Generative Prompt

Inputs

Name	Type	Description
Prompt	String	The LLM prompt
Temperature	Number	Measure of randomness in generated text (tune only if you know the impact)
Model	String	The LLM model to use
Response Format	Optional Object	Optional response format (JSON schema). Omit for free-form text.

Model options: gemini-2.5-flash, azure-gpt-4o-mini, azure-gpt-4o, azure-gpt-5-mini, azure-gpt-5

Outputs

Name	Type	Description
Response	String	The LLM response
Success	Boolean	Whether the call was successful

Response format example

Use the Response Format input to constrain the LLM output to a JSON structure. Example:

{
  "type": "json_schema",
  "json_schema": {
    "name": "ConversationEvaluation",
    "description": "An evaluation of an E-commerce customer service conversation for a given criteria.",
    "schema": {
      "type": "object",
      "properties": {
        "explanation": {
          "description": "The explanation for the verdict, based on the rubric and conversation evidence.",
          "type": "string"
        },
        "score": {
          "description": "A score for the criterion on a 0.0-1.0 scale (in 0.1 increments)",
          "type": "number"
        }
      },
      "required": ["explanation", "score"],
      "additionalProperties": false
    }
  }
}

This produces structured output with explanation (string) and score (number).

Notes

The formatted response is returned as a string. If you expect an object, use the JSON Parse utility activity.