For the university services objective to help data owners find the approved source and owner of each dataset, RAG factual grounding addresses a different task—reduce unsupported answers by providing approved source documents at inference. Its operating mechanism differs from that of Data cataloging: grounding gives the model retrieved evidence relevant to the question; this does not satisfy the requested outcome.

For the university services objective to help data owners find the approved source and owner of each dataset, Data checksum verification addresses a different task—detect unexpected changes to model-training objects during transfer. Its operating mechanism differs from that of Data cataloging: checksums provide an integrity signal when expected hashes match the received object; this does not satisfy the requested outcome.

For the university services objective to help data owners find the approved source and owner of each dataset, 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 Data cataloging: provenance metadata identifies author, revision and authorized origin of documents; this does not satisfy the requested outcome.

For the industrial maintenance objective to apply managed safety filters to inputs and outputs in a GenAI application, Amazon Macie addresses a different task—discover potentially sensitive customer information stored in Amazon S3. Its operating mechanism differs from that of Amazon Bedrock Guardrails: Macie analyzes S3 data to identify sensitive information and related risks; this does not satisfy the requested outcome.

For the industrial maintenance objective to apply managed safety filters to inputs and outputs in a GenAI application, Data leakage prevention addresses a different task—prevent a helpdesk assistant from disclosing restricted customer records. Its operating mechanism differs from that of Amazon Bedrock Guardrails: combine permission-scoped retrieval, output checking and monitored tool access; this does not satisfy the requested outcome.

For the industrial maintenance objective to apply managed safety filters to inputs and outputs in a GenAI application, Output validation addresses a different task—block model-generated fields that break a permitted-data schema. Its operating mechanism differs from that of Amazon Bedrock Guardrails: output validation checks generated data against field rules before downstream use; this does not satisfy the requested outcome.

For the travel services objective to explain which source and transformation produced a feature used in evaluation, 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 Dataset lineage: a catalog records metadata, ownership and classification of data assets; this does not satisfy the requested outcome.

For the travel services objective to explain which source and transformation produced a feature used in evaluation, RAG factual grounding addresses a different task—reduce unsupported answers by providing approved source documents at inference. Its operating mechanism differs from that of Dataset lineage: grounding gives the model retrieved evidence relevant to the question; this does not satisfy the requested outcome.

For the travel services objective to explain which source and transformation produced a feature used in evaluation, Data checksum verification addresses a different task—detect unexpected changes to model-training objects during transfer. Its operating mechanism differs from that of Dataset lineage: checksums provide an integrity signal when expected hashes match the received object; this does not satisfy the requested outcome.

For the telecommunications objective to keep a retrieved page from issuing unauthorized instructions to an assistant, Tool-action approval gate addresses a different task—require a person to confirm that an assistant may transfer funds or delete records. Its operating mechanism differs from that of Prompt injection defense: an approval checkpoint prevents high-impact tool invocations without explicit authorization; this does not satisfy the requested outcome.

For the telecommunications objective to keep a retrieved page from issuing unauthorized instructions to an assistant, Prompt and response audit trail addresses a different task—reconstruct which AI request and authorized tool call caused a disputed action. Its operating mechanism differs from that of Prompt injection defense: audit logs retain identity, time, operation and relevant trace information under privacy rules; this does not satisfy the requested outcome.

For the telecommunications objective to keep a retrieved page from issuing unauthorized instructions to an assistant, Amazon CloudWatch monitoring addresses a different task—observe model-backed application errors, latency and operating metrics. Its operating mechanism differs from that of Prompt injection defense: CloudWatch collects metrics and operational logs for supported services and applications; this does not satisfy the requested outcome.

For the university services objective to limit an application's Bedrock model calls to only necessary AWS permissions, AWS Secrets Manager addresses a different task—store and rotate third-party API credentials used by an AI agent. Its operating mechanism differs from that of IAM least privilege: secrets Manager provides managed secret storage and rotation integration; this does not satisfy the requested outcome.

For the university services objective to limit an application's Bedrock model calls to only necessary AWS permissions, Amazon Bedrock AgentCore Identity addresses a different task—manage agent authentication and delegated access to external resources. Its operating mechanism differs from that of IAM least privilege: AgentCore Identity helps agents use managed identity and credentials for authorized connections; this does not satisfy the requested outcome.

For the university services objective to limit an application's Bedrock model calls to only necessary AWS permissions, AgentCore Policy addresses a different task—limit tool actions that an AI agent is allowed to perform. Its operating mechanism differs from that of IAM least privilege: AgentCore Policy supports policy-based enforcement of agent actions; this does not satisfy the requested outcome.

For the logistics objective to require a different employee to approve a high-risk AI production deployment, AgentCore Policy addresses a different task—limit tool actions that an AI agent is allowed to perform. Its operating mechanism differs from that of Separation of duties: AgentCore Policy supports policy-based enforcement of agent actions; this does not satisfy the requested outcome.

