You are a data scientist who needs to view and manage models in Einstein Studio.

You
also need to create prompt templates in Prompt Builder.

Which permission sets should you assign to the data scientist?

● Prompt Template User and Data Cloud Admin

● Prompt Template Manager and Prompt Template User
● Data Cloud Admin and Prompt Template Manager

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_build_template.htm&type
=5

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_get_to_know.htm&type=5

You are considering using a Field Generation prompt template type.

What should you check before creating the Field Generation prompt to ensure it is
possible for the field to be enabled for generative AI?

● That the field chosen must be a rich text field with 255 characters or more
● The Lightning page layout where the field will reside has been upgraded to Dynamic
Forms
● That the org is set to API version 59 or higher

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_add_field_gen_to_lightnin
g_record_page.htm&type=5

you configured Data Masking within the Einstein Trust Layer.

How should you begin validating that the correct fields are being masked?

● Request the Einstein Generative AI Audit Data from the Security section of the Setup
menu.
● Enable the collection and storage of Einstein Generative Al Audit Data on the
Einstein Feedback setup page.
● Use a Flow-based resource in Prompt Builder to debug the fields' merge values using
Flow Debugger.
Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_feedback_enable.htm&type=
5

You want to create a new Sales Email prompt template in Prompt Builder using the
"Save As" function. However, UC notices that the new template produces different
results compared to the standard Sales Email prompt due to missing hyperparameters.

What should UC do to ensure the new prompt template produces results comparable to
the standard Sales Email prompts?

● Revert to using the standard template without modifications.

● Manually add the hyperparameters to the new template
● Use Model Playground to create a model configuration with the specified
parameters.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_standard_prompt_templat
es.htm&type=5

Your current AI data masking rules do not align with organizational privacy and security
policies and requirements.

What should you recommend to resolve the issue?

● Configure data masking in the Einstein Trust Layer setup

● Add new data masking rules in LLM setup.
● Enable data masking for sandbox refreshes.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_trust_setup.htm&type=5

You want to assess Salesforce's generative AI features but have concerns over its
company data being exposed to third-party large language models (LLMs). Specifically,
UC wants the following capabilities to be part of Einstein's generative Al service.

○ No data is used for LLM training or product improvements by third-party LLMs.
○ No data is retained outside of UC's Salesforce org.
○ The data sent cannot be accessed by the LLM provider.
Which property of the Einstein Trust Layer should you highlight to UC that addresses
these requirements?

● Data Masking
● Zero-Data Retention Policy
● Prompt Defense

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_trust_layer.htm&type=5

https://help.salesforce.com/s/articleView?id=sf.generative_ai_trust_arch.htm&type=5

you turned on Einstein Generative AI in Setup. Now, you would like to create custom
prompt templates in Prompt Builder. However, they cannot access Prompt Builder in the
Setup menu.

What is causing the problem?

● The Prompt Template Manager permission set was not assigned correctly.
● The large language model (LLM) was not configured correctly in Data Cloud.
● The Prompt Template User permission set was not assigned correctly.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_enable.htm&type=5

you built a Field Generation prompt template that worked for many records, but users
are reporting random failures with token limit errors.

What is the cause of the random nature of this error?

● The template type needs to be switched to Flex to accommodate the variable

amount of tokens generated by the prompt grounding.
● The number of tokens that can be processed by the LLM varies with total user
demand.
● The number of tokens generated by the dynamic nature of the prompt template will
vary by record.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.engagement_service_innovations_einstein_copilot_
get_engagements_details_flow_limits.htm&type=5
https://help.salesforce.com/s/articleView?id=sf.prompt_builder_about.htm&type=5

You are working on a prompt template to generate personalized emails for product
demonstration requests from customers. It is important for the AI-generated email to
adhere strictly to the guideline a, using only associated opportunity information, and to
encourage the recipient to take the desired action.

How should you include these instructions on a new line in the prompt template?

● Use curly brackets () to encapsulate instructions

● Make sure merged fields are defined.
● Surround them with triple quotes (“””).

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_template_ingredients.htm
&type=5

Which feature in the Einstein Trust Layer helps to minimize the risks of jailbreaking and
prompt injection attacks?

● Data Masking
● Secure Data Retrieval and Grounding
● Prompt Defense

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_trust_arch.htm&type=5

Your service team wants to customize the standard case summary response from
Einstein Copilot.

What should you do to achieve this?

