Transform quick start

Get started with Transform by writing your first instructions to modify documents.

Transform is a Sanity Agent Action that lets you programmatically run schema-aware AI transformations on Sanity documents. You can run instructions from anywhere you can execute code, such as Sanity Functions, custom components, webhook listeners, CI/CD pipelines, migration scripts, and more.

In this guide, you'll use Transform to run a find/replace style instruction on content across multiple fields in a document. You'll use @sanity/client to create the instructions (you can also make requests using the HTTP API directly).

Prerequisites:

• @sanity/client v7.1.0 or higher and an environment to run client requests.
• API Version vX is required for any requests to the Agent Actions APIs.
• Optional: In Node.js v23.6 and above, you can run the TypeScript examples below without additional servers or build processes. Alternatively, you can use earlier versions with an experimental flag. Converting the examples to JavaScript is okay too.
• sanity CLI v3.88.0 or later.
• A Sanity project for testing. The examples below use details from the sample "Movies" studio schema that you can select when initializing a new project.
  • A read/write API token to authenticate requests.
  • A valid projectId and dataset name.

Agent Actions requires an uploaded schema. If you've deployed recently, you can check for a list of uploaded schemas by running the following command from your project directory:

sanity schema list

Copy the schema ID, which you'll need for the third step. If you don't see a schema or want to deploy the latest version, redeploy your studio to Sanity or deploy the schema.

To deploy your studio and schema together, run the following from your project directory:

sanity deploy

To deploy just the schema without your studio, run the following:

sanity schema deploy

Then, run the sanity schema list command again and copy the schema ID associated with your workspace, dataset, and project.

You can learn more about schema deployment here.

Import and configure @sanity/client with the projectId, dataset, API token, and an apiVersion of vX.

// instruction.ts

import { createClient } from "@sanity/client";

export const client = createClient({
    projectId: '<project-id>',
    dataset: '<datset-name>', // such as 'production'
    apiVersion: 'vX',
    token: '<editor-token>'
})

If you're already using the client elsewhere in an application, you can reuse its base configuration. If you need to adjust the token and/or API version, use the withConfig method to create a new client based on your existing one. For example:

// ...
const generateClient = client.withConfig({
  token: '<your-token>',
})

Transform uses the concept of an instruction. This is where you tell Transform what to do with the content in a document. In the simplest form, transform takes the following settings:

• schemaId: The ID of your schema.
• documentId: The documentId is defines both the source and the target document. This lets you run the transformation in-place. You can provide a published ID, draft ID, or a version ID.
• instruction: The instruction is where you tell the system how to act.

In this example, we create an instruction that changes the term "Alien" or "Aliens" in a movie document to "lifeform from outer space" and "lifeforms from outer space".

Update the code to include the following instruction, and change the document ID to a valid ID in your project, and the instruction to one that matches your content:

await client.agent.action.transform({
  // Replace with your schema ID
  schemaId: "sanity.workspace.schema.default",

  // Tell the client the ID of the document to transform.
  documentId: "<document-id>",

  // Provide an instruction, or prompt.
  instruction: "Change all instances of 'Alien' to 'Lifeform from another planet'. Match the case of the existing text.",
});

This code reads each field in the document and runs the instruction against them.

Run the code to see Transform edit the document and update the content. In the case of the example, it updated the movie's title and updated parts of the description.

Transform can also create new documents based on the content in the source. If you want to create new documents from scratch, give Generate a try instead.

In this step we'll modify the code from the previous example so that it will create a new document that uses the original document as the source, and we'll pass in parameters.

• Add targetDocument: This takes an operation type, create, and optionally an ID. If you provide an ID, Transform will populate that document. If you omit one, it will create a draft on the source documentId.
• Add instructionParams: The parameters can have any $key name you like. This example uses the field and const parameter types. Field targets a specific field in the source document, which, in this example is the title field. The const type uses a shorthand syntax to set it like a string.
• Update the instruction: Include the newly defined parameters, and prefix them with $. In the example, these are $title and $new.
• Add a target paths (optional): This example also adds explicit targets. Instead of affecting the whole document, only the paths set in target will see changes.

const docId = "<existing-document-id>";
await client.agent.action.transform({
  schemaId: "sanity.workspace.schema.default",
  // documentId is equivalent to targetDocument: {operation: 'edit', _id: docId }
  documentId: docId,
  targetDocument: {
    operation: 'create'
  },
  instruction: "Replace every instance of $title with $new. Match the case of the existing text.",
  instructionParams: {
    title: {
      type: "field",
      path: "title",
    },
    new: "lifeforms from outer space"
  },
  target: [
    { path: ['title', 'overview'] }
  ]
});

Field-type instruction parameters expect a path leading to fields in the document. In this case, it uses the title field to read the title.

Another approach is to use a GROQ-type query and capture the whole or parts of other documents as context.

await client.agent.action.transform({
  // ...
  instructionParams: {
    title: {
      type: "groq",
      query: `*[_id == "some-other-document-id"].title`,
    },
  },
  // ...
});

GROQ-type instruction parameters take a GROQ query and pass the result to the parameter. In this case, it passes the titles of other movie documents in our dataset.

This example also introduces the target parameter, and its child path. Target lets you explicitly tell the instruction which fields to write to. This is a really powerful field, and can even take field-level instruction requests. Check out more examples of target in the cheat sheet.

Run the example to see a new draft populate for your document.

These examples run once, but you can loop over multiple documents, build multi-step workflows, custom components, and much more. The resources below provide additional examples and details.