Update a Task
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_visibilityto control who can view all task runs - Options:
owner_only,editors_and_owners,all_viewers
Fallback Model Support:
- Configure
fallback_llm_model_idandfallback_llm_configfor automatic failover - Improves reliability when primary model encounters errors or rate limits
For integration_bindings, omission inherits the prior revision and an empty
array removes every binding. Use a source binding_id to preserve a read-only
fixed_connection binding. integration_tool_ids is deprecated.
Note: Creating a new revision does not automatically make it active. Use the active_revisions field to control which revisions receive traffic.
Authentication
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.
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
Request
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.
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.
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.
Specifies what file types are accepted for visual LLM processing. Values: ‘none’ (default), ‘image’, ‘pdf’, ‘image_or_pdf’, ‘any’.
True if revision is a test revision. Test revisions cannot be live and are used for rapid Task testing/iteration.
When true (default) images will be automatically optimised before processing. Set to false to disable lossy image optimisation.
When true the Task is active and callable. false denotes the Task is not yet operational.
When true the Task is accessible to agents through the unauthenticated agent endpoint.
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.
Response headers
ID of newly created revision (if task_revision was provided)
Response
When true the Task is active and callable. false denotes the Task is not yet operational.
When true the Task is public and can be accessed by any User.
When true the Task is accessible to agents through the unauthenticated agent endpoint.
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.
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.