AI SPECIALIST SALESFORCE EXAM
AI SPECIALIST SALESFORCE EXAM
1. An HR team needs to create personalized onboarding materials for new employees across different
departments. These materials should include department-specific training plans, company policies, and
customized welcome messages. The team wants to ensure consistency across all documents while
saving time in the creation process. Should they use Prompt Builder, and why?
a) Yes, because Prompt Builder can generate consistent and customized onboarding materials based on
predefined templates
b) No, because onboarding materials require a personal touch that AI cannot provide
c) Yes, but only for generating generic content like company policies, not for personalized sections
d) No, because Prompt Builder is more suitable for customer-facing content, not internal documents
2. A sales team wants to ensure that their AI-generated emails are always based on the most recent
customer interaction data stored in the CRM, such as recent purchases or support cases. Which
grounding technique should they use to achieve this?
3. In a scenario where customer service agents need AI-generated summaries of case details after
resolving an issue, which Einstein for Service feature should be used?
4. A tech startup is building a chatbot to assist users with complex troubleshooting tasks. The team is
debating between using a standard Salesforce LLM, customizing their own model, or bringing in an
external LLM that was trained on a vast amount of technical documentation. Under which condition
would it be most appropriate to configure a custom generative model?
a) When the startup requires the chatbot to understand and generate responses based on very specific, in-
house technical terminology that standard models might not cover
b) When the startup needs the chatbot to handle basic customer inquiries that do not require technical
depth
c) When the startup wants to use a model trained exclusively on general, public domain technical
documents
Marina Carabelos Sánchez
Latest Update 22-01-2025
d) When the startup has a very limited dataset and no specific customization needs
5. A customer service center wants to provide customers with immediate answers to common questions,
such as business hours or return policies, even outside of normal working hours. The team needs a
feature that can automate these interactions without requiring agent involvement. Which Einstein for
Service feature should they implement?
6. A marketing team wants to leverage a pre-trained Large Language Model (LLM) provided by Salesforce
to generate personalized email content. What is the most appropriate first step in configuring this
model?
7. A sales manager wants to ensure that all client interactions, such as emails and meetings, are
automatically logged into the CRM without the need for manual input. This will help maintain accurate
records and improve team efficiency. Which Einstein feature should the sales manager implement?
8. When configuring a custom generative model in Salesforce Model Builder, which step is crucial to
ensure the model’s effectiveness in generating relevant outputs?
9. After implementing Einstein Copilot, your company notices that some departments are not fully utilizing
the tool. To improve adoption, you want to identify the specific barriers to its usage. What is the best
method to gain insights into these challenges?
a) Implement a survey to collect feedback from users on their experience with Copilot
b) Schedule daily meetings to discuss Copilot usage
c) Mandate the use of Copilot in all processes without exceptions
d) Review only the successful cases where Copilot was used
10. A sales team is ready to start using a new prompt template that has been created and assigned to them.
What must they do to execute the prompt template in their daily workflow?
11. How does the Large Language Model (LLM) in Einstein Copilot determine the appropriate action to take
when a user asks for help with generating a sales report?
12. An organization wants to delegate the execution of predefined prompt templates to specific users who
will generate content using these templates without altering them. Which user role should be assigned
this task?
a) Content Creator
b) Salesforce Developer
c) Prompt Executor
d) System Administrator
13. A financial services company needs to assess the credit risk of loan applicants based on their financial
history and other relevant factors. When should they use Model Builder?
14. Your team has successfully created and activated a prompt template in Salesforce.
What is the final step to ensure that the template is utilized in the intended business process?
15. A company wants to generate personalized customer emails using a pre-trained model that Salesforce
provides out of the box. What is the first step they should take to configure this model?
16. A sales director needs to project the upcoming quarter’s sales performance based on the current
pipeline, historical trends, and real-time data. The director wants to use AI to predict future revenue and
identify potential risks in achieving sales targets. Which Einstein feature should the director use?
