List Task Agents

GET

/org/:org_id/project/:project_id/task-agent

GET

/api/v1/org/:org_id/project/:project_id/task-agent

curl https://app.rightbrain.ai/api/v1/org/org_id/project/project_id/task-agent \
     -H "Authorization: Bearer <token>"

{
  "results": [
    {
      "id": "019df849-e106-3301-5894-291b4c9c6cab",
      "name": "Support Triage Agent",
      "task_agent_run_visibility": "editors_and_owners",
      "is_deleted": false,
      "created": "2026-05-05T10:15:00Z",
      "modified": "2026-06-12T09:30:00Z",
      "active_revision": {
        "id": "019df849-e12a-b57e-62d4-0e5875e91ef4",
        "task_agent_id": "019df849-e106-3301-5894-291b4c9c6cab",
        "created": "2026-06-12T09:30:00Z",
        "modified": "2026-06-12T09:30:00Z"
      },
      "revisions": [
        {
          "id": "019df849-e12a-b57e-62d4-0e5875e91ef4",
          "task_agent_id": "019df849-e106-3301-5894-291b4c9c6cab",
          "description": "Triages inbound client support emails, looks up the client's account, and drafts a reply.",
          "instruction": "You triage inbound client support emails for Fenwick & Co Bookkeeping. For every message: (1) run the Customer Support Analyzer to classify the sender's sentiment and issue category, (2) look up the client's account in the Customer Database sheet using their email address to confirm their plan, billing status, and any existing notes before you say anything about their account, (3) draft a reply that directly answers what they asked, references specific figures from the account lookup rather than the analyzer's summary, and matches a warm but professional tone, and (4) once a team member confirms the reply, log a one-line resolution note back to the Tickets sheet so the team can see the case was handled. Never promise a refund or credit yourself — say that a member of the team will confirm and action it within one business day. If the account lookup returns no match for the sender's email, say so plainly in the draft and ask the client to confirm the email address on file rather than guessing.",
          "mode": "agentic",
          "llm_model_id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
          "fallback_llm_model_id": "af2a9bbf-5f36-4b12-bd3f-92c57be96dec",
          "created": "2026-06-12T09:30:00Z",
          "llm_model": {
            "provider": "OpenAI",
            "vendor": "openai",
            "name": "gpt-4-turbo",
            "alias": "GPT-4 Turbo",
            "description": "Latest GPT-4 Turbo model with vision capabilities. 128K context window with training cut off of Dec 2023.",
            "supports_vision": true,
            "max_context_window": 128000,
            "id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
            "supports_image_output": false,
            "supports_pdf_vision": false,
            "supports_tool_calling": true,
            "supports_context_caching": false,
            "price": "average",
            "speed": "fast",
            "knowledge_cutoff": "2023-12-01",
            "created": "2024-01-16T13:33:25.247662Z",
            "modified": "2024-01-16T13:33:25.247662Z",
            "llm_model_comments": []
          },
          "fallback_llm_model": {
            "provider": "OpenAI",
            "vendor": "openai",
            "name": "gpt-3.5-turbo",
            "alias": "GPT-3.5 Turbo",
            "description": "Fast, efficient model suitable for simple tasks. 16K context window.",
            "supports_vision": false,
            "max_context_window": 16385,
            "id": "af2a9bbf-5f36-4b12-bd3f-92c57be96dec",
            "supports_image_output": false,
            "supports_pdf_vision": false,
            "supports_tool_calling": true,
            "supports_context_caching": false,
            "price": "cheap",
            "speed": "standard",
            "knowledge_cutoff": "2021-09-01",
            "created": "2024-01-16T13:33:25.247662Z",
            "modified": "2024-01-16T13:33:25.247662Z",
            "llm_model_comments": []
          },
          "task_tools": [
            {
              "id": "019df7a2-44a0-7ee9-8876-25aa7a902f38",
              "task_id": "019df7a2-44a0-7f6b-8a18-d81df57049d0",
              "task_name": "Customer Support Analyzer",
              "order": 0,
              "enabled": true,
              "task_revision_id": "019df7a2-44a0-75d6-b036-4e86f6d45302",
              "revision_strategy": "pinned",
              "is_output_formatter": false,
              "action_mode": "auto_run",
              "approval_percent": 100,
              "rejection_behavior": "end_run"
            },
            {
              "id": "019ebb2a-b9c0-7d29-a460-f6aa6fd9edbb",
              "task_id": "019df7a2-44a0-7186-92a6-a8e45e78537b",
              "task_name": "Draft Support Reply",
              "order": 1,
              "enabled": true,
              "task_revision_id": "019df7a2-44a0-78c4-ba7b-6ae382a6253a",
              "revision_strategy": "pinned",
              "is_output_formatter": true,
              "action_mode": "auto_run",
              "approval_percent": 100,
              "rejection_behavior": "end_run"
            }
          ],
          "integrations": [
            {
              "id": "019ebb2a-b9c0-7af9-b42d-e9cd2819667d",
              "project_integration_id": "019df7a2-44a0-7a75-ae4f-4c8edcdac22e",
              "integration_type": "google_sheets",
              "integration_name": "Customer Database",
              "order": 0,
              "enabled": true,
              "credential_policy": "project_default",
              "provision_source": "manual",
              "tool_count": 2,
              "allowed_tool_ids": [
                "019df7a2-44a0-7b09-afd0-c59cbc20126d",
                "019df7a2-44a0-7923-9ea9-87be4ba93be9"
              ],
              "default_action_mode": "auto_run",
              "default_approval_percent": 100,
              "default_rejection_behavior": "end_run",
              "tool_action_modes": {
                "019df7a2-44a0-7923-9ea9-87be4ba93be9": "require_approval"
              },
              "tool_approval_percents": {
                "019df7a2-44a0-7923-9ea9-87be4ba93be9": 10
              },
              "tool_rejection_behaviors": {}
            }
          ],
          "skills": [],
          "mcp_servers": [],
          "registered_tools": [],
          "tags": [],
          "max_turns": 50,
          "active": true,
          "modified": "2026-06-12T09:30:00Z"
        }
      ],
      "shared_with_project": true
    },
    {
      "id": "019fa2da-4790-7eeb-a8e7-a8f225f87026",
      "name": "Invoice Reconciliation Agent",
      "task_agent_run_visibility": "owner_only",
      "is_deleted": false,
      "created": "2026-07-01T08:00:00Z",
      "modified": "2026-07-01T08:00:00Z",
      "active_revision": {
        "id": "019fa2da-4790-7498-a387-8196969ee341",
        "task_agent_id": "019fa2da-4790-7eeb-a8e7-a8f225f87026",
        "created": "2026-07-01T08:00:00Z",
        "modified": "2026-07-01T08:00:00Z"
      },
      "revisions": [
        {
          "id": "019fa2da-4790-7498-a387-8196969ee341",
          "task_agent_id": "019fa2da-4790-7eeb-a8e7-a8f225f87026",
          "description": "Matches supplier invoices to purchase orders.",
          "instruction": "Reconcile incoming supplier invoices against open purchase orders and flag mismatches over £25 for manual review.",
          "mode": "agentic",
          "llm_model_id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
          "fallback_llm_model_id": "af2a9bbf-5f36-4b12-bd3f-92c57be96dec",
          "created": "2026-07-01T08:00:00Z",
          "llm_model": {
            "provider": "OpenAI",
            "vendor": "openai",
            "name": "gpt-4-turbo",
            "alias": "GPT-4 Turbo",
            "description": "Latest GPT-4 Turbo model with vision capabilities. 128K context window with training cut off of Dec 2023.",
            "supports_vision": true,
            "max_context_window": 128000,
            "id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
            "supports_image_output": false,
            "supports_pdf_vision": false,
            "supports_tool_calling": true,
            "supports_context_caching": false,
            "price": "average",
            "speed": "fast",
            "knowledge_cutoff": "2023-12-01",
            "created": "2024-01-16T13:33:25.247662Z",
            "modified": "2024-01-16T13:33:25.247662Z",
            "llm_model_comments": []
          },
          "fallback_llm_model": {
            "provider": "OpenAI",
            "vendor": "openai",
            "name": "gpt-3.5-turbo",
            "alias": "GPT-3.5 Turbo",
            "description": "Fast, efficient model suitable for simple tasks. 16K context window.",
            "supports_vision": false,
            "max_context_window": 16385,
            "id": "af2a9bbf-5f36-4b12-bd3f-92c57be96dec",
            "supports_image_output": false,
            "supports_pdf_vision": false,
            "supports_tool_calling": true,
            "supports_context_caching": false,
            "price": "cheap",
            "speed": "standard",
            "knowledge_cutoff": "2021-09-01",
            "created": "2024-01-16T13:33:25.247662Z",
            "modified": "2024-01-16T13:33:25.247662Z",
            "llm_model_comments": []
          },
          "task_tools": [],
          "integrations": [],
          "skills": [],
          "mcp_servers": [],
          "registered_tools": [],
          "tags": [],
          "active": true,
          "modified": "2026-07-01T08:00:00Z"
        }
      ],
      "shared_with_project": false
    }
  ],
  "pagination": {
    "has_next": false,
    "page_limit": 25
  }
}

