agents

Creates, updates, deletes, gets or lists an agents resource.

Overview

Name	`agents`
Type	Resource
Id	`google.aiplatform.agents`

Fields

The following fields are returned by SELECT queries:

get
list

Name	Datatype	Description
`id`	`string`	Immutable. The user-specified ID for the agent. This ID becomes the final component of the agent resource name. If not provided, Vertex AI will generate a value for this ID. The ID can be up to 63 characters and must match the regular expression `[a-z]([a-z0-9-]{0,61}[a-z0-9])?`.
`name`	`string`	Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`.
`base_agent`	`string`	Required. The base agent for the agent. Supported values: * `antigravity-preview-05-2026`
`base_environment`	`any`	Optional. The base environment configuration for the agent. Valid types: * A string value for the environment ID, or `remote` for the default. * A struct value for the `environment_config`.
`created`	`string (google-datetime)`	Output only. The time the agent was created.
`description`	`string`	Optional. The description of the agent.
`metadata`	`object`	Optional. The metadata for the agent.
`object`	`string`	Output only. The object type of the resource. For agents, the value is `agent`.
`system_instruction`	`string`	Optional. The instructions for the agent to follow. These instructions are passed to the LLM as a system instruction.
`tools`	`array`	Optional. The tools available to the agent.
`updated`	`string (google-datetime)`	Output only. The time the agent was last updated.

Name	Datatype	Description
`id`	`string`	Immutable. The user-specified ID for the agent. This ID becomes the final component of the agent resource name. If not provided, Vertex AI will generate a value for this ID. The ID can be up to 63 characters and must match the regular expression `[a-z]([a-z0-9-]{0,61}[a-z0-9])?`.
`name`	`string`	Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`.
`base_agent`	`string`	Required. The base agent for the agent. Supported values: * `antigravity-preview-05-2026`
`base_environment`	`any`	Optional. The base environment configuration for the agent. Valid types: * A string value for the environment ID, or `remote` for the default. * A struct value for the `environment_config`.
`created`	`string (google-datetime)`	Output only. The time the agent was created.
`description`	`string`	Optional. The description of the agent.
`metadata`	`object`	Optional. The metadata for the agent.
`object`	`string`	Output only. The object type of the resource. For agents, the value is `agent`.
`system_instruction`	`string`	Optional. The instructions for the agent to follow. These instructions are passed to the LLM as a system instruction.
`tools`	`array`	Optional. The tools available to the agent.
`updated`	`string (google-datetime)`	Output only. The time the agent was last updated.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
`get`	`select`	`projectsId`, `locationsId`, `agentsId`		Retrieves an agent.
`list`	`select`	`projectsId`, `locationsId`	`pageSize`, `pageToken`, `orderBy`	Lists agents in a location.
`create`	`insert`	`projectsId`, `locationsId`		Creates an agent.
`patch`	`update`	`projectsId`, `locationsId`, `agentsId`	`updateMask`	Updates an agent.
`delete`	`delete`	`projectsId`, `locationsId`, `agentsId`		Deletes an agent.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
`agentsId`	`string`
`locationsId`	`string`
`projectsId`	`string`
`orderBy`	`string`
`pageSize`	`integer (int32)`
`pageToken`	`string`
`updateMask`	`string (google-fieldmask)`

`SELECT` examples

get
list

Retrieves an agent.

SELECT
id,
name,
base_agent,
base_environment,
created,
description,
metadata,
object,
system_instruction,
tools,
updated
FROM google.aiplatform.agents
WHERE projectsId = '{{ projectsId }}' -- required
AND locationsId = '{{ locationsId }}' -- required
AND agentsId = '{{ agentsId }}' -- required
;

Lists agents in a location.

SELECT
id,
name,
base_agent,
base_environment,
created,
description,
metadata,
object,
system_instruction,
tools,
updated
FROM google.aiplatform.agents
WHERE projectsId = '{{ projectsId }}' -- required
AND locationsId = '{{ locationsId }}' -- required
AND pageSize = '{{ pageSize }}'
AND pageToken = '{{ pageToken }}'
AND orderBy = '{{ orderBy }}'
;

`INSERT` examples

create
Manifest

Creates an agent.

INSERT INTO google.aiplatform.agents (
data__description,
data__name,
data__metadata,
data__id,
data__base_environment,
data__tools,
data__base_agent,
data__system_instruction,
projectsId,
locationsId
)
SELECT 
'{{ description }}',
'{{ name }}',
'{{ metadata }}',
'{{ id }}',
'{{ base_environment }}',
'{{ tools }}',
'{{ base_agent }}',
'{{ system_instruction }}',
'{{ projectsId }}',
'{{ locationsId }}'
RETURNING
name,
done,
error,
metadata,
response
;

# Description fields are for documentation purposes
- name: agents
props:
  - name: projectsId
    value: "{{ projectsId }}"
    description: Required parameter for the agents resource.
  - name: locationsId
    value: "{{ locationsId }}"
    description: Required parameter for the agents resource.
  - name: description
    value: "{{ description }}"
    description: |
      Optional. The description of the agent.
  - name: name
    value: "{{ name }}"
    description: |
      Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`.
  - name: metadata
    value: "{{ metadata }}"
    description: |
      Optional. The metadata for the agent.
  - name: id
    value: "{{ id }}"
    description: |
      Immutable. The user-specified ID for the agent. This ID becomes the final component of the agent resource name. If not provided, Vertex AI will generate a value for this ID. The ID can be up to 63 characters and must match the regular expression `[a-z]([a-z0-9-]{0,61}[a-z0-9])?`.
  - name: base_environment
    value: "{{ base_environment }}"
    description: |
      Optional. The base environment configuration for the agent. Valid types: * A string value for the environment ID, or `remote` for the default. * A struct value for the `environment_config`.
  - name: tools
    description: |
      Optional. The tools available to the agent.
    value:
      - url: "{{ url }}"
        type: "{{ type }}"
        headers: "{{ headers }}"
        name: "{{ name }}"
  - name: base_agent
    value: "{{ base_agent }}"
    description: |
      Required. The base agent for the agent. Supported values: * `antigravity-preview-05-2026`
  - name: system_instruction
    value: "{{ system_instruction }}"
    description: |
      Optional. The instructions for the agent to follow. These instructions are passed to the LLM as a system instruction.

`UPDATE` examples

patch

Updates an agent.

UPDATE google.aiplatform.agents
SET 
data__description = '{{ description }}',
data__name = '{{ name }}',
data__metadata = '{{ metadata }}',
data__id = '{{ id }}',
data__base_environment = '{{ base_environment }}',
data__tools = '{{ tools }}',
data__base_agent = '{{ base_agent }}',
data__system_instruction = '{{ system_instruction }}'
WHERE 
projectsId = '{{ projectsId }}' --required
AND locationsId = '{{ locationsId }}' --required
AND agentsId = '{{ agentsId }}' --required
AND updateMask = '{{ updateMask}}'
RETURNING
id,
name,
base_agent,
base_environment,
created,
description,
metadata,
object,
system_instruction,
tools,
updated;

`DELETE` examples

delete

Deletes an agent.

DELETE FROM google.aiplatform.agents
WHERE projectsId = '{{ projectsId }}' --required
AND locationsId = '{{ locationsId }}' --required
AND agentsId = '{{ agentsId }}' --required
;

Overview​

Fields​

Methods​

Parameters​

SELECT examples​

INSERT examples​

UPDATE examples​

DELETE examples​