Turn on toxicity detection in prompts so you can monitor the prompts that have toxic language and modify them accordingly. These settings are applied to your Salesforce org.
Required Editions
| Available in: Enterprise, Performance, and Unlimited Editions with an Einstein for Sales, Einstein for Platform, Einstein for Service, Einstein 1 Service, or Einstein GPT Service add-on. To purchase add-ons, contact your Salesforce account executive. |
| User Permissions Needed | |
|---|---|
| To turn on toxicity detection in prompts: | View Setup |
| AND | |
| Customize Application | |
Einstein Generative AI must be enabled.
Toxicity detection in responses is turned on by default and can't be turned off. By turning on toxicity detection in prompts, you can monitor prompts that have problematic language that can lead to toxicity in responses.
Note Toxicity Detection in prompts is in Beta.
-
From Setup, in the Quick Find field, enter Einstein, and
then select Einstein Trust Layer.
Note If you can’t find Einstein Generative AI Setup, make sure that your org meets the prerequisites for any generative AI features you plan to use. For more support, contact your Salesforce account executive (AE).
- Click Safety & Security.
- Review the beta service terms. Turn on toxicity detection in prompts.
- Use the reports and dashboards in Data Cloud to review and analyze the toxicity scores and trends.
