The Processing Tool in Agent Copilot simplifies API responses by converting them into readable formats. It works with the API Tool to handle large datasets and allows custom formatting to match user needs.

Key Benefits

• Improved Readability: Converts complex API data into clear, easy-to-understand formats for quicker decision-making.

• Customizable Formats: Allows tailoring of data presentation to fit specific business needs.

• Faster, Accurate Responses: Speeds up processing and reduces errors, enhancing customer satisfaction.

Use Case: Customer Service Support with Processing Tool

In a customer service scenario, an agent needs to quickly interpret data from multiple APIs to assist a customer. Using the Text Processing Tool, the agent can receive API responses in a clear, structured format, making the data easy to understand and act upon.

For instance, when a customer inquires about their order status, the Text Processing Tool automatically formats the API response to present key information such as order details, shipping status, and expected delivery date. This streamlined presentation allows the agent to provide a faster, more accurate response, improving the overall customer experience by reducing response time and minimizing the risk of errors.

Steps to Configure the Processing Tool

Follow the steps below to configure the Update Properties Tool in AI Agent Studio:

​

1. Access the Processing Tool

• Navigate to Agent Copilot from the Sprinklr Launchpad.

• Select the Agent Copilot you want to configure.

• Expand the Define Tasks and Tools section and open Tools.

• Click + Add Tool and select Processing Tool from the list.
  

2. Define Basic Details

• Name: Enter a unique name to identify the tool.

• Description: Provide a brief description of the tool’s purpose.

3. Configure Setup Function

The Setup Function defines how the Processing Tool transforms raw API responses into a clean, readable, and structured format. The Processing Tool typically works after the API Tool, using its output as input for further processing.

Use this section to control formatting rules, manage large datasets, and extract specific fields required by your workflow.

System Prompt

Use the System Prompt to define how the API response should be processed.

• Specify formatting rules, constraints, and transformation logic.

• Clearly describe what information to extract and how to present it.

The system prompt guides the Processing Tool on how to interpret and restructure the incoming data. 

User Text

The User Text field specifies the variable that contains the API response.

• Enter the variable in the format: ${variable}

• This variable is typically generated by the API Tool.

This ensures the Processing Tool knows which data to process.

Output Variable

Use Output Variable to store the processed result.

• The processed output can be reused in downstream tasks, responses, or tools.

• Choose a clear and descriptive variable name.

Chunking

Enable Chunking when processing large API responses.

Chunking splits large datasets into smaller parts to prevent token limits and improve accuracy.

Chunk Size

• Defines the size of each chunk (in tokens).

• Supported range: 1024–4096 tokens.

​

Overlap Size

• Specifies the number of overlapping tokens between chunks.

• Prevents data loss between chunks.

• Supported range: 256–820 tokens.

​

Best practice: Use overlap when data continuity is important, such as summaries or lists.

Extract Fields

Enable Extract Fields when you want the Processing Tool to return structured outputs instead of free-form text.

This option allows you to define a schema for the processed data. 

Function Name

Provide a Function Name to identify the processing logic.

• Use a short, action-oriented name.

• This name is referenced internally when the function is executed.

Function Description

Describe what the function does and when it should be used.

Configure Fields

Use the Configure Fields section to define the output schema when Extract Fields is enabled.

For each field, specify:

• Name: Output field name (for example, orderStatus)

• Description: What the field represents

• Type: Data type (for example, String)

• Required: Whether the field is mandatory

• Multi-valued: Whether the field can contain multiple values

This structured output makes the data easier to reuse across tasks and tools.

Click Save to add the Processing Tool to your Agent Copilot.

How the Setup Function Works Together

1. The API Tool fetches data from an external system.

2. The Processing Tool receives the API output via User Text.

3. The System Prompt defines how the data is transformed.

4. Optional Chunking handles large datasets.

5. Optional Field Extraction produces structured, reusable outputs.

6. The result is stored in the Output Variable for downstream use.
   

A well-configured Setup Function ensures that complex API responses are converted into accurate, readable, and reusable formats; helping agents respond faster, reduce errors, and deliver better customer experiences.