Classify and route your data using Content Understanding Studio

Content Understanding Studio enables you to create custom classification workflows that route your data to the right custom analyzer. With routing, you can input multiple different data streams into the same pipeline and ensure your data is always routed to the best analyzer.

Prerequisites

To get started, make sure you have the following resources and permissions:

An Azure subscription. If you don't have an Azure subscription, create a free account.
Once you have your Azure subscription, create a Microsoft Foundry resource in the Azure portal. Be sure to create it in a supported region.
- This resource is listed under Foundry > Foundry in the portal.
Set up default model deployments for your Content Understanding resource. Setting defaults creates a connection to the Foundry models you use for Content Understanding requests. Choose one of the following methods:
- Portal
- REST API
1. Go to the Content Understanding settings page
2. Select the "+ Add resource" button in the upper left
3. Select the Foundry resource that you want to use and click Next, then Save
  - Make sure to leave "Enable autodeployment for required models if no defaults are available." checked. This ensures your resource is fully set up with the required GPT-4.1, GPT-4.1-mini, and text-embedding-3-large models. Different prebuilt analyzers require different models.
By taking these steps, you set up a connection between Content Understanding and Foundry models in your Foundry resource.
1. Create Foundry Model deployments of GPT-4.1, GPT-4.1-mini, and text-embedding-3-large in your Foundry resource. For details on how to deploy these models, see Create model deployments in Microsoft Foundry portal. Different prebuilt analyzers require different models, so you need to deploy all three.
2. Define default model deployments at the resource level.
  
  Before running the following cURL command, make the following changes to the HTTP request:
  - Replace {endpoint} and {key} with the corresponding values from your Foundry instance in the Azure portal.
  - Replace {myGPT41Deployment}, {myGPT41MiniDeployment}, and {myEmbeddingDeployment} with your actual model deployment names from your Foundry resource.
```
curl -i -X PATCH "{endpoint}/contentunderstanding/defaults?api-version=2025-11-01" \
  -H "Ocp-Apim-Subscription-Key: {key}" \
  -H "Content-Type: application/json" \
  -d '{
        "modelDeployments": {
          "gpt-4.1": "{myGPT41Deployment}",
          "gpt-4.1-mini": "{myGPT41MiniDeployment}",
          "text-embedding-3-large": "{myEmbeddingDeployment}"
        }
      }'
```
By taking these steps, you set up a connection between Content Understanding and Foundry models in your Foundry resource.

Go to the Content Understanding Studio portal and sign in with your credentials. You might recognize the classic Azure Document Intelligence in Foundry Tools Studio experience. Content Understanding extends the same content and field extraction that you're familiar with in Document Intelligence across all modalities - document, image, video, and audio. Select the option to try out the new Content Understanding experience to get all of the multimodal capabilities of the service.

Create your custom categories

Custom categories let you route your data to a specific analyzer so you get the best output based on the type of data. In this guide, you learn how to classify invoice documents based on the client that provided them. Documents for different clients might have a different structure depending on the unique business agreement in place. This classification workflow ensures that the documents are analyzed with the correct context. To successfully route your data, you might want to create custom analyzers to route to depending on your scenario. For more information on building custom analyzers, see Create and improve your custom analyzer in Content Understanding Studio.

Start with a new project: To get started with creating your custom classification workflow, select Create project on the home page.
Select your project type: For this scenario, select the option to Classify and route with custom categories. To learn more about creating custom analyzers for content and field extraction, see Create and improve your custom analyzer in Content Understanding Studio.
Upload your data: To get started with classifying, upload a piece of sample data.
Create routing rules: Under the Routing rules tab, select Add category. Give the category a name and description, and select an analyzer to correspond to that route. For example, if you're analyzing invoices from multiple clients that each require custom schemas, you can route to the custom analyzer that was built for that specific invoice type. The tool allows you to preview the schema for each analyzer to ensure you have the right one.
Test your classification workflow: When your custom routing rules are ready for testing, select Run analysis to see the output of the rules on your data. You can optionally upload additional pieces of sample data for testing to see how it performs with multiple different rules.
Build your classification analyzer: When you’re satisfied with the output, select the Build analyzer button at the top of the page. Give the analyzer a name and select Save.
Use your classification analyzer: Now you have an analyzer endpoint that you can use in your own application via the REST API.

Next step

Learn more about Best practices for Azure Content Understanding in Foundry Tools

Feedback

Was this page helpful?

Last updated on 2025-11-20

Share via

Classify and route your data using Content Understanding Studio

Prerequisites

Sign in to Content Understanding Studio

Create your custom categories

Next step

Feedback

Additional resources