Universal Containers is considering leveraging the Einstein Trust Layer in conjunction with Einstein Generative AI Audit Data. Which audit data is available using the Einstein Trust Layer?

Question

Options

• AResponse accuracy and offensiveness score
• BHallucination score and bias score
• CMasked data and toxicity score

• A
  8% (3)
• B
  3% (1)
• C
  90% (36)

Explanation

The Einstein Trust Layer provides a set of trust and safety capabilities for generative AI in Salesforce. Its audit log captures what data was masked (PII/sensitive data masked before being sent to the LLM) and toxicity scores (evaluating whether generated content contains harmful or inappropriate language). Response accuracy and hallucination scores (options A and B) are not metrics surfaced by the Trust Layer audit - those would require external evaluation frameworks. The Trust Layer focuses on data privacy (masking) and content safety (toxicity).

No community discussion yet for this question.