---
schema_version: "1"
id: 922dfcf94982bc032f4e4d6d0a24fd6427849f0c16991135557dadd3c57d6f87
title: Test Your Prompt
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/data/264-0-0/c360_a_ai_foundation_models_configured_prompts.md
canonical_url: https://help.salesforce.com/s/articleView?id=data.c360_a_ai_foundation_models_configured_prompts.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 5ad02efaff7fc996c9fda43ed303a946445c335a61a605bb3eda5867d5d22ca6
description: Before you put a model into production, test it using prompts in Model Playground to evaluate the generated responses based on your model’s hyperparameter settings.
products:
  - Data 360
release: "264"
---
# Test Your Prompt

Before you put a model into production, test it using prompts in Model Playground to evaluate the generated responses based on your model’s hyperparameter settings.

1. In Model Playground, enter a prompt, such as a question or task.
    
    For example, enter a prompt to create an email to offer a new customer an online deal.
2. Click **Settings**.
3. Enter the number of responses for each prompt and the stop sequence.
4. Enable data masking to mask sensitive information during testing. If you don’t enable masking in Model Playground, org-level data masking settings are applied.
    
    These prompt settings are used only during testing. They aren’t saved with your model configuration.
5. To get a prompt response, click **Generate**.
6. To evaluate your prompt, click **Debug**.
7. If you’re satisfied with the quality of your test prompt, save your work and exit Model Playground.