Skip to content

/AWS1/CL_BDOGWPOLICYENGINECONF

The configuration for a policy engine associated with a gateway. A policy engine is a collection of policies that evaluates and authorizes agent tool calls. When associated with a gateway, the policy engine intercepts all agent requests and determines whether to allow or deny each action based on the defined policies.

CONSTRUCTOR

IMPORTING

Required arguments:

iv_arn TYPE /AWS1/BDOGWPOLICYENGINEARN /AWS1/BDOGWPOLICYENGINEARN

The ARN of the policy engine. The policy engine contains Cedar policies that define fine-grained authorization rules specifying who can perform what actions on which resources as agents interact through the gateway.

iv_mode TYPE /AWS1/BDOGWPOLICYENGINEMODE /AWS1/BDOGWPOLICYENGINEMODE

The enforcement mode for the policy engine. Valid values include:

  • LOG_ONLY - The policy engine evaluates each action against your policies and adds traces on whether tool calls would be allowed or denied, but does not enforce the decision. Use this mode to test and validate policies before enabling enforcement.

  • ENFORCE - The policy engine evaluates actions against your policies and enforces decisions by allowing or denying agent operations. Test and validate policies in LOG_ONLY mode before enabling enforcement to avoid unintended denials or adversely affecting production traffic.


Queryable Attributes

arn

The ARN of the policy engine. The policy engine contains Cedar policies that define fine-grained authorization rules specifying who can perform what actions on which resources as agents interact through the gateway.

Accessible with the following methods

Method Description
GET_ARN() Getter for ARN, with configurable default
ASK_ARN() Getter for ARN w/ exceptions if field has no value
HAS_ARN() Determine if ARN has a value

mode

The enforcement mode for the policy engine. Valid values include:

  • LOG_ONLY - The policy engine evaluates each action against your policies and adds traces on whether tool calls would be allowed or denied, but does not enforce the decision. Use this mode to test and validate policies before enabling enforcement.

  • ENFORCE - The policy engine evaluates actions against your policies and enforces decisions by allowing or denying agent operations. Test and validate policies in LOG_ONLY mode before enabling enforcement to avoid unintended denials or adversely affecting production traffic.

Accessible with the following methods

Method Description
GET_MODE() Getter for MODE, with configurable default
ASK_MODE() Getter for MODE w/ exceptions if field has no value
HAS_MODE() Determine if MODE has a value