17. Which user role is best suited to manage and maintain prompt templates within Salesforce, ensuring
they align with business needs?
a) Sales Representative
b) Marketing Manager
c) System Administrator
d) Customer Service Agent
18. A company has rolled out Einstein Copilot and needs to ensure that its adoption leads to measurable
business outcomes. The management team wants to link Copilot usage to key business metrics such as
sales growth and customer satisfaction. What is the best method to achieve this?
a) Regularly compare the performance of departments using Copilot with those that aren't
b) Focus only on qualitative feedback from users about their Copilot experience
c) Integrate Copilot usage data with business performance dashboards to correlate usage with key metrics
d) Evaluate the impact of Copilot after a year of usage without intermediate checks
19. A retail company wants to use a large language model (LLM) to generate personalized product
descriptions based on customer preferences and past purchase behavior. They are evaluating whether to
configure a standard generative model provided by Salesforce, create a custom model, or implement
their own Bring Your Own Large Language Model (BYOLLM). Which option should they choose if they
need highly tailored outputs and want full control over the model’s behavior?
20. What should be the primary focus when managing the adoption of Einstein Copilot across different
departments?
21. A company is using Salesforce Einstein to analyze customer data and generate predictive insights. They
need to ensure that sensitive employee salary information is not included in any Einstein analytics due
to strict internal data governance policies. How can the company implement this using the Einstein Trust
Layer?
a) Use Field-Level Security to hide the salary information from all users
b) Apply Einstein Data Exclusion to exclude salary information from being processed by Einstein
c) Encrypt the salary fields using Salesforce Shield Encryption
d) Remove the salary fields from the Salesforce schema
22. When would it be most appropriate to create a custom Copilot action in Salesforce Einstein?
a) When you need to automate a repetitive task that is common across all industries
b) When a specific business process requires unique data inputs and custom logic
c) When you want to use Salesforce’s default functionalities without modification
d) When you need to generate a standard sales report
Marina Carabelos Sánchez
Latest Update 22-01-2025
23. A marketing team in a large enterprise is tasked with creating and managing AI-driven campaigns using
Salesforce’s Prompt Builder. The team consists of content creators, data analysts, and a marketing
manager. Which user role should be assigned to the marketing manager to ensure they can both
manage and execute prompt templates effectively?
a) Content Creator
b) Data Analyst
c) Prompt Template Administrator
d) Campaign Viewer
24. Which of the following is the primary consideration when configuring a Bring Your Own Large Language
Model (BYOLLM) in Salesforce?
25. A team is tasked with creating a prompt template to be used across multiple departments, each with
different objectives. What key consideration should guide the creation of this template to ensure it
meets the needs of all departments?
26. A Salesforce implementation team is setting up a series of prompt templates that will be used across
multiple departments, including marketing and customer service. They need to ensure that only
qualified users can modify these templates while allowing broader access for execution. Which user role
should be assigned the responsibility of modifying and managing these prompt templates?
a) Marketing Specialist
b) Salesforce Consultant
c) Content Editor
d) IT Manager
27. An organization wants to monitor the adoption of Einstein Copilot among its customer service agents
and identify areas for improvement. What is the most appropriate approach for tracking and evaluating
Copilot usage?
a) Analyze the frequency of Copilot actions across all agents using Salesforce dashboards
b) Conduct weekly surveys asking agents if they are using Copilot
c) Set monthly targets for Copilot usage and penalize agents who do not meet them
d) Assign a team member to manually track Copilot usage by observing agent workflows
28. When a user asks Einstein Copilot to schedule a follow-up meeting with a client, how does the large
language model (LLM) execute this action?
a) The LLM directly modifies the user’s calendar in Salesforce without further verification
b) The LLM interprets the user’s request, identifies the appropriate action, and uses Salesforce’s scheduling
API to create a calendar event
c) The LLM sends a generic email to the client requesting a meeting time
Marina Carabelos Sánchez
Latest Update 22-01-2025
d) The LLM requires manual input from the user to execute the scheduling
29. A customer support team is integrating Salesforce Einstein Copilot into their operations. They plan to
use standard copilot actions to automate ticket creation and follow-ups but also need to create custom
actions for handling escalations based on specific criteria, such as issue severity and customer status.
