema. The technical limitation—a well-formed output can still contain an unsupported claim requiring factual review—needs a separate check.

Incorrect Answers

A:

In this media publishing question about Output validation, the statement instead characterizes Amazon Bedrock Guardrails: guardrails can help filter harmful content and sensitive information under configured policies. That can support a goal to apply managed safety filters to inputs and outputs in a GenAI application, but does not explain the operation required for Output validation to block model-generated fields that break a permitted-data schema.

B:

In this media publishing question about Output validation, the statement instead characterizes Data leakage prevention: combine permission-scoped retrieval, output checking and monitored tool access. That can support a goal to prevent a helpdesk assistant from disclosing restricted customer records, but does not explain the operation required for Output validation to block model-generated fields that break a permitted-data schema.

D:

In this media publishing question about Output validation, the statement instead characterizes Amazon Macie: Macie analyzes S3 data to identify sensitive information and related risks. That can support a goal to discover potentially sensitive customer information stored in Amazon S3, but does not explain the operation required for Output validation to block model-generated fields that break a permitted-data schema.

Question 979

Which explanation correctly describes Resource-based policy when a healthcare administration project needs to control which AWS principals can read a sensitive data bucket used for retrieval?

  1. A resource policy can specify allowed principals and access conditions.
  2. Separate roles and approval responsibilities reduce unilateral unauthorized changes.
  3. An IAM role provides temporary credentials to trusted AWS service workloads.
  4. AgentCore Identity helps agents use managed identity and credentials for authorized connections.

Explanation

Correct Answer

A:

For the proposed healthcare administration use, the key operating principle is that a resource policy can specify allowed principals and access conditions; that mechanism is what enables Resource-based policy to control which AWS principals can read a sensitive data bucket used for retrieval. The technical limitation—allowing an application role does not automatically open a resource to everyone—needs a separate check.

Incorrect Answers

B:

In this healthcare administration question about Resource-based policy, the statement instead characterizes Separation of duties: separate roles and approval responsibilities reduce unilateral unauthorized changes. That can support a goal to require a different employee to approve a high-risk AI production deployment, but does not explain the operation required for Resource-based policy to control which AWS principals can read a sensitive data bucket used for retrieval.

C:

In this healthcare administration question about Resource-based policy, the statement instead characterizes IAM role for workloads: an IAM role provides temporary credentials to trusted AWS service workloads. That can support a goal to let a managed workload access AI-related AWS resources without embedded long-term keys, but does not explain the operation required for Resource-based policy to control which AWS principals can read a sensitive data bucket used for retrieval.

D:

In this healthcare administration question about Resource-based policy, the statement instead characterizes Amazon Bedrock AgentCore Identity: AgentCore Identity helps agents use managed identity and credentials for authorized connections. That can support a goal to manage agent authentication and delegated access to external resources, but does not explain the operation required for Resource-based policy to control which AWS principals can read a sensitive data bucket used for retrieval.

Question 980

A media publishing design uses AWS Secrets Manager in order to store and rotate third-party API credentials used by an AI agent. Which technical description is accurate?

  1. IAM permissions authorize specific service actions and resources for a principal.
  2. AgentCore Policy supports policy-based enforcement of agent actions.
  3. Separate roles and approval responsibilities reduce unilateral unauthorized changes.
  4. Secrets Manager provides managed secret storage and rotation integration.

Explanation

Correct Answer

D:

For the proposed media publishing use, the key operating principle is that secrets Manager provides managed secret storage and rotation integration; that mechanism is what enables AWS Secrets Manager to store and rotate third-party API credentials used by an AI agent. The technical limitation—placing credentials in a prompt or document risks their exposure to the model context—needs a separate check.

Incorrect Answers

A:

In this media publishing question about AWS Secrets Manager, the statement instead characterizes IAM least privilege: IAM permissions authorize specific service actions and resources for a principal. That can support a goal to limit an application's Bedrock model calls to only necessary AWS permissions, but does not explain the operation required for AWS Secrets Manager to store and rotate third-party API credentials used by an AI agent.

B:

In this media publishing question about AWS Secrets Manager, the statement instead characterizes AgentCore Policy: AgentCore Policy supports policy-based enforcement of agent actions. That can support a goal to limit tool actions that an AI agent is allowed to perform, but does not explain the operation required for AWS Secrets Manager to store and rotate third-party API credentials used by an AI agent.

C:

In this media publishing question about AWS Secrets Manager, the statement instead characterizes Separation of duties: separate roles and approval responsibilities reduce unilateral unauthorized changes. That can support a goal to require a different employee to approve a high-risk AI production deployment, but does not explain the operation required for AWS Secrets Manager to store and rotate third-party API credentials used by an AI agent.

AWS Certified AI Practitioner AIF-C01 Practice Tests