Create, edit, and evaluate your model configuration in Model Playground without the need for setup or specialized technical expertise. Model Playground uses a trust layer, which ensures data privacy and security.
- Create a Model Configuration
After you add a foundation model, you can create an associated model configuration for a specific use case. - Data Masking
Data masking settings in your Salesforce org and Model Playground determine the privacy of sensitive information and how that data is surfaced in a prompt response. Org-level settings are enabled by default. - Edit a Model Configuration
Try different prompts and adjust your hyperparameters to evaluate how well the model responds to your prompts. However, if your model is already associated with prompts, create a new model instead. Updating model settings can affect the performance of associated prompts. - 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. - Create a Prompt Template
If you're satisfied with your model's response to one or more test prompts in Model Playground, create your prompt templates.