Sanity Fetch Schema

Task type: Sanity Fetch Schema

Use Sanity Fetch Schema to retrieve a document schema before generating or publishing Sanity content.

Run behavior

• Side effects: This task is read-only or computation-only by default. It returns data for later steps rather than directly writing records or sending messages.
• Credit usage: This task is not classified as credit-billed by the workflow task registry.

When to use this task

• Generate structured content that must match a Sanity document type.
• Give an AI Prompt task the schema it should conform to.
• Validate your workflow inputs before a publish step.

Setup tips

• Use the same project id and dataset as the publish step.
• Fetch the schema before generating the document.
• Pass the schema into AI Prompt with the json filter.

Examples

Fetch case study schema

Fetch the caseStudy schema and pass it to AI Prompt before generating a draft document.

Outputs

• Sanity schema data for the selected document type.

Common pitfalls

• Fetching a schema from a different dataset than the publish target.
• Skipping schema context before asking AI to generate content.
• Assuming schema fetch validates the final publish payload.

Related guides

• Publish content to Sanity

Reference details

These details are generated from the workflow task registry and match the fields available in the builder.

Required fields

• projectId
• documentType

Variable-aware fields

Fields that accept variable references ({{ inputs.x }}, {{ steps.N.y }}) from the workflow's variable graph:

• documentType

Liquid template fields

Fields that are rendered through Liquid (variables plus filters and control flow):

• documentType

Builder guidance

When the Workflow Builder Genie configures this task, it follows this guidance:

Use before Sanity publish tasks that need schema context.

Default configuration

New instances of this task start with the following configuration:

{
  "name": "Sanity Fetch Schema",
  "outputKey": "sanity_fetch_schema",
  "taskType": "Sanity Fetch Schema",
  "description": "",
  "projectId": "",
  "dataset": "production",
  "documentType": ""
}