What considerations should an Agentforce Specialist be aware of when using Record Snapshots grounding in a prompt template?

1. A. Activities such as tasks and events are excluded.
2. B. Empty data, such as fields without values or sections without limits, is filtered out.
3. C. Email addresses associated with the object are excluded.

Correct Answer: A
Comprehensive and Detailed In-Depth Explanation:Record Snapshots
grounding in Agentforce prompt templates allows the AI to access and use data from a specific Salesforce record (e.g., fields and related records) to generate contextually relevant responses. However, there are specific limitations to consider. Let??s analyze each option based on official documentation.
✑ Option A: Activities such as tasks and events are excluded.According to Salesforce Agentforce documentation, when grounding a prompt template with Record Snapshots, the data included is limited to the record??s fields and certain related objects accessible via Data Cloud or direct Salesforce relationships. Activities (tasks and events) are not included in the snapshot because they are stored in a separate Activity object hierarchy and are not directly part of the primary record??s data structure. This is a key consideration for an Agentforce Specialist, as it means the AI won??t have visibility into task or event details unless explicitly provided through other grounding methods (e.g., custom queries). This limitation is accurate and critical to understand.
✑ Option B: Empty data, such as fields without values or sections without limits, is filtered out.Record Snapshots include all accessible fields on the record, regardless of whether they contain values. Salesforce documentation does not indicate that empty fields are automatically filtered out when grounding a prompt template. The Atlas Reasoning Engine processes the full snapshot, and empty fields are simply treated as having no data rather than being excluded. The phrase "sections without limits" is unclear but likely a typo or misinterpretation; it doesn??t align with any known Agentforce behavior. This option is incorrect.
✑ Option C: Email addresses associated with the object are excluded.There??s no specific exclusion of email addresses in Record Snapshots grounding. If an email field (e.g., Contact.Email or a custom email field) is part of the record and accessible to the running user, it is included in the snapshot. Salesforce documentation does not list email addresses as a restricted data type in this context, making this option incorrect.
Why Option A is Correct:The exclusion of activities (tasks and events) is a documented limitation of Record Snapshots grounding in Agentforce. This ensures specialists design prompts with awareness that activity-related context must be sourced differently (e.g., via Data Cloud or custom logic) if needed. Options B and C do not reflect actual Agentforce behavior per official sources.
References:
✑ Salesforce Agentforce Documentation: Prompt Templates > Grounding with Record Snapshots – Notes that activities are not included in snapshots.
✑ Trailhead: Ground Your Agentforce Prompts – Clarifies scope of Record Snapshots data inclusion.
✑ Salesforce Help: Agentforce Limitations – Details exclusions like activities in
grounding mechanisms.

Which object stores the conversation transcript between the customer and the agent?

1. A. Messaging End User
2. B. Messaging Session
3. C. Case

Correct Answer: B
Why is "Messaging Session" the correct answer?
In Agentforce, the Messaging Session object stores the conversation transcript
between the customer and the agent.
Key Features of the Messaging Session Object:
✑ Stores the Entire Customer-Agent Conversation
✑ Supports AI-Powered Work Summaries
✑ Links with Service Cloud for Case Resolution
Why Not the Other Options?
* A. Messaging End User
✑ Incorrect because this object stores details about the customer (e.g., name, contact details) but not the conversation transcript.
* C. Case
✑ Incorrect because Cases store structured service requests but do not contain raw conversation transcripts.
✑ Instead, cases may reference the Messaging Session object.
Agentforce Specialist References
✑ Salesforce AI Specialist Material confirms that Messaging Sessions store chat conversations and support Einstein Work Summaries.

An administrator is responsible for ensuring the security and reliability of Universal Containers' (UC) CRM data. UC needs enhanced data protection and up-to-date AI capabilities. UC also needs to include relevant information from a Salesforce record to be merged with the prompt. Which feature in the Einstein Trust Layer best supports UC's need?

1. A. Data masking
2. B. Dynamic grounding with secure data retrieval
3. C. Zero-data retention policy

Correct Answer: B
Dynamic grounding with secure data retrieval is a key feature in Salesforce's Einstein Trust Layer, which provides enhanced data protection and ensures that AI- generated outputs are both accurate and securely sourced. This feature allows relevant Salesforce data to be merged into the AI-generated responses, ensuring that the AI outputs are contextually aware and aligned with real-time CRM data.
Dynamic grounding means that AI models are dynamically retrieving relevant information from Salesforce records (such as customer records, case data, or custom object data) in a secure manner. This ensures that any sensitive data is protected during AI processing and that the AI model??s outputs are trustworthy and reliable for business use. The other options are less aligned with the requirement:
✑ Data masking refers to obscuring sensitive data for privacy purposes and is not related to merging Salesforce records into prompts.
✑ Zero-data retention policy ensures that AI processes do not store any user data after processing, but this does not address the need to merge Salesforce record information into a prompt.
References:
✑ Salesforce Developer Documentation on Einstein Trust Layer
✑ Salesforce Security Documentation for AI and Data Privacy

Universal Containers wants to allow its service agents to query the current fulfillment status of an order with natural language. There is an existing auto launched flow to query the information from Oracle ERP, which is the system of record for the order fulfillment process.
How should An Agentforce apply the power of conversational AI to this use case?

1. A. Create a Flex prompt template in Prompt Builder.
2. B. Create a custom copilot action which calls a flow.
3. C. Configure the Integration Flow Standard Action in Agent.

Correct Answer: B
To enable Universal Containers service agents to query the current fulfillment status of an order using natural language and leverage an existing auto-launched flow that queries Oracle ERP, the best solution is to create a custom copilot action that calls the flow. This action will allow Agent to interact with the flow and retrieve the required order fulfillment information seamlessly. Custom copilot actions can be tailored to call various backend systems or flows in response to user requests.
✑ Option B is correct because it enables integration between Agent and the flow that
connects to Oracle ERP.
✑ Option A (Flex prompt template) is more suited for static responses and not for invoking flows.
✑ Option C (Integration Flow Standard Action) is not directly related to creating a specific copilot action for this use case.
References:
✑ Salesforce Agent Actions: https://help.salesforce.com/s/articleView?id=einstein_copilot_actions.htm

What is the primary function of the planner service in the Agent system?

1. A. Generating record queries based on conversation history
2. B. Offering real-time language translation during conversations
3. C. Identifying copilot actions to respond to user utterances

Correct Answer: C
The primary function of the planner service in the Agent system is to identify copilot actions that should be taken in response to user utterances. This service is responsible for analyzing the conversation and determining the appropriate actions (such as querying records, generating a response, or taking another action) that the Agent should perform based on user input.