What is the best approach for implementing these actions?
a) Apply standard copilot actions for both routine and complex tasks to simplify the process
b) Focus on developing custom copilot actions for all tasks to ensure full customization
c) Leverage standard copilot actions for routine tasks and create custom actions for escalations that
require specific handling
d) Use a manual process for all tasks to ensure accuracy and control over the support process
30. Universal Containers recently launched a pilot program to integrate conversational AI into its CRM
business operations with Einstein Copilot. How should the AI Specialist monitor Copilot’s usability and
the assignment of actions?
31. An administrator wants to check the response of the Flex prompt template they’ve build, but the
preview button is greyed out. What is the reason for this?
32. An AI Specialist wants to include data from the response of external service invocation (REST API callout)
into the prompt template. How should the AI Specialist meet this requirement?
33. What is the role of the large language model (LLM) in the executing an Einstein Copilot Action?
34. Which use case is best supported by Salesforce Einstein Copilot’s capabilities?
a) Bring together a conversational interface for interacting with AI for all Salesforce users, such as
developers and ecommerce retailers
b) Enable data scientist to train predictive AI models with historical CRM data using built-in machine
learning capabilities
c) Enable Salesforce admin users to create and train custom large language models (LLMs) using CRM data
35. Universal Containers (UC) is experimenting with using public Generative AI models and is familiar with
the language required to get the information it needs. However, it can be time consuming for both UC’s
Marina Carabelos Sánchez
Latest Update 22-01-2025
sales and service reps to type in the prompt to get the information they need, and ensure prompt
consistency. Which Salesforce feature should a Salesforce AI Specialist recommend to address these
concerns?
36. An AI Specialist wants to use the related lists from an account in a custom prompt template. What
should the AI Specialist consider when configuring the prompt template?
37. Universal Containers tests 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 the 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?
a) The user does not have Einstein Sales Emails permission assigned
b) The user does not have permission to access the fields
c) The user’s locale language is not supported by Prompt Builder
38. What is the correct process to leverage Prompt Builder in a Salesforce org?
a) 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
b) 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
c) 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 generative responses
39. Universal Containers (UC) has implemented Generative AI within Salesforce to enable summarization of
the custom object called Guest. Users have reported mismatches in the generative information. In
refining its prompt design strategy, which key practices should UC prioritize?
a) 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
b) Create concise, clear, and consistent prompt templates with effective grounding, contextual role-playing,
clear instructions, and iterative feedback
c) Submit a prompt review case to Salesforce and conduct thorough testing in the playground to refine
outputs until they meet user expectations
40. An AI Specialist needs to create a Sales Email with a custom prompt template. They need to ground on
the following data: Opportunity products, events near the customer, and tone and voice examples. How
should the AI Specialist obtain related items?
a) Call the prompt-initiated flow to fetch and ground the required data
b) Create a flex template that takes the records in question as inputs
Marina Carabelos Sánchez
Latest Update 22-01-2025
c) Utilize a standard email template and manually insert the required data fields
41. Universal Containers (UC) wants 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 prompt?
a) Use Model Playground to create a model configuration with the specified parameters
b) Manually add the hyperparameters to the new template
c) Revert to using the standard template without modifications
42. An AI Specialist is 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
the AI Specialist use to include data from the related list of opportunities in the prompt template?
43. An AI Specialist is tasked with configuring a generative model to create personalized sales emails using
costumer data stored in Salesforce. The AI Specialist has already fine-turned a large language model
(LLM) on the OpenAI platform. Security and data privacy are critical concerns for the client. How should
the AI Specialist integrate the custom LLM into Salesforce?
44. Universal Containers (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?
a) When the goal is to streamline customer Support processes and improve response times
b) When the main objective is to enhance data security and compliance measures
c) When the focus is on optimizing marketing campaigns and strategies
45. How does Einstein Trust Layer ensure that sensitive data is protected while generating useful and
meaningful responses?
46. Universal Containers (UC) wants to use Flow data from unified data objects to prompt templates. Which
type of flow should UC use?
47. An AI Specialist needs 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 the AI Specialist gather the necessary data from the prompt template?
Marina Carabelos Sánchez
Latest Update 22-01-2025
48. A data scientist needs to view and manage models in Einstein Studio. The data scientist also needs to
create prompt templates in Prompt Builder. Which permission sets should an AI Specialist assign to the
data scientist?
