Update a Task | Rightbrain Docs | Transform AI Ideas into Production Tasks

Update an existing Task with new configuration or create a new revision.

When updating a Task, you can:

Modify basic Task properties (name, description, enabled status, task_run_visibility)
Create a new revision with updated prompts, models, and configuration (including fallback models)
Manage active revisions and their traffic weights for A/B testing
Update tags for the Task or specific revisions

Task Run Visibility Control:

Update task_run_visibility to control who can view all task runs
Options: owner_only, editors_and_owners, all_viewers

Fallback Model Support:

Configure fallback_llm_model_id and fallback_llm_config for automatic failover
Improves reliability when primary model encounters errors or rate limits

Note: Creating a new revision does not automatically make it active. Use the active_revisions field to control which revisions receive traffic.

Update an existing Task with new configuration or create a new revision. When updating a Task, you can: 1. Modify basic Task properties (name, description, enabled status, task_run_visibility) 2. Create a new revision with updated prompts, models, and configuration (including fallback models) 3. Manage active revisions and their traffic weights for A/B testing 4. Update tags for the Task or specific revisions Task Run Visibility Control: - Update `task_run_visibility` to control who can view all task runs - Options: `owner_only`, `editors_and_owners`, `all_viewers` Fallback Model Support: - Configure `fallback_llm_model_id` and `fallback_llm_config` for automatic failover - Improves reliability when primary model encounters errors or rate limits Note: Creating a new revision does not automatically make it active. Use the active_revisions field to control which revisions receive traffic.

Authentication

AuthorizationBearer

Bearer token authentication using JWT tokens from Ory Kratos/Hydra

Path Parameters

org_idstringRequiredformat: "uuid"

The unique identifier of the organization.

project_idstringRequiredformat: "uuid"

The unique identifier of the project.

task_idstringRequiredformat: "uuid"

The specific Task to reference.

Request

This endpoint expects an object.

system_promptstring or nullOptional

The system prompt that is used to set the LLM context.

user_promptstring or nullOptional

The description of the Task. It is not required to mention the outputs in the prompt, but it can help the model to understand the context better. Any input strings should be referenced with the dynamic {...} syntax, this informs the model to look for those values in the input data.

llm_model_idstring or nullOptionalformat: "uuid"

The LLM model to use for the Task.

llm_configmap from strings to any or nullOptional

Specific configuration parameters for the LLM model.

output_formatmap from strings to objects or enums or nullOptional

This gives control over the structure of how the Task responds. Supports shorthand notation or an object with type can be specified for each attribute. In most instances, the LLM will be able to generate the desired output into the relevant property, but an optional description can be passed to provide it with additional context.

task_forwarder_idstring or nullOptionalformat: "uuid"

The unique identifier for a valid Task Forwarder. It is used to forward the Task output to another system or service.

ragobject or nullOptional

Note: This is a Paid Tier feature. Provide additional domain specific input to the LLM so that it is able to reference user specific information when executing the Task. Examples of this could be a product catalogue, terms and conditions or a user manual.

image_requiredboolean or nullOptional

When true it requires an image to be sent in the Task Run request.

annotationstring or nullOptional<=255 characters

testbooleanOptionalDefaults to false

True if revision is a test revision. Test revisions cannot be live and are used for rapid Task testing/iteration.

input_processorslist of objectsOptional

optimise_imagesboolean or nullOptionalDefaults to true

When true (default) images will be automatically optimised before processing. Set to false to disable lossy image optimisation.

fallback_llm_model_idstring or nullOptionalformat: "uuid"

The LLM model to use as fallback if the primary model fails.

fallback_llm_configmap from strings to any or nullOptional

Specific configuration parameters for the fallback LLM model.

namestring or nullOptionalformat: "^[a-zA-Z0-9\- ]+$"

A name or reference for the Task.

descriptionstring or nullOptional

A longer description of the Task for internal reference.

enabledboolean or nullOptional

When true the Task is active and callable. false denotes the Task is not yet operational.

exposed_to_agentsboolean or nullOptional

When true the Task is accessible to agents through the unauthenticated agent endpoint.

task_run_visibilityenum or nullOptional

Controls who can view all task runs. ‘owner_only’ - only task owners see all runs (default), ‘editors_and_owners’ - task editors and owners see all runs, ‘all_viewers’ - all users with view permission see all runs.

Allowed values:

active_revisionslist of objects or nullOptional

The revision currently active for this Task.

tagslist of strings or nullOptional

revision_tagslist of strings or nullOptional

Response

Task updated successfully

namestringformat: "^[a-zA-Z0-9\- ]+$"

A name or reference for the Task.

enabledboolean

When true the Task is active and callable. false denotes the Task is not yet operational.

idstringformat: "uuid"

The unique identifier of the Task.

project_idstringformat: "uuid"

The Project that the Task belongs to.

createdstring

When the Task was created.

access_tokenstring or null

Task specific Bearer token that can be used to authenticated when executing this Task.

active_revisionslist of objects

The revision currently active for this Task.

descriptionstring or null

A longer description of the Task for internal reference.

publicboolean or nullDefaults to false

When true the Task is public and can be accessed by any User.

exposed_to_agentsboolean or nullDefaults to false

When true the Task is accessible to agents through the unauthenticated agent endpoint.

output_modalityenum or nullDefaults to json

Specifies the output modality of the task. Can be 'json' or 'image'. Defaults to 'json'.