● Customize the standard Record Summary template for the Case object.
● Summarize the Case with a standard copilot action.
● Create a custom Record Summary prompt template for the Case object.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_standard_prompt_templat
es.htm&type=5
You plan to enhance the customer support team's productivity using AI.

Which specific use case necessitates the use of Prompt Builder?

● Creating a draft of a support bulletin post for new product patches

● Estimating support ticket volume based on historical data and seasonal trends
● Creating an AI-generated customer support agent performance score
Reference(s):
https://help.salesforce.com/s/articleView?id=sf.copilot_actions_ref_mc_draft_content.htm
&type=5

A service agent is looking at a custom object that stores travel information. They
recently received a weather alert and now need to cancel flights for the customers that
are related with this itinerary. The service agent needs to review the Knowledge articles
about canceling and rebooking the customer flights.

Which Einstein Copilot capability helps the agent accomplish this?

● I nvoke a flow which makes a call to external data to create a Knowledge article
● Execute tasks based on available actions, answering questions using information
from accessible Knowledge articles.
● Generate a Knowledge article based off the prompts that the agent enters to create
steps to cancel flights.

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.copilot_actions_ref_answer_questions_with
_knowledge.htm&type=5

You have a legacy system that needs to integrate with Salesforce. UC wishes to create a
digest of account action plans using the generative API feature.

Which API service should UC use to meet this requirement?

● SOAP API
● REST API
● Metadata API

Reference(s):
https://developer.salesforce.com/docs/einstein/genai/guide/get-started-prompt-builder.ht
ml?q=METADATA%20API#connect-api

You want to use the related lists from an account in a custom prompt template.

What should you consider when configuring the prompt template?

● The text encoding (for example, UTF-8, ASCII) option

● The choice between XML and JSON rendering formats for the list
● The maximum number of related list merge fields

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_limits.htm&type=5

How does the Einstein Trust Layer ensure that sensitive data is protected while
generating useful and meaningful responses?

● Masked data will be de-masked during response journey.

● Masked data will be de-masked during request journey.
● Responses that do not meet the relevance threshold will be automatically rejected

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_trust_arch2.htm&type=5

You have implemented Generative Al within Salesforce to enable summarization of a

custom object called Guest. Users have reported mismatches in the generated
information.

In refining its prompt design strategy, which key practices should UC prioritize?

● Create concise, clear, and consistent prompt templates with effective grounding,
contextual role-playing, clear instructions, and iterative feedback.
● Submit a prompt review case to Salesforce and conduct thorough testing in the
playground to refine outputs until they meet user expectations.
 ● Enable prompt test mode, allocate different prompt variations to a subset of users
for evaluation, and standardize the most effective model based on performance
feedback.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_best_practices.htm&type=
5

you of Northern Trail Outfitters reviewed the organization's data masking settings
within the Configure Data Masking menu within Setup. Upon assessing all of the fields,
a few additional fields were deemed sensitive and have been masked within Einstein's
Trust Layer.

Which steps should you take upon modifying the masked fields?

● Turn on Einstein Feedback so that end users can report if there are any negative side
effects on Al features.
● Test and confirm that the responses generated from prompts that utilize the data
and masked data do not adversely affect the quality of the generated response
● Turn off the Einstein Trust Layer and turn it on again.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_mask_select.htm&type=5

What is the main purpose of Prompt Builder?

● A tool for developers to use in Visual Studio Code that creates prompts for Apex
programming, assisting developers in writing code more efficiently.
● A tool that enables companies to create reusable prompts for large language models
(LLMs), bringing generative Al responses to their flow of work
● A tool within Salesforce offering real-time Al-powered suggestions and guidance to
users, improving productivity and decision-making.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_about.htm&type=5

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

● Hallucination score and bias score

● Masked data and toxicity score
● Response accuracy and offensiveness score

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_audit_trail.htm&type=5

You want to be able to detect with a high level of confidence if content generated by a
large language model (LLM) contains toxic language.

Which action should you take in the Trust Layer to confirm toxicity is being
appropriately managed?

● Create a Trust Layer audit report within Data Cloud that uses a toxicity detector type
filter to display toxic responses and their respective scores.
● Create a flow that sends an email to a specified address each time the toxicity score
from the response exceeds a predefined threshold.
● Access the Toxicity Detection log in Setup and export all entries where
istoxicityDetected is true.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_audit_toxicity.htm&type=5

You want to allow its service agents to query the current fulfillment status of an order
with natural language. There is an existing autolaunched flow to query the information
from Oracle ERP, which is the system of record for the order fulfillment process.

How should you apply the power of conversational AI to this use case?

