You are here:
Prompt Builder Usage, and Feedback Metrics Control
Monitors the adoption and quality of specific Einstein prompt templates by tracking generation counts and user-submitted feedback.
Control Name
Einstein Prompt Builder Usage, and Feedback Metrics
Control Overview
Monitors the adoption and quality of specific Einstein prompt templates by tracking generation counts and user-submitted feedback.
Description
Enables the capture of template-specific performance data. This includes how often a template is triggered and the associated feedback reasons.
Recommended Configuration
From Setup, in the Quick Find box, enter Einstein Audit, and then select “Einstein Audit, Analytics, and Monitoring Setup”. Turn on “Prompt Builder Usage and Feedback Metrics”. Assign the "Prompt Template Manager" permission to admins to review these metrics.
Security Impact
Identifies variation in AI performance where prompt templates may start producing lower-quality or risky responses due to changes in underlying CRM data.
Business Impact
Enables a data-driven ROI analysis of generative AI by showing which departments are actually using the tools and which templates require engineering improvements to be useful.
Security Risk If Not Configured
Companies remain unaware of the effectiveness of their prompts. Low-quality or misleading AI responses may be used by employees without a formal feedback loop for correction.
Threat Scenarios
Unnoticed Hallucinations: A template consistently generates incorrect data, but because metrics are off, admins are unaware that users are manually correcting (or ignoring) the AI.
Estimated CVSS Score Range
Critical (9.0–10.0).
Risk Impact Considerations
High impact for companies scaling AI across large teams where manual spot-checking of AI interactions is no longer feasible. With higher usage, implementing regular monitoring of these logs becomes a crucial step to result in the full benefit of this feature.
Higher Risk When
Custom review/feedback steps for the prompts are not configured, leaving admins with limited data but no context as to why the response failed.
Low Risk When
A process has been implemented to review prompt template usage metrics regularly and poorly performing templates are iteratively refined in a sandbox.
Business and Integration Considerations
Storage Costs: This data consumes Data Cloud credits. Latency: Audit data can take up to 24 hours to appear in reports.
Security Health Review Guidance
Security Health Review verifies the "Enabled" status of the Prompt Builder Usage and Feedback Metrics and flags instances where prompt template usage metrics are not logged, preventing the company from improving its AI safety.
Who Is Impacted
Data governance officers, AI admins, customer service managers, and legal/compliance auditors.