Allowed values:

task_run_visibilityenum or nullDefaults to owner_only

Allowed values:

modifiedstring or null

When the Task was last updated.

revisionslist of objects or null

Each update to a Task results in a new Revision being created. Task Revisions are a powerful concept that can be used to assist with A/B testing, comparing responses from different LLM’s, etc.

cloned_from_task_revision_idstring or nullformat: "uuid"

The unique identifier of the task revision this task was cloned from, if applicable.

tagslist of objects or null

Errors

Update an existing Task with new configuration or create a new revision.

When updating a Task, you can:

Modify basic Task properties (name, description, enabled status, task_run_visibility)
Create a new revision with updated prompts, models, and configuration (including fallback models)
Manage active revisions and their traffic weights for A/B testing
Update tags for the Task or specific revisions

Task Run Visibility Control:

Update task_run_visibility to control who can view all task runs
Options: owner_only, editors_and_owners, all_viewers

Fallback Model Support:

Configure fallback_llm_model_id and fallback_llm_config for automatic failover
Improves reliability when primary model encounters errors or rate limits

Note: Creating a new revision does not automatically make it active. Use the active_revisions field to control which revisions receive traffic.

1	curl -X POST https://app.rightbrain.ai/api/v1/org/123e4567-e89b-12d3-a456-426614174000/project/123e4567-e89b-12d3-a456-426614174001/task/01909843-3596-da54-4756-28af46917e74 \
2	-H "Authorization: Bearer <token>" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"system_prompt": "You are an updated assistant.",
6	"user_prompt": "Updated prompt: {{input}}",
7	"llm_model_id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
8	"output_format": {
9	"response": {
10	"type": "str",
11	"description": "Updated response"
12	}
13	},
14	"annotation": "Version 2 with improved prompts",
15	"test": false,
16	"name": "My Task v2"
17	}'

1	{
2	"name": "Fintech Pre-Triage",
3	"enabled": true,
4	"id": "019011e6-e530-3aca-6cf7-2973387c255d",
5	"project_id": "019010a2-8327-2607-11d7-41bb0a8936d4",
6	"created": "2024-06-13T14:01:03.021673",
7	"access_token": "eyJhbGciOiJSUzI1NiIsImtpZCI6IjY1NmVkZWJkLTcyOWItNDhjNS1hYjk3LTFiYjgzNDM3ZGY5MyIsInR5cCI6IkpXVCJ1",
8	"active_revisions": [
9	{
10	"task_revision_id": "0190a234-8dc6-6d08-aea9-928fcecad8f1",
11	"weight": 1
12	}
13	],
14	"description": "A task to pre-triage user onboarding before IDV.",
15	"public": false,
16	"exposed_to_agents": false,
17	"modified": "2024-06-13T14:01:03.021673",
18	"revisions": [
19	{
20	"system_prompt": "You are an expert software program specifically designed for the fintech industry that will be used for pre-triage tasks to ensure the best possible client UX and efficient 3rd party platform interoperability.",
21	"user_prompt": "Your task is to validate the uploaded image and determine whether it will be suitable for authentication and onboarding checks. If the image of the person is clear and typical of a passport style photo then set the compliance field to true. Provide rationale for your decision in the rationale field. If the compliance result is false, then provide a helpful hint for the customer who has submitted the photo informing them why it is unacceptable and some steps to remedy it, place this into the hint field. Determine whether the following description matches the provided image: {description}",
22	"llm_model_id": "019011e6-e530-3aca-6cf7-2973387c255d",
23	"id": "0190a234-8dc6-6d08-aea9-928fcecad8f1",
24	"created": "2024-06-13T14:01:03.021673",
25	"modified": "2024-06-13T14:01:03.021673",
26	"llm_model": {
27	"provider": "OpenAI",
28	"vendor": "openai",
29	"name": "gpt-4-turbo-preview",
30	"alias": "GPT-4 Turbo",
31	"description": "Latest GPT-4 model with 128k context window and knowledge cutoff of December 2023.",
32	"supports_vision": true,
33	"max_context_window": 128000,
34	"id": "019011e6-e530-3aca-6cf7-2973387c255d",
35	"created": "2024-01-16T13:33:25.247662",
36	"modified": "2024-01-16T13:33:25.247662"
37	},
38	"input_params": [
39	"string"
40	],
41	"llm_config": {
42	"temperature": 0.7
43	},
44	"output_format": {
45	"compliance": "bool",
46	"hint": {
47	"type": "str"
48	},
49	"match": {
50	"description": "True if the provided description is a close match",
51	"type": "bool"
52	},
53	"rationale": "str"
54	},
55	"task_forwarder_id": "0190a234-8dc6-6d08-aea9-928fcecad8f1",
56	"rag": {
57	"collection_id": "0190a234-8dc6-6d08-aea9-928fcecad8f1",
58	"rag_param": "context"
59	},
60	"image_required": true,
61	"optimise_images": true,
62	"test": false,
63	"input_processors": [
64	{
65	"param_name": "description",
66	"input_processor": "url_fetcher",
67	"config": {
68	"extract_text": true,
69	"include_title": true,
70	"max_length": 5000
71	}
72	}
73	],
74	"annotation": "Production v2 - Added image matching capability",
75	"active": true,
76	"tags": []
77	}
78	]
79	}