Collected AI Attributes

Shared Agent Attributes

These shared agent attributes are available across supported agent automations.


Attribute	Supported systems	Description	Notes
Agent ARN / Resource ID	All supported agent automations	Platform resource identifier for the agent.	Bedrock uses an ARN. Azure Foundry uses the agent name.
Agent ID	All supported agent automations	Platform-specific unique identifier for the agent.	Includes normalized AgentCore AgentId values.
Agent Name	All supported agent automations	Display name of the agent.	Includes normalized AgentCore Name values.
Agent Source	All supported agent automations	Source platform from which the agent was discovered.	Includes AgentCore as a Bedrock source value.
Agent Version	All supported agent automations	Version of the agent.	Includes normalized AgentCore AI Agent Version values.
Agentic Compound System	All supported agent automations	Indicates whether the discovered record is an agentic compound system.	For discovered agents, this is Yes.
Creation Source	All supported agent automations	How the record was created.	For automation-discovered records, this is Automation.
Full Resource Name	All supported agent automations	Fully qualified platform resource identifier.	Includes normalized AgentCore Full Source Name values.
Hosting Environment	All supported agent automations	Platform hosting the agent.	Example: Amazon Web Services (AWS) Bedrock.
Is Deployed	All supported agent automations	Indicates whether the agent is deployed.	Based on platform deployment or publish state.
Operational Status	All supported agent automations	Current operational state of the agent.	Includes normalized AgentCore Operational Status values.
Region	All supported agent automations	Cloud region where the agent runs.	Includes normalized AgentCore Agent Region values.
Scope	All supported agent automations	Platform scope or path for the discovered asset.	The exact path structure varies by platform.
Stage	All supported agent automations	Lifecycle stage of the agent.	Use the platform-supported lifecycle value where available.
Underlying Model	All supported agent automations	Foundation or backing model used by the agent.	Keep as the shared model-binding field.
Version Aliases	All supported agent automations	Version-to-alias mapping for the agent.	Bedrock-only when populated.

AgentCore Attributes

For Amazon Bedrock AgentCore, fields that correspond to existing agent attributes use the same attribute names used elsewhere in AI Automations. AgentCore-only fields appear in the system-specific section.


AgentCore source label	Canonical label	Category
AI Agent Version	Agent Version	Shared Agent attributes
Agent Region	Region	Shared Agent attributes
Agent Source	Agent Source	Shared Agent attributes
AgentId	Agent ID	Shared Agent attributes
Creation Source	Creation Source	Shared Agent attributes
Description	Description	System-specific Agent attributes
Full Source Name	Full Resource Name	Shared Agent attributes
Hosting Environment	Hosting Environment	Shared Agent attributes
Name	Agent Name	Shared Agent attributes
Operational Status	Operational Status	Shared Agent attributes
Organization	Organization	System-specific Agent attributes

Shared Model Attributes

These model attributes are available across supported model automations. Use the Supported systems column to determine where each attribute applies.


Attribute	Supported systems	Description
Created Date	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	Date the model record was created.
Creation Source	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	How the record was created.
Deployment ID	Azure Foundry	Deployment identifier for the model.
Description	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	Description of the model and its purpose.
Endpoint URL	Azure Foundry	Endpoint address for the model.
Framework	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	Machine learning framework used by the model.
Full Resource Name	AWS Bedrock, Azure Foundry	Fully qualified platform resource identifier.
Generative AI	AWS Bedrock, Databricks	Indicates whether the model is generative AI.
Hosting Provider	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	Provider hosting the model.
Mode	AWS Bedrock, Databricks	Operating mode for the model.
Model ID	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	Platform-specific unique identifier for the model.
Model Name	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	Display name of the model.
Model Source	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	Source platform from which the model was discovered.
Model Version	AWS Bedrock, AWS SageMaker, Azure Foundry, GCP Vertex, Databricks	Version of the model.
Programming Language	AWS Bedrock, Databricks	Programming language used to implement the model.
Scope	AWS Bedrock, Azure Foundry	Platform scope or path for the discovered model.
Stage	AWS SageMaker, Databricks	Lifecycle stage of the model.
Type of Learning	AWS Bedrock, Databricks	Learning method used to train the model.

System-Specific Agent Attributes

These agent attributes are available for specific platforms.


System	Attribute	Description
AWS Bedrock	Agent Type	Classification of the agent.
	Autonomy Level	Degree of agent autonomy.
	Description	Description of the agent and its purpose.
Azure Foundry	Default Model	Default model associated with the agent.
Amazon Bedrock AgentCore	Organization	Organization or policy domain associated with the agent.

System-Specific Model Attributes

Use this section for platform-specific notes that affect how a shared model attribute is populated or interpreted.


System	Shared field
AWS SageMaker	Framework
AWS SageMaker	Stage
Azure Foundry	Deployment ID
	Endpoint URL
	Scope
AWS Bedrock	Scope

Guardrail Attributes

This section lists the supported guardrail attributes for agents and models.

Azure Foundry models use the same guardrail attributes as Azure Foundry agents, but Azure Foundry and Amazon Bedrock do not support the exact same guardrail types.


Display label	System field label	Supported systems
Automated Reasoning	Has Automated Reasoning Guardrail	AWS Bedrock
Content Filtering — Input	Has Content Filtering Guardrail - Input	AWS Bedrock, Azure Foundry
Content Filtering — Output	Has Content Filtering Guardrail - Output	AWS Bedrock, Azure Foundry
Contextual Grounding	Has Contextual Grounding Guardrail	AWS Bedrock, Azure Foundry
Denied Topics — Input	Has Denied Topics Guardrail - Input	AWS Bedrock
Denied Topics — Output	Has Denied Topics Guardrail - Output	AWS Bedrock
Prompt Attack Protection	Has Prompt Attack Guardrail	AWS Bedrock, Azure Foundry
Protected Material — Code	Has Protected Material - Code Guardrail	Azure Foundry
Protected Material — Text	Has Protected Material - Text Guardrail	Azure Foundry
Sensitive Info Filters — Input	Has Sensitive Information Filters Guardrail - Input	AWS Bedrock, Azure Foundry
Sensitive Info Filters — Output	Has Sensitive Information Filters Guardrail - Output	AWS Bedrock, Azure Foundry
Word Filters — Input	Has Word Filters Guardrail - Input	AWS Bedrock, Azure Foundry
Word Filters — Output	Has Word Filters Guardrail - Output	AWS Bedrock, Azure Foundry

Dataset Attributes

Dataset attributes are currently supported for Databricks only.


Attribute	Supported system	Description	Notes
Catalog Metadata	Databricks	Structured catalog metadata for the dataset.	Keep as the canonical catalog metadata field.
Dataset Version	Databricks	Dataset version value.	Keep as the canonical version field.
Full Name	Databricks	Full dataset name.	Keep as the canonical dataset display name.
Unique Identifier	Databricks	Platform-specific unique identifier for the dataset.	Keep as the canonical identifier field.

AI Governance