TheAI audit trailin Salesforce provides a detailed log of AI activities, including the data used, its handling, and masking procedures applied in the Einstein Trust Layer. It allows the AI Specialist to inspect and verify that sensitive data, such as addresses, is appropriately masked before being used in prompts or outputs.
* Enable data encryption on the address field: While encryption ensures data security at rest or in transit, it does not verify masking in AI operations.
* Review the platform event logs: Platform event logs capture system events but do not specifically focus on the handling or masking of sensitive data in AI processes.
* Inspect the AI audit trail: This is the most relevant option, as it provides visibility into how data is processed and masked in AI activities.

* Sales Email Template Use Case:When creating a Sales email template (especially for outreach or follow-up), you often need to reference relevant details about the Account linked to the recipient.
* Standard Merge Fields in Salesforce Email Templates:
* Recipient(Contact, Lead, or Person receiving the email)
* Sender(User sending the email)
* Recipient Account(the Account related to that Contact, providing company-level details and other relevant data)
* Why Recipient Account?
* For Sales communications, referencing theAccountdata (e.g., Account name, industry, or other custom fields) in an email is very common.
* This is especially important for B2B scenarios where the Contact is tied to an Account.
* "Recipient Opportunities" could be multiple, so it's less direct for standard email merges. The
"User Organization" is more generic internal information, not typically inserted for personalization to the recipient.
* References and Study Resources:
* Salesforce Help & Training#Email Templates: Merge Fields
* Salesforce Trailhead#"Create and Customize Email Templates in Sales Cloud"
* Salesforce AI Specialist Study Resources(covers recommended best practices for leveraging standard objects like Account in AI-powered or prompt-based communications)

To allow a data scientist to view and manage models in Einstein Studio and create prompt templates in Prompt Builder, the AI Specialist should assign the Data Cloud Admin and Prompt Template Manager permission sets.
* Data Cloud Admin provides access to manage and oversee models within Einstein Studio.
* Prompt Template Manager gives the user the ability to create and manage prompt templates within Prompt Builder.
* Option A is correct because it assigns the necessary permissions for both managing models and creating prompt templates.
* Option B and Option C are incorrect as they do not provide the correct combination of permissions for managing models and building prompts.
References:
* Salesforce Permissions Documentation: https://help.salesforce.com/s/articleView?id=sf.
perm_sets_overview.htm

Action Instructions are critical for defining how a custom Agent action should be executed, ensuring alignment with the intended user experience. They provide step-by-step guidance to the bot or LLM on logic, data handling, and integration workflows, directly impacting how users interact with the action. For example, clear instructions prevent errors in API calls or data processing, ensuring seamless interactions.
Salesforce documentation states that poorly defined instructions lead to mismatched expectations, while well- structured instructions ensure the action behaves predictably. This aligns with delivering a consistent user experience.
* A refers to user invocation, which is handled by dialogue flows, not instructions.
* B is incorrect because the LLM selects actions based on context/intent, not instructions.

Salesforce has restrictions on which objects and related lists can be used for grounding prompt templates. This is likely due to security and privacy concerns related to user data.
While it might seem intuitive to use the User related list to provide context to the LLM, Salesforce prevents this to ensure that sensitive user information is not inadvertently exposed or misused.
Therefore, the AI Specialist needs to explore alternative ways to incorporate the necessary user information into the prompt template, perhaps by using other related objects or fields that are supported.