● Create a custom copilot action which calls a flow.

● Configure the Integration Flow Standard Action in Einstein Copilot.
● Create a Flex prompt template in Prompt Builder.
Reference(s):
https://help.salesforce.com/s/articleView?id=sf.copilot_actions_custom_create_scratch.ht
m&type=5

You need to create a Sales Email with a custom prompt template. They need to ground
on the following data.

○ Opportunity Products
○ Events near the customer
○ Tone and voice examples

How should you obtain related items?

● Call a prompt initiated flow to fetch and ground the required data.
● Utilize a standard email template and manually insert the required data fields.
● Create a flex template that takes the records in question as inputs.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_create_sales_email_templ
ate.htm&type=5

You implement Custom Copilot Actions to enhance its customer service operations. The
development team needs to understand the core components of a Custom Copilot
Action to ensure proper configuration and functionality.

What should the development team review in the Custom Copilot Action configuration
to identify one of the core components of a Custom Copilot Action?

● Instructions
● Output Types
● Action Triggers

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.copilot_actions_instructions.htm&type=5

You are tasked with configuring a generative model to create personalized sales emails
using customer data stored in Salesforce. You have already fine-tuned a large language
model (LLM) on the OpenAI platform. Security and data privacy are critical concerns for
the client.
How should you integrate the custom LLM into Salesforce?

● Add the fine-tuned LLM in Einstein Studio Model Builder.

● Create an application of the custom LLM and embed it in Sales Cloud via Frame.
● Enable model endpoint on OpenAl and make callouts to the model to generate
emails.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.c360_a_ai_mm_manage_models.htm&typ
e=5

You have created a copilot custom action using flow as the reference action type.
However, it is not delivering the expected results to the conversation preview, and
therefore needs troubleshooting.

What should you do to identify the root cause of the problem?

● In Copilot Builder within the Dynamic Panel, confirm selected action and observe
the values in Input and Output sections.
● In Copilot Builder, verify the utterance entered by the user and review session event
logs for debug information.
● In Copilot Builder within the Dynamic Panel, turn on dynamic debugging to show
the inputs and outputs.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.copilot_actions_instructions.htm&type=5

A sales rep at You is extremely busy and sometimes will have very long sales calls on
voice and video calls and might miss key details. They are just starting to adopt new
generative AI features.

Which Einstein Generative Al feature should you recommend to help the rep get the
details they might have missed during a conversation?

● Call Explorer
● Call Summary
● Sales Summary
https://help.salesforce.com/s/articleView?id=sf.eci_call_summaries.htm&type=5

You are experimenting with using public Generative Al models and are familiar with the
language required to get the information it needs. However, it can be time consuming
for both UC's sales and service reps to type in the prompt to get the information they
need, and ensure prompt consistency.

Which Salesforce feature should you recommend to address these concerns?

● Einstein Recommendation Builder

● Einstein Prompt Builder and Prompt Templates
● Einstein Copilot Action: Query Records

Reference(s):

What is best practice when refining Einstein Copilot custom action instructions?

● Use consistent introductory phrases and verbs across multiple action instructions.
● Provide examples of user messages that are expected to trigger the action.
● Specify the persona who will request the action.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.copilot_actions_instructions.htm&type=5

When configuring a prompt template, you preview the results of the prompt template
they've written. They see two distinct text outputs: Resolution and Response.

Which information does the Resolution text provide?

● It shows the full text that is sent to the Trust Layer.
● It shows which sensitive data is masked before it is sent to the LLM
● It shows the response from the LLM based on the sample record.

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_enable_resolution.htm&ty
pe=5
You recently launched a pilot program to integrate conversational Al into its CRM
business operations with Einstein Copilot.

How should you monitor Copilot's usability and the assignment of actions?

● Run Einstein Copilot Analytics.

● Run a report on the Platform Debug Logs.
● Query the Copilot log data using the metadata API.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.copilot_analytics.htm&type=5

You (UC) recently rolled out Einstein Generative Al capabilities and has created a custom
prompt to summarize case records. Users have reported that the case summaries
generated are not returning the appropriate information.

What is a possible explanation for the poor prompt performance?

● The Einstein Trust Layer is incorrectly configured.

● The data being used for grounding is incorrect or incomplete.
● The prompt template version is incompatible with the chosen LLM.

Reference(s): Pending/Missing

What is the primary function of the planner service in the Einstein Copilot system?

