Universal Containers is very concerned about security compliance and wants to understand: - Which prompt text is sent to the large language model (LLM) - How it is masked - The masked response What sh

The correct answer is C. Enable audit trail in the Einstein Trust Layer.. The Einstein Trust Layer's Audit Trail feature logs the complete lifecycle of every AI interaction: the full prompt text sent to the LLM, which fields were masked (and how), and the response returned. This gives compliance teams a transparent, inspectable record of AI activity. I

AI Features for Service (e.g., Einstein Bots, Next Best Action)

Question

Universal Containers is very concerned about security compliance and wants to understand:

Which prompt text is sent to the large language model (LLM)
How it is masked
The masked response

What should the Agentforce Specialist recommend?

Options

AIngest the Einstein Shield Event logs into CRM Analytics.
BReview the debug logs of the running user.
CEnable audit trail in the Einstein Trust Layer.

How the community answered

(18 responses)

A
17% (3)
B
6% (1)
C
78% (14)

Explanation

The Einstein Trust Layer's Audit Trail feature logs the complete lifecycle of every AI interaction: the full prompt text sent to the LLM, which fields were masked (and how), and the response returned. This gives compliance teams a transparent, inspectable record of AI activity. Ingesting Einstein Shield Event logs into CRM Analytics (A) is a broader Shield Platform Event approach, not the purpose-built Trust Layer audit tool. Reviewing debug logs (B) captures Apex/system execution details but does not provide structured visibility into LLM prompt content or data masking-that information lives in the Trust Layer, not standard debug logs.

Topics

#LLM security#Einstein Trust Layer#Data masking#Audit trails

Community Discussion

No community discussion yet for this question.

Full AI-201 Practice