List all Task Agents configured for the project.

Returns a paginated list of Task Agents with their root metadata and embedded revision history. Runtime configuration such as instructions, models, and tools is stored on each revision. Results can be filtered by a case-insensitive partial name match or to Task Agents created by the current user.

Authentication

AuthorizationBearer

API key or access token, sent as Authorization: Bearer <token>. The simplest option: create an API key in your dashboard under Settings, then paste it here.

AuthorizationBearer

API key or access token, sent as Authorization: Bearer <token>. The simplest option: create an API key in your dashboard under Settings, then paste it here.

Path parameters

org_idstringRequiredformat: "uuid"

The unique identifier of the organization.

project_idstringRequiredformat: "uuid"

The unique identifier of the project.

Query parameters

namestring or nullOptional

Filter Task Agents by name (case-insensitive partial match).

created_by_mebooleanOptionalDefaults to false

Filter Task Agents to those created by the current user.

cursorstring or nullOptional

Pagination cursor

page_limitintegerOptional1-100Defaults to 100

Max results per page

seven_day_summarybooleanOptionalDefaults to false

When true, include a seven day summary of visible run count, average charged credits, and average duration for each returned TaskAgent.

Response

Successfully retrieved Task Agents

resultslist of objects

The list of items returned for the current page.

paginationobject or nullOptional

Contains pagination information for the result set.

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

422

Unprocessable Entity Error

500

Internal Server Error