● Generating record queries based on conversation history

● Identifying copilot actions to respond to user utterances
● Offering real-time language translation during conversations

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.copilot_building_blocks.htm&type=5

You is very concerned about security compliance and wants to understand:

○  hich prompt text is sent to the large language model (LLM)

W
○ How it is masked
○ The masked response

What should you recommend?

 ● Ingest the Einstein Shield Event logs into CRM Analytics.
● Enable audit trail in the Einstein Trust Layer.
● Review the debug logs of the running user.

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.generative_ai_audit_trail.htm&type=5

You (UC) noticed an increase in customer contract cancellations in the last few months.
UC is seeking ways to address this issue by implementing a proactive outreach program
to customers before they cancel their contracts and is asking the Salesforce team to
provide suggestions.

Which use case functionality of Model Builder aligns with UC's request?

● Customer churn prediction

● Contract Renewal Date prediction
● Product recommendation prediction

Reference(s): Pending/Missing

An administrator wants to check the response of the Flex prompt template they've built,
but the preview button is greyed out.

What is the reason for this?

● The records related to the prompt have not been selected.

● A merge field has not been inserted in the prompt.
● The prompt has not been saved and activated.

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.prompt_builder_flex_example_templates.h
tm&type=5

What is the correct process to leverage Prompt Builder in a Salesforce org?

● Enable the target object for generative prompting, develop the prompt within the
prompt workspace, select records to fine-tune and ground the response, enable the
Trust Layer, and associate the prompt to an action.
 ● Select the appropriate prompt template type to use, select one of Salesforce's
standard prompts, determine the object to associate the prompt, select a record to
validate against, and associate the prompt to an action.
● Select the appropriate prompt template type to use, develop the prompt within the
prompt workspace, select resources to dynamically insert CRM-derived grounding
data, pick the model to use, and test and validate the generated responses.

Reference(s):

https://admin.salesforce.com/blog/2024/the-ultimate-guide-to-prompt-builder-spring-2
4#:~:text=Hallucination:%20a%20type%20of%20response,Prompt%20Builder%20w
ill%20help%20you:

You want to utilize Einstein for Sales to help sales reps reach their sales quotas by
providing AI-generated plans containing guidance and steps for closing deals.

Which feature should you recommend to the sales team?

● Create Account Plan

● Create Close Plan
● Find Similar Deals

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.copilot_actions_ref_close_plan.htm&type=
5

You want to use Flow to bring data from unified Data Cloud objects to prompt
templates.

Which type of flow should UC use?

● Data Cloud-triggered flow

● Unified-object linking flow
● Template-triggered prompt flow

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.prompt_builder_add_flows_with_data_clo
ud_sales_email.htm&type=5

You (UC) plans to send one of three different emails to its customers based on the
customer's lifetime value score and their market segment.
Considering that UC are required to explain why an email was selected, which AI model
should UC use to achieve this?

● Predictive model
● Generative model
● Predictive model and generative model

Which use case is best supported by Salesforce Einstein Copilot's capabilities?

● Enable Salesforce admin users to create and train custom large language models
(LLMs) using CRM data.
● Bring together a conversational interface for interacting with AI for all Salesforce
users, such as developers and ecommerce retailers.
● Enable data scientists to train predictive AI models with historical CRM data using
built-in machine learning capabilities.

Reference(s):

https://www.salesforce.com/news/press-releases/2023/09/12/ai-einstein-news-dreamforc
e/

You (UC) uses Salesforce Service Cloud to support its customers and agents handling
cases. UC is considering implementing Einstein Copilot and extending Service Cloud to
mobile users.

When would Einstein Copilot implementation be most advantageous?

● When the goal is to streamline customer support processes and improve response
times
● When the focus is on optimizing marketing campaigns and strategies
● When the main objective is to enhance data security and compliance measures

You have recently received an increased number of support cases. As a result, UC has
hired more customer support reps and has started to assign some of the ongoing cases
to newer reps.

Which generative AI solution should the new support reps use to understand the details
of a case without reading through each case comment?

● Einstein Sales Summaries

 ● Einstein Copilot
● Einstein Work Summaries

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.cc_generative_ai_use_work_summaries.ht
m&type=5

Amid their busy schedules, sales reps at You dedicate time to follow up with prospects
and existing clients via email regarding renewals or new deals. They spend many hours
throughout the week reviewing past communications and details about their customers
before performing their outreach.

Which standard Copilot action helps sales reps draft personalized emails to prospects by
generating text based on previous successful communications?