49. An AI Specialist configured Data Masking within the Einstein Trust Layer. How should the AI Specialist
begin validating that the correct fields are being masked?
a) Use a Flow-based resource in Prompt Builder to debug the fields’ merge values using Flow Debugger
b) Request the Einstein Generative AI Audit Data from the Security section of the Setup menu
c) Enable the collection and storage of Einstein Generative AI Audit Data on the Einstein Feedback setup
page
50. Universal Containers (UC) recently rolled out Einstein Generative AI 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 performance?
51. What is best practice when refining Einstein Copilot custom action instructions?
a) Provide examples of user messages that are expected to trigger the action
b) Use consistent introductory phrases and verbs across multiple action instructions
c) Specify the persona who will request the action
52. Universal Containers (UC) has 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?
a) REST API
b) SOAP API
c) Metadata API
53. Universal Containers (UC) service team wants to customize the standard case summary response from
Einstein Copilot. What should the AI Specialist do to achieve this?
a) Customize the standard Record Summary template for the case object
b) Summarize the Case with a standard copilot action
c) Create a custom Record Summary prompt template for the case object
54. The marketing team at Universal Containers 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?
Marina Carabelos Sánchez
Latest Update 22-01-2025
55. Universal Containers (UC) wants to assess Salesforce’s generative AI features but has 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 AI service.
Which property of the Einstein Trust Layer should the AI Specialist highlight to UC that addresses these
requirements?
a) Zero-Data Retention Policy
b) Data Masking
c) Prompt Defense
56. Universal Containers wants to be able to detect with a high level of confidence if content by a large
language model (LLM) contains toxic language. Which action should an AI Specialist take in the Trust
Layer to confirm toxicity is being appropriately managed?
a) Access the Toxicity Detection log in the Setup and export all entries where the Toxicity Detected is true
b) Create a flow that send an email to a specified address each time toxicity score from the responses
exceeds a predefined threshold
c) Create a Trust Layer audit report withing Data Cloud that uses a toxicity detector type filter to display
toxic responses and their respective scores
57. An AI Specialist has 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 the AI Specialist do to identify the root cause of the problem?
a) In Copilot Builder within the Dynamic Panel, confirm selected action and observe the values in Input and
Output sections
b) In Copilot Builder, verify the utterance entered by the user and review session event logs for debug
information
c) In Copilot Builder within the Dynamic Panel, turn on dynamic debugging to show the inputs and outputs
58. When configuring a prompt template, an AI Specialist previews 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?
59. Universal Containers (UC) wants to enable its sales team to use AI to suggest recommended products
from its catalog. Which type of prompt template should UC use?
60. What is the primary function of the planner service in the Einstein Copilot system?
61. Universal Containers (UC) wants to enable its sales team with automatic post-call visibility into mention
of competitors, products, and other custom phrases. Which feature should the AI Specialist set up to
enable UC’s sales team?
a) Call Summaries
b) Call Explorer
c) Call Insights
62. A sales rep at Universal Containers 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 AI feature should an AI Specialist recommend to help the rep get
the details they might have missed during conversations?
a) Call Summaries
b) Call Explorer
c) Sales Summary
63. Universal Containers wants 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 from the order fulfillment process. How should an AI Specialist apply the
power of conversational AI to this use case?
64. When a customer chat is initiated, which functionality in Salesforce provides generative AI replies or
draft emails based on recommended knowledge articles?
65. Universal Containers (UC) wants to offer personalized service experiences and reduce agent handling
time with AI-generated email responses, grounded in Knowledge base. Which AI capability should UC
use?
66. Universal Containers implements 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?
Marina Carabelos Sánchez
Latest Update 22-01-2025
a) Action Triggers
b) Output Types
c) Instructions
67. An AI Specialist turned on Einstein Generative AI in Setup. Now, the AI Specialist 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?
a) The Prompt Template User permission set was not assigned correctly
b) The Prompt Template Manager permission set was not assigned correctly
c) The large language model (LLM) was not configured correctly in Data Cloud
68. Universal Containers is very concerned about security compliance and wants to understand:
Which prompt text is sent to the large language model (LLM)
How it is masked
The masked response
What should the AI Specialist recommend?
