HighLevel: Create Agent — agent Studio create Agent
HighLevel agentStudio.createAgent: arguments, response, policy and SDK examples.
← Agent studio operations · Get started
Operation gohighlevel.createagent
Provider route: POST /agent-studio/agent. Alter supplies the connection’s credentials and routing.
Call through Alter
Section titled “Call through Alter”Install @alter-ai/sdk @alter-ai/gohighlevel with npm, or alter-sdk-gohighlevel with pip. Supply your connected customer’s grant ID and the arguments described below.
import { App } from "@alter-ai/sdk";import { HighLevelIntegration } from "@alter-ai/gohighlevel";
async function execute(input: Parameters<HighLevelIntegration["agentStudio"]["createAgent"]>[0]) { const app = new App({ apiKey: process.env.ALTER_API_KEY! }); try { const provider = new HighLevelIntegration(app, { grantId: process.env.PROVIDER_GRANT_ID! }); const call = await provider.agentStudio.createAgent(input); const result = await call.wait(); return result.bodyJson(); } finally { await app.close(); }}import osfrom alter_sdk import Appfrom alter_sdk_gohighlevel import HighLevelIntegration
async def execute(arguments): async with App(api_key=os.environ["ALTER_API_KEY"]) as app: provider = HighLevelIntegration(app, {"grant_id": os.environ["PROVIDER_GRANT_ID"]}) call = await provider.agent_studio.create_agent(arguments) result = await call.wait() return result.body_json()| Field | Type | Presence | Description and constraints |
|---|---|---|---|
$ | object | Root | Additional keys: not allowed |
query | object | Optional | Additional keys: not allowed |
query.source | string | Optional | |
body | Model | Required within parent | Expand Create Agent — agent Studio create Agent — request body — body |
Referenced models: Create Agent — agent Studio create Agent — request body — body
Response
Section titled “Response”Response media type: application/json. The table describes the pinned successful response. Referenced models link to their complete fields.
| Field | Type | Presence | Description and constraints |
|---|---|---|---|
$ | Model | Root | Expand Create Agent — agent Studio create Agent — response body |
Referenced models: Create Agent — agent Studio create Agent — response body
Schemas
Section titled “Schemas”Create Agent — agent Studio create Agent — request body — body
| Field | Type | Presence | Description and constraints |
|---|---|---|---|
$ | object | Root | |
agencyId | string | Optional | Agency ID |
authorEmail | string | Optional | Author email |
authorId | string | Optional | Author ID |
authorName | string | Optional | Author name |
description | string | Optional | Description of the agent |
edges | array | Optional | Edges array (deprecated, prefer using version.edges) |
edges[] | string | Each item | |
locationId | string | Required within parent | Location ID |
name | string | Optional | Name of the agent |
nodes | array | Optional | Nodes array (deprecated, prefer using version.nodes) |
nodes[] | string | Each item | |
status | string | Required within parent | Status of the agent One of: active, inactive, archived |
version | object | Required within parent | Version data for the agent including nodes, edges, and configuration |
Create Agent — agent Studio create Agent — response body
| Field | Type | Presence | Description and constraints |
|---|---|---|---|
$ | object | Root | |
agent | object | Required within parent | Created agent data with metadata |
message | string | Required within parent | Response message |
success | boolean | Required within parent | Success status |
versions | array | Required within parent | Created versions array (initial staging version) |
Policy, approvals and errors
Section titled “Policy, approvals and errors”SDK function policy ID: gohighlevel.createagent. Catalog operation: createAgent. Rules can name either ID; function rules distinguish managed calls and conservatively cover raw calls sharing the route. Existing grant permissions and policy rules apply. wait() returns an immediate result or waits for a required approval; it never approves the request itself. Persist the approval ID to resume after a restart.
Provider errors retain their response; JSON decoding raises ProviderAPIError for provider failures. ManagedOperationError identifies contract/input/retention errors. See error handling and provider-specific behavior. Sensitive input may be refused before approval storage. A decoding error never resubmits a write.
Required provider scopes: ["agent-studio.write"]
Pinned headers: {"Version": "v3"}