● Einstein Copilot Action: Draft or Revise Sales Email

● Einstein Copilot Action: Find Similar Opportunities
● Einstein Copilot Action: Summarize Record

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.copilot_actions_ref_draft_or_revise_email.h
tm&type=5

You are evaluating Einstein Generative Al features to improve the productivity of the
service center operation.

Which features should you recommend?

● Service Replies and Case Summaries

● Reply Recommendations and Sales Summaries
● Service Replies and Work Summaries

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.reply_recs_generative_ai_service_replies.ht
m&type=5

https://help.salesforce.com/s/articleView?id=sf.cc_generative_ai_work_summaries.htm&ty
pe=5
You need to create a prompt template to fill a custom field named Latest Opportunities
Summary on the Account object with information from the three most recently opened
opportunities.

How should you gather the necessary data for the prompt template?

● Create a flow to retrieve the opportunity information.

● Select the Account Opportunity object as a resource when creating the prompt
template.
● Select the latest Opportunities related list as a merge field.

Reference(s):

Related list does not support filters. Hence a flow will be necessary to get the 3 latest opportunities.

"Record-level filters aren't applied"

Where should you go to add/update actions assigned to a copilot?

● Copilot Actions page or Global Actions

● Copilot Detail page, Global Actions, or the record page for the copilot action
● Copilot Actions page, the record page for the copilot action, or the Copilot Action
Library tab

Before activating a custom copilot action, you would like to understand multiple
real-world user utterances to ensure the action is being selected appropriately.

Which tool should you recommend?

● Model Playground
● Einstein Copilot
● Copilot Builder

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.copilot_actions_custom_create_scratch.ht
m&type=5
What should you consider when using related list merge fields in a prompt template
associated with an Account object in Prompt Builder?

● Prompt generation will yield no response when there is no related list associated
with an Account in runtime.
● If person accounts have been enabled, merge fields will not be available for the
Account object.
● The Activities related list on the Account object is not supported because it is a
polymorphic field.

Reference(s):

https://developer.salesforce.com/docs/atlas.en-us.252.0.uiapi.meta/uiapi/ui_api_all_supported_obj
ects.htm
You test out a new Einstein Generative

You test out a new Einstein Generative AI feature for its sales team to create
personalized and contextualized emails for its customers. Sometimes, users find that the
draft email contains placeholders for attributes that could have been derived from the
recipient's contact record.

What is the most likely explanation for why the draft email shows these placeholders?

● The user does not have Einstein Sales Emails permission assigned.
● The user's locale language is not supported by Prompt Builder.
● The user does not have permission to access the fields.

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.prompt_builder_get_to_know.htm&type=5

You want to improve the efficiency of addressing customer questions and reduce agent
handling time with Al-generated responses. The agents should be able to leverage their
existing knowledge base and identify whether the responses are coming from the large
language model (LLM) or from Salesforce Knowledge.

Which step should UC take to meet this requirement?

● Turn on Service Al Grounding, Grounding with Case, and Service Replies.

● Turn on Service Replies, Service Al Grounding, and Grounding with Knowledge.
● Turn on Service Al Grounding and Grounding with Knowledge.

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.reply_recs_generative_ai_service_replies.ht
m&type=5

In Model Playground, which hyperparameters of an existing Salesforce-enabled

foundational model can you change?

● Temperature, Top-k sampling, Presence Penalty

● Temperature, Frequency Penalty, Output Tokens
● Temperature, Frequency Penalty, Presence Penalty

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.c360_a_ai_foundation_models_configure.
htm&type=5

You want to offer personalized service experiences and reduce agent handling time with
AI-generated email responses, grounded in Knowledge base.

Which Al capability should UC use?

● Einstein Email Replies

● Einstein Generative Service Replies for Email
● Einstein Service Replies for Email

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.reply_recs_service_emails_console.htm&typ
e=5

You are tasked with creating a prompt template for a sales team. The template needs to
generate a summary of all related opportunities for a given Account.
Which grounding technique should you use to include data from the related list of
opportunities le prompt template?

● Use merge fields to reference the default related list of opportunities.

● Use formula fields to reference the Einstein related list of opportunities.
● Use the merge fields to reference a custom related list of opportunities.

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.prompt_builder_ground_template.htm&typ
e=5

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_ground_related_list.htm&t
ype=5

You want to include data from the response of external service invocation (REST API
callout) into the prompt template.

How should you meet this requirement?

● Use External Service Record merge fields.

● Use "Add Prompt Instructions" flow element.
● Convert the JSON to an XML merge field.