For the logistics objective to require a different employee to approve a high-risk AI production deployment, Amazon Bedrock AgentCore Identity addresses a different task—manage agent authentication and delegated access to external resources. Its operating mechanism differs from that of Separation of duties: AgentCore Identity helps agents use managed identity and credentials for authorized connections; this does not satisfy the requested outcome.

For the logistics objective to require a different employee to approve a high-risk AI production deployment, AWS Secrets Manager addresses a different task—store and rotate third-party API credentials used by an AI agent. Its operating mechanism differs from that of Separation of duties: secrets Manager provides managed secret storage and rotation integration; this does not satisfy the requested outcome.

For the customer operations objective to prevent a helpdesk assistant from disclosing restricted customer records, Amazon Macie addresses a different task—discover potentially sensitive customer information stored in Amazon S3. Its operating mechanism differs from that of Data leakage prevention: Macie analyzes S3 data to identify sensitive information and related risks; this does not satisfy the requested outcome.

For the customer operations objective to prevent a helpdesk assistant from disclosing restricted customer records, PII minimization addresses a different task—avoid sending unneeded customer identifiers to a third-party tool. Its operating mechanism differs from that of Data leakage prevention: data minimization removes unnecessary personal information before processing; this does not satisfy the requested outcome.

For the customer operations objective to prevent a helpdesk assistant from disclosing restricted customer records, Amazon Bedrock Guardrails addresses a different task—apply managed safety filters to inputs and outputs in a GenAI application. Its operating mechanism differs from that of Data leakage prevention: guardrails can help filter harmful content and sensitive information under configured policies; this does not satisfy the requested outcome.

For the customer operations objective to prevent a helpdesk assistant from disclosing restricted customer records, Output validation addresses a different task—block model-generated fields that break a permitted-data schema. Its operating mechanism differs from that of Data leakage prevention: output validation checks generated data against field rules before downstream use; this does not satisfy the requested outcome.

For the industrial maintenance objective to control which AWS principals can read a sensitive data bucket used for retrieval, Separation of duties addresses a different task—require a different employee to approve a high-risk AI production deployment. Its operating mechanism differs from that of Resource-based policy: separate roles and approval responsibilities reduce unilateral unauthorized changes; this does not satisfy the requested outcome.

For the industrial maintenance objective to control which AWS principals can read a sensitive data bucket used for retrieval, 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 Resource-based policy: IAM permissions authorize specific service actions and resources for a principal; this does not satisfy the requested outcome.

For the industrial maintenance objective to control which AWS principals can read a sensitive data bucket used for retrieval, Amazon Bedrock AgentCore Identity addresses a different task—manage agent authentication and delegated access to external resources. Its operating mechanism differs from that of Resource-based policy: AgentCore Identity helps agents use managed identity and credentials for authorized connections; this does not satisfy the requested outcome.

For the professional-services objective to detect software flaws in infrastructure hosting an AI application, Amazon Inspector addresses a different task—assess supported workloads for software vulnerabilities and exposure. Its operating mechanism differs from that of Vulnerability management: inspector continually scans eligible compute and container artifacts for security findings; this does not satisfy the requested outcome.

For the professional-services objective to detect software flaws in infrastructure hosting an AI application, Amazon CloudWatch monitoring addresses a different task—observe model-backed application errors, latency and operating metrics. Its operating mechanism differs from that of Vulnerability management: CloudWatch collects metrics and operational logs for supported services and applications; this does not satisfy the requested outcome.

For the professional-services objective to detect software flaws in infrastructure hosting an AI application, Tool-action approval gate addresses a different task—require a person to confirm that an assistant may transfer funds or delete records. Its operating mechanism differs from that of Vulnerability management: an approval checkpoint prevents high-impact tool invocations without explicit authorization; this does not satisfy the requested outcome.

For the customer operations objective to protect a customer's prompt while it travels between client and service, 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 in transit: AWS KMS helps create and control cryptographic keys used by AWS encryption features; this does not satisfy the requested outcome.

For the customer operations objective to protect a customer's prompt while it travels between client and service, Encryption at rest addresses a different task—protect stored embeddings and documents against exposure of underlying storage media. Its operating mechanism differs from that of Encryption in transit: at-rest encryption protects persisted data with managed cryptographic controls; this does not satisfy the requested outcome.

For the customer operations objective to protect a customer's prompt while it travels between client and service, Tool-action approval gate addresses a different task—require a person to confirm that an assistant may transfer funds or delete records. Its operating mechanism differs from that of Encryption in transit: an approval checkpoint prevents high-impact tool invocations without explicit authorization; this does not satisfy the requested outcome.

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.

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.

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.