nerdexam
Salesforce

AI-201 · Question #112

Universal Containers wants to be able to detect with a high level confidence if content generated by a large language model (LLM) contains toxic language. Which action should an Al Specialist take in

The correct answer is C. Create a Trust Layer audit report within Data Cloud that uses a toxicity detector type filter to. Creating a Trust Layer audit report in Data Cloud with a toxicity detector type filter provides a scalable, queryable view of all LLM interactions where toxicity detection ran-including scores and outcomes. This gives a high-confidence, systematic way to validate the feature is w

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

Question

Universal Containers wants to be able to detect with a high level confidence if content generated by a large language model (LLM) contains toxic language. Which action should an Al Specialist take in the Trust Layer to confirm toxicity is being appropriately managed?

Options

  • AAccess the Toxicity Detection log in Setup and export all entries where isToxicityDetected is true.
  • BCreate a flow that sends an email to a specified address each time the toxicity score from the
  • CCreate a Trust Layer audit report within Data Cloud that uses a toxicity detector type filter to

How the community answered

(44 responses)
  • A
    11% (5)
  • B
    7% (3)
  • C
    82% (36)

Explanation

Creating a Trust Layer audit report in Data Cloud with a toxicity detector type filter provides a scalable, queryable view of all LLM interactions where toxicity detection ran-including scores and outcomes. This gives a high-confidence, systematic way to validate the feature is working across all transactions. Option A is incorrect because there is no dedicated 'Toxicity Detection log' export in Setup structured that way. Option B describes a custom Flow-based notification approach, which is not a standard Salesforce mechanism for auditing Trust Layer toxicity and would not provide the breadth of data needed for confident validation.

Topics

#LLM Safety#AI Trust Layer#Toxicity Management#Data Cloud Auditing

Community Discussion

No community discussion yet for this question.

Full AI-201 Practice