Thestandard Einstein Copilot actionthat would be used in response to the user utterance, "Show me all the customers in New York," isQuery Records. This action is responsible for retrieving a set of records from Salesforce based on a specified condition - in this case, filtering customers by location (New York).
* Query Recordsis the action that fetches relevant data based on the criteria provided in the user's input.
* Select Recordsis more about picking specific records from an already presented list.
* Fetch Recordsis not a standard term used in this context for the action.
Refer toEinstein Copilot documentationon how Copilot actions work with natural language queries and data retrieval.

To enable Sales Email prompt templates:
* Permission Set: Assign the Prompt Template User permission set to the sales team to grant access to use pre-built templates.
* Feature Activation: Enable Sales Emails in Salesforce Setup to activate the integration between prompt templates and email workflows.
* Option B (Manager permission set): Required for creating/modifying templates, not for usage.
* Option C (Data Cloud Admin): Unrelated to prompt template access.
References:
* Salesforce Help: Prompt Template Permissions
* Specifies that "Prompt Template User" is required to leverage templates in workflows.
* Sales Email Setup outlines enabling the feature in Setup.

For sales reps who need to draft personalized emails based on previous communications, the AI Specialist should recommend theEinstein Copilot Action: Draft or Revise Sales Email. This action uses AI to generate or revise email content, leveraging past successful communications to create personalized and relevant outreach to prospects or clients.
* Find Similar Opportunitiesis used for opportunity matching, not email drafting.
* Summarize Recordprovides a summary of customer data but does not directly help with drafting emails.
For more information, refer toSalesforce's Einstein Copilot documentationon standard actions for sales teams.

The Einstein Trust Layer is designed to ensure responsible and compliant AI usage. Data Masking (B) is the mechanism that directly addresses compliance with data protection regulations like GDPR by obscuring or anonymizing sensitive personal data (e.g., names, emails, phone numbers) before it is processed by AI models. This prevents unauthorized exposure of personally identifiable information (PII) and ensures adherence to privacy laws.
Salesforce documentation explicitly states that Data Masking is a core component of the Einstein Trust Layer, enabling organizations to meet GDPR requirements by automatically redacting sensitive fields during AI interactions. For example, masked data ensures that PII is not stored or used in AI model training or inference without explicit consent.
In contrast:
* Toxicity Scoring (A) identifies harmful or inappropriate content in outputs but does not address data privacy.
* Prompt Defense (C) guards against malicious prompts or injection attacks but focuses on security rather than data protection compliance.

Event Logs in Salesforce capture detailed interaction data, including agent errors, triggered actions, and incomplete plans. These logs provide visibility into user-Agent interactions for troubleshooting performance issues. The Einstein Bot Analytics documentation highlights Event Logs as the primary source for auditing bot behavior and diagnosing issues like misconfigured actions or plan execution failures.
* Plan Canvas (B) is for designing workflows, not auditing.
* Agent Settings (C) control configuration but do not store interaction history.