69. Universal Containers is evaluating Einstein Generative AI features to improve the productivity of the
service center operation. Which features should the AI Specialist recommend?
70. Amid their busy schedules, sales reps at Universal Containers dedicate time to follow up with prospects
and existing clients via email regarding renewals or new deals. They spend many hours through 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?
71. Universal Containers (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 e-mail was selected, which AI model should UC use to achieve this?
72. An AI Specialist at Universal Containers is 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 guidelines, using only associated opportunity information, and to encourage the
recipient to take the desired action. How should the AI Specialist include these instructions on a new line
in the prompt template?
Marina Carabelos Sánchez
Latest Update 22-01-2025
73. Universal Containers (UC) has 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 should the new support reps use to understand the details of a case without
reading through each case comment?
a) Einstein Copilot
b) Einstein Sales Summaries
c) Einstein Work Summaries
74. Universal Containers (UC) wants to improve the efficiency of addressing customer questions and reduce
agent handling time with AI-generated responses. The agents should be able to leverage their existing
knowledge based 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?
75. Universal Containers’ current AI data masking rules do not align with organizational privacy and security
policies and requirements. What should an AI Specialist recommend to resolve the issue?
a) A tool for developers to use in Vital Studio Code that creates prompts for Apex programming, assisting
developers in writing code more efficiently
b) A tool within Salesforce offering real-time AI-powered suggestions and guidance to users, improving
productivity and decision-making
c) A tool that enables companies to create reusable prompts for large language models (LLMs), bringing
generative AI responses to their flow of work
77. The AI Specialist 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 the AI
Specialist take upon modifying the masked fields?
78. What should an AI Specialist consider when using related list merge fields in a prompt template
associate with an Account object in Prompt Builder?
a) The Activities related list on the Account object is not supported because it is a polymorphic field
Marina Carabelos Sánchez
Latest Update 22-01-2025
b) If person accounts have been enabled, merge fields will not be available for the Account object
c) Prompt generation will yield no response when there is no related list associated with an Account in
runtime
79. Before activating a custom copilot action, an AI Specialist would like to understand multiple real-world
user utterances to ensure the action is being selected appropriately. Which tool should the AI Specialist
recommend?
a) Model Playground
b) Einstein Copilot
c) Copilot Builder
80. An AI Specialist 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?
a) The number of tokens generated by the dynamic nature of the prompt template will vary by record
b) The template type needs to be switched to Flex to accommodate the variable amount of tokens
generated by the prompt grounding
c) The number of tokens that can be processed by the LLM varies with the total user demand
81. Universal Containers (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? Churn = abandono
82. Universal Containers wants 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 the
AI Specialist recommend to the sales team?
83. An AI Specialist is considering using a Field Generation prompt template type. What should the AI
Specialist check before creating the Filed Generation prompt to ensure it is possible for the field to be
enabled for generative AI?
a) That the field chosen must be a rich text field with 255 characters or more
b) That the org is set to API version 59 or higher
c) That the Lightning page layout where the field will reside has been upgraded to Dynamic Forms
84. Universal Containers plans to enhance the customer support team’s productivity using AI. Which specific
use case necessitates the use of Prompt Builder?
85. Which feature in the Einstein Trust Layer helps to minimize the risks of jailbreaking and prompt injection
attacks?
86. 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?
87. A service agent is looking at a custom object that stores travel information. They recently received a
weather alert and now needs to cancel flights for the customers that are related with the itinerary. The
service agent needs to review the Knowledge articles about cancelling and rebooking the customer
flights. Which Einstein Copilot capability helps the agent accomplish this?
a) Execute tasks based on available actions, answering questions using information from accessible
Knowledge articles
b) Generate a knowledge article based off the prompts that the agent enters to create steps to cancel
flights
c) Invoke a flow which makes a call to external data to create a knowledge article
a) Copilot Actions page, the record page for the copilot action, or the Copilot Action Library tab
b) Copilot Actions page or Global Actions
c) Copilot Detail page, Global Actions, or the record page for the copilot action
89. In Model Playground, which hyperparameters of an existing Salesforce-enable foundational model can
an AI Specialist change?