Reference(s):
https://developer.salesforce.com/docs/einstein/genai/guide/get-started-prompt-builder.ht
ml

The marketing team at You is looking for a way to personalize emails based on customer
behavior, preferences, and purchase history.

Why should the team use Einstein Copilot as the solution?

● To generate relevant content when engaging with each customer

● To analyze past campaign performance
● To send automated emails to all customers
●
Reference(s):
https://help.salesforce.com/s/articleView?id=sf.generative_ai_solutions.htm&type=5
You want to enable its sales team with automatic post-call visibility into unknown of
competitors, products, and other custom phrases.

Which feature should you set up to enable UC's sales team?

● Call Insights
● Call Summaries
● Call Explorer

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.copilot_actions_ref_explore_conversation.h
tm&type=5

When a customer chat is initiated, which functionality in Salesforce provides generative

AI replies or draft emails based on recommended Knowledge articles?

● Einstein Service Replies

● Einstein Grounding
● Einstein Reply Recommendations

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.reply_recs_generative_ai_service_replies.ht
m&type=5

What is the role of the large language model (LLM) in executing an Einstein Copilot
Action?

● Identify the best matching actions and correct order of execution

● Find similar requests and provide the actions that need to be executed
● Determine a user's access and sort actions by priority to be executed

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.copilot_how_copilot_works.htm&type=5
You want to enable its sales team to use AI to suggest recommended products from its
catalog.

Which type of prompt template should UC use?

● Email generation prompt template

● Flex prompt template
● Record summary prompt template

You are tasked with configuring a generative model to create personalized sales emails
using customer data stored in Salesforce. You have already fine-tuned a large language
model (LLM) on the OpenAI platform. Security and data privacy are critical concerns for
the client.

How should you integrate the custom LLM into Salesforce?

● Create an application of the custom LLM and embed it in Sales Cloud via IFrame.
● Enable model endpoint on OpenAI and make callouts to the model to generate
emails.
● Add the fine-tuned LLM in Einstein Studio Model Builder.

Reference(s): Pending/Missing

An administrator is responsible for ensuring the security and reliability of your CRM
data. Your org needs enhanced data protection and up-to-date AI capabilities. You also
need 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?

● Zero-data retention policy

● Data masking
● Dynamic grounding with secure data retrieval

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_trust_arch.htm&type=5

You want to use the Draft with Einstein feature in Sales Cloud to create a personalized
introduction email.
After creating a proposed draft email, which predefined adjustment should UC choose
to revise the draft with a more casual tone?

● Enhance Friendliness
● Optimize for Clarity
● Make Less Formal

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.copilot_setup_tone.htm&type=5

You are planning a marketing email about products that most closely match a
customer's expressed interests.
,
What should you recommend to generate this email?

● Standard email marketing template using Apex or flows for matching interest in
products
● Standard email draft with Einstein and choose standard email template
● Custom sales email template which is grounded with interest and product
information

Reference(s): Pending/Missing

you are creating a custom action in Einstein Copilot.

Which option is available for you to choose for the custom copilot action?

● SOQL
● Flows
● Apex trigger

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.copilot_actions_custom_create_scratch.ht
m&type=5

You have an active standard email prompt template that does not fully deliver on the
business requirements.
Which steps should you take to use the content of the standard prompt email template
in question and customize it to fully meet the business requirements?

● Save as New Version and edit as needed.

● Save as New Template and edit as needed.
● Clone the existing template and modify as needed.

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_standard_prompt_templat
es.htm&type=5

You have a mature Salesforce org with a lot of data in cases and Knowledge articles. UC
is concerned that there are many legacy fields, with data that might not be applicable
for Einstein AI to draft accurate email responses.

Which solution should UC use to ensure Einstein AI can draft responses from a defined
data source?

● Service AI Grounding
● Service Replies
● Work Summaries

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.einstein_generative_ai_grounding_setup.ht
m&type=5

You are implementing Einstein Generative AI to improve customer insights and

interactions. UC needs audit and feedback data to be accessible for reporting purposes.

What is a consideration for this requirement?

● Storing this data requires Data Cloud to be provisioned.

● Storing this data requires Salesforce big objects.
● Storing this data requires a custom object for data to be configured.

Reference(s):
https://help.salesforce.com/s/articleView?id=sf.generative_ai_feedback_review_feedback.h
tm&type=5

You implement Einstein Sales Emails for a sales team. The team wants to send
personalized follow-up emails to leads based on their interactions and data stored in
Salesforce. You need to configure the system to use the most accurate and up-to-date
information for email generation.

