Configuring Agent Operations

Configure the Agent Define Prompt Template Operation

Use the Agent define prompt template operation to use specific prompt templates with your LLMs. This allows you to create natural language prompts that generate responses, extract information, invoke other prompts, or perform any text-based task.

To configure the Agent define prompt template operation:

Select the operation on the Anypoint Code Builder or Studio canvas.
In the General properties tab for the operation, enter these values:
- Dataset
  
  Specify the dataset for the LLM to evaluate using the provided template and instructions.
- Template
  
  Enter the prompt template for the operation.
- Instructions
  
  Provide the instructions for the LLM, outlining the goals of the task. This is the XML for this operation:

<ms-chainai:agent-define-prompt-template
  doc:name="Agent define prompt template"
  doc:id="f1c29c39-eac9-468c-9c46-4109a66303ec"
  config-ref="MuleChain_AI_Llm_configuration"
  template="#[payload.template]"
  instructions="#[payload.instructions]"
  dataset="#[payload.dataset]"
/>

This image shows an example of the configuration for the Agent define prompt template action in Anypoint Code Builder: Anypoint Code Builder canvas with Agent define prompt template highlighted, configuration attributes filled in, and the XML code for the configured action

Output Configuration

This operation responds with a JSON payload containing the main LLM response. Additionally, attributes such as token usage are included as part of the metadata (attributes) but not within the main payload.

This is an example response:

{
  "response": "{\n  \"type\": \"positive\",\n  \"response\": \"Thank you for your positive feedback on the training last week. We are glad to hear that you had a great experience. Have a nice day!\"\n}"
}

The operation also returns attributes that aren’t within the main JSON payload, which include information about token usage, for example:

{
  "tokenUsage": {
      "outputCount": 9,
      "totalCount": 18,
      "inputCount": 9
  },
  "additionalAttributes": {}
}

tokenUsage

Token usage metadata returned as attributes
outputCount

Number of tokens used to generate the output
totalCount

Total number of tokens used for input and output
inputCount

Number of tokens used to process the input

Configuring Agent Operations

Configure the Agent Define Prompt Template Operation

Output Configuration

See Also