Question 31
Choose 1
Universal Containers tests out a new Einstein Generative AI feature for its sales team to create personalized and contextualized emails for its customers. Sometimes, users find that the draft email contains placeholders for attributes that could have been derived from the recipient’s contact record. What is the most likely explanation for why the draft email shows these placeholders?
Correct answer:
A. The user does not have permission to access the fields.
Explanation:
In Salesforce Einstein Generative AI features — such as personalized email generation — the system can pull data dynamically from related records like Contact, Opportunity, or Account. However, if the user lacks field-level security (FLS) access to specific fields, then:
1. Those fields cannot be included in the AI prompt grounding.
2. The output may display placeholders (e.g., {FirstName}, {CompanyName}) instead of actual values.
This behavior ensures data security by adhering to Salesforce’s Trust Layer, which prevents the AI from accessing or displaying data the user is not authorized to see.
🔐 Example:
If the user doesn't have access to the "Contact.FirstName" field, the AI draft email may show:
"Hello {FirstName},"
instead of
"Hello Alice,"
📘 Salesforce Documentation Reference:
"Einstein features honor user-level security and field-level access. If a user doesn’t have access to a field, the AI model will not be able to use that data."
— Salesforce Trust Layer Overview
❌ Why the other options are incorrect:
B. The user’s locale language is not supported by Prompt Builder
❌ Incorrect – Locale support affects language output, not whether data is retrieved from fields or replaced by placeholders.
C. The user does not have Einstein Sales Emails permission assigned
❌ Incorrect – Without this permission, the user wouldn’t be able to use the feature at all. Since the user can see the draft (with placeholders), this isn’t the root cause.
✅ Summary:
When draft emails show unresolved placeholders instead of actual values, it’s most likely because the user lacks permission to access the relevant fields used in the prompt.
In Salesforce Einstein Generative AI features — such as personalized email generation — the system can pull data dynamically from related records like Contact, Opportunity, or Account. However, if the user lacks field-level security (FLS) access to specific fields, then:
1. Those fields cannot be included in the AI prompt grounding.
2. The output may display placeholders (e.g., {FirstName}, {CompanyName}) instead of actual values.
This behavior ensures data security by adhering to Salesforce’s Trust Layer, which prevents the AI from accessing or displaying data the user is not authorized to see.
🔐 Example:
If the user doesn't have access to the "Contact.FirstName" field, the AI draft email may show:
"Hello {FirstName},"
instead of
"Hello Alice,"
📘 Salesforce Documentation Reference:
"Einstein features honor user-level security and field-level access. If a user doesn’t have access to a field, the AI model will not be able to use that data."
— Salesforce Trust Layer Overview
❌ Why the other options are incorrect:
B. The user’s locale language is not supported by Prompt Builder
❌ Incorrect – Locale support affects language output, not whether data is retrieved from fields or replaced by placeholders.
C. The user does not have Einstein Sales Emails permission assigned
❌ Incorrect – Without this permission, the user wouldn’t be able to use the feature at all. Since the user can see the draft (with placeholders), this isn’t the root cause.
✅ Summary:
When draft emails show unresolved placeholders instead of actual values, it’s most likely because the user lacks permission to access the relevant fields used in the prompt.