Which grounding technique should you use?

● Ground with Record Merge Fields

● Automatic grounding using Draft with Einstein feature
● Ground with Apex Merge Fields

Reference(s): Pending/Missing

Your data science team is hosting a generative large language model (LLM) on Amazon
Web Services (AWS).

What should the team use to access externally-hosted models in the Salesforce
Platform?

● App Bullder
● Copilot Builder
● Model Builder

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_large_language_model_supp
ort.htm&language=en_US&type=5

Leadership needs to populate a dynamic form field with a summary or description

created by a large language model (LLM) to facilitate more productive conversations
with customers. Leadership also wants to keep a human in the loop to be considered in
their AI strategy.
Which prompt template type should you recommend?

● Sales Email
● Field Generation
● Record Summary

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.prompt_builder_add_field_gen_to_lightnin
g_record_page.htm&type=5

You are using Einstein Copilot for Sales to find similar opportunities to help close deals
faster. The team wants to understand the criteria used by the copilot to match
opportunities.

What is one criteria that Einstein Copilot for Sales uses to match similar opportunities?

● Matched opportunities were created in the last 12 months.

● Matched opportunities have a status of Closed Won from last 12 months.
● Matched opportunities are limited to the same account.

Reference(s): Pending/Missing

You want to enable its sales reps to explore opportunities that are similar to previously
won opportunities by entering the utterance, "Show me other opportunities like this
one."

How should UC achieve this in Einstein Copilot?

● Create a custom Copilot action calling an Apex class.

● Create a custom Copilot action calling a flow.
● Use the standard Copilot action.

Reference(s): Pending/Missing

You need sales reps to be able to only execute prompt templates.

What should you recommend to achieve this requirement?

● Prompt Template User permission set

● Prompt Template Manager permission set
● Prompt Execute Template permission set

Reference(s): Pending/Missing

You are looking to enhance its operational efficiency. UC has recently adopted
Salesforce and is considering implementing Einstein Copilot to improve its processes.

What is a key reason for implementing Einstein Copilot?

● Improving data entry and data cleansing

● Streamlining workflows and automating repetitive tasks
● Allowing Al to perform tasks without user interaction

Reference(s): Pending/Missing

Based on the user utterance, "Show me all the customers in New York", which standard
Einstein Copilot action will the planner service use?

● Query Records
● Fetch Records
● Select Records

Reference(s): Pending/Missing

You are tasked with creating a new custom prompt template to populate a field with
generated output. UC enabled the Einstein Trust Layer to ensure AI Audit data is
captured and monitored for adoption and possible enhancements.

Which prompt template type should you use and which consideration should they
review?

● Flex, and that Dynamic Fields is enabled

● Field Generation, and that Dynamic Forms is enabled
● Field Generation, and that Dynamic Fields is enabled
Reference(s): Pending/Missing

You have seen a high adoption rate of a new feature that uses generative AI to populate
a summary field of a custom object, Competitor Analysis. All sales users have the same
profile but one user cannot see the generative AI-enabled field icon next to the
summary field.

What is the most likely cause of the issue?

● The prompt template associated with summary field is not activated for that user.
● The user does not have the Prompt Template User permission set assigned.
● The user does not have the field Generative AI User permission set assigned.

Reference(s): Pending/Missing

You want to implement a solution in Salesforce with a custom UX that allows users to
enter a sales order number. Subsequently, the system will invoke a custom prompt
template to create and display a summary of the sales order header and sales order
details.

Which solution should you implement to meet this requirement?

● Create an autolaunched flow and invoke the prompt template using the standard
"Prompt Template"
flow action.
● Create a screen flow to collect sales order number and invoke the prompt template
using the standard "Prompt Template" flow action.
● Create a template-triggered prompt flow and invoke the prompt template using the
standard "prompt Template" flow action.

Reference(s): Pending/Missing

You are implementing Service AI Grounding to enhance its customer service operations.
UC wants to ensure that its AI-generated responses are grounded in the most relevant
data sources. The team needs to configure the system to include all supported objects
for grounding.

Which objects should UC select to configure Service Al Grounding?

● Case and Knowledge

 ● Case, Knowledge, and Case Notes
● Case, Case Emails, and Knowledge

Reference(s): Pending/Missing

You plan to implement prompt templates that utilize the standard foundation models.

What should you consider when building prompt templates in Prompt Builder?

● Include multiple-choice questions within the prompt to test the LIM's understanding
of the context.
● Train LLM with data using different writing styles including word choice, intensifiers,
emojis, and punctuation.
● Ask it to role-play as a character in the prompt template to provide more context to
the LLM.

Reference(s): Pending/Missing

You are interested in improving the sales operation efficiency by analyzing their data
using AI-powered predictions in Einstein Studio.

Which use case works for this scenario?

● Predict customer sentiment toward a promotion message.

● Predict most popular products from new product catalog.
● Predict customer lifetime value of an account.

Reference(s): Pending/Missing

You want to use an external large language model (LLM) in Prompt Builder.

What should you recommend?

● Use Flow and External Services to bring data from an external LLM.
● Use BYO-LLM functionality in Einstein Studio.
● Use Apex to connect to an external LLM and ground the prompt.

Reference(s): Pending/Missing
You want to reduce overall agent handling time by minimizing the time spent typing
routine answers for common questions in-chat, and reducing the post-chat analysis by
suggesting values for case fields.

Which combination of Einstein for Service features enables this effort?

● Einstein Reply Recommendations and Case Summaries

● Einstein Reply Recommendations and Case Classification
● Einstein Service Replies and Work Summaries

Reference(s): Pending/Missing

You want to make a sales proposal and directly use data from multiple unrelated objects
(standard and custom) in a prompt template.

What should you recommend?

● Create a prompt template passing in a special custom object that connects the
records temporarily.
● Create a Flex template to add resources with standard and custom objects as inputs.
● Create a prompt template-triggered flow to access the data from standard and
custom objects.

Your current AI data masking rules do not align with organizational privacy and security
policies and requirements.

What should you recommend to resolve the issue?

● Enable data masking for sandbox refreshes.

● Configure data masking in the Einstein Trust Layer setup.
● Add new data masking rules in LLM setup.

Reference(s): Pending/Missing

You want to configure Einstein Trust Layer in its production org but is unable to see the
option on the Setup page.

After provisioning Data Cloud, which step must you take to make this option available to
NTO?
 ● Turn on Prompt Builder.
● Turn on Einstein Generative AI.
● Turn on Einstein Copilot.

Reference(s): Pending/Missing

You implemented Einstein Copilot for its users. One user complains that Einstein Copilot
is not deleting activities from the past 7 days.

What is the reason for this issue?

● Einstein Copilot does not have the permission to delete the user's records.
● Einstein Copilot does not support the Delete Record action.
● Einstein Copilot Delete Record Action permission is not associated with the user.

Reference(s): Pending/Missing

You want to enable its sales team to get insights into product and competitor names
mentioned during calls.

How should UC meet this requirement?

● Enable Einstein Conversation Insights, connect a recording provider, assign

permission sets, and customize insights with up to 25 products.
● Enable Einstein Conversation Insights, enable sales recording, assign permission sets,
and customize insights with up to 50 products.
● Enable Einstein Conversation Insights, assign permission sets, define recording
managers, and customize insights with up to 50 competitor names.

Reference(s): Pending/Missing

The sales team at a hotel resort would like to generate a guest summary about the
guests' interests and provide recommendations based on their activity preferences
captured in each guest profile. They want the summary to be available only on the
contact record page.

Which AI capability should the team use?

● Prompt Builder
 ● Model Builder
● Einstein Copilot

Reference(s): Pending/Missing

What are you able to do when the "Enrich event logs with conversation data" setting in
Einstein Copilot is enabled?

● View the user click path that led to each copilot action.
● Generate details reports on all Copilot conversations over any time period.
● View session data including user input and copilot responses for sessions over the
past 7 days.

Reference(s): Pending/Missing

A support team handles a high volume of chat interactions and needs a solution to
provide quick, relevant responses to customer inquiries. Responses must be grounded
in the organization's knowledge base to maintain consistency and accuracy.

Which feature in Einstein for Service should the support team use?

● Einstein Knowledge Recommendations

● Einstein Service Replies
● Einstein Reply Recommendations

Reference(s): Pending/Missing

You are using Einstein Generative AI to generate an account summary. UC aims to

ensure the content is safe and inclusive, utilizing the Einstein Trust Layer's toxicity
scoring to assess the content's safety level.

What does a safety category score of 1 indicate in the Einstein Generative AI Toxicity
Score?

● Moderately safe
● Not safe
● Safe

Reference(s):

https://help.salesforce.com/s/articleView?id=sf.generative_ai_audit_toxicity.htm&type=5
The score for the safety category ranges from 0 through 1 with 1 being the safest.