90. 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 the AI Specialist recommend?
a) Sales Email
b) Field Generation
c) Record Summary
91. Universal Containers wants to make a sales proposal and directly use data from multiple unrelated
objects (standard and custom) in a prompt template. What should the AI Specialist recommend?
a) Create a Flex template to add resources with standard and custom objects as inputs.
Marina Carabelos Sánchez
Latest Update 22-01-2025
b) Create a prompt template passing in a special custom object that connects the records temporarily
c) Create a prompt template-triggered flow to access the data from standard and custom objects.
92. What is an AI Specialist able to do when the ''Enrich event logs with conversation data" setting in
Einstein Copilot is enabled?
a) View the user click path that led to each copilot action.
b) View session data including user Input and copilot responses for sessions over the past 7days.
c) Generate details reports on all Copilot conversations over any time period.
93. In a sales scenario, which generative AI feature in Einstein can be used to generate personalized email
content for prospects?
a) Einstein Discovery
b) Einstein Write
c) Einstein Automate
d) Einstein GPT for Sales
94. How does the Einstein Trust Layer ensure grounding of AI models?
95. Universal Containers’ (UC) 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?
a) Model Builder
b) App Builder
c) Copilot Builder
96. A Salesforce Administrator is exploring the capabilities of Einstein Copilot to enhance user interaction
within their organization. They are particularly interested in how Einstein Copilot processes user
requests and the mechanism it employs to deliver responses. The administrator is evaluating whether
Einstein Copilot directly interfaces with a large language model (LLM) to fetch and display responses to
user inquiries, facilitating a broad range of requests from users. How does Einstein Copilot handle user
requests In Salesforce?
a) Einstein Copilot will trigger a flow that utilizes a prompt template to generate the message.
b) Einstein Copilot will perform an HTTP callout to an LLM provider.
c) Einstein Copilot analyzes the user's request and LLM technology is used to generate and display the
appropriate response.
97. Which feature in the Einstein Trust Layer primarily addresses security concerns in Al model
deployment?
98. When dealing with a high volume of customer service requests, which Einstein feature is most
appropriate for automating responses?
99. Which business scenario is most appropriate for using a custom generative model in Salesforce?
100. Universal Containers 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?
a) Einstein Copilot Delete Record Action permission is not associated to the user.
b) Einstein Copilot does not have the permission to delete the user's records.
c) Einstein Copilot does not support the Delete Record action.
101. What is the primary purpose of Model Builder in Salesforce? (lo preguntaban antes pero con otras
respuestas)
102. When configuring a custom Al model in Salesforce, what is a key factor to consider?
103. Which type of model would be most suitable for generating personalized customer experiences?
104. What is the benefit of using a Bring Your Own Large Language Model (BYOLLM) in Salesforce?
105. Which feature of the Einstein Trust Layer is designed to identify and reduce the risk of harmful or toxic
outputs from generative Al?
106. How does the Einstein Trust Layer help organizations comply with strict data privacy regulations?
107. An Al Specialist wants to ground a new prompt template with the User related list. What should the Al
Specialist consider?
108. What is the primary role of Prompt Defense in the Einstein Trust Layer?
109. Which feature of the Einstein Trust Layer is critical for maintaining compliance with international data
protection standards?
110. In a scenario where a sales representative needs to quickly generate personalized email templates for
outreach, which Einstein for Sales feature would be most appropriate?
111. For a customer service scenario where a support agent requires suggestions for responses to customer
queries, which Einstein for Service feature should be used?
112. Which Einstein for Sales feature can automatically create follow-up tasks based on customer
interactions and insights?
Marina Carabelos Sánchez
Latest Update 22-01-2025
113. If a sales team wants to generate predictive insights about customer behavior and preferences, which
Einstein for Sales feature would be suitable?
114. For a scenario where customer service needs to automate ticket creation from incoming emails, which
Einstein for Service feature is most appropriate?
a) Einstein Bots
b) Einstein Case Classification
c) Einstein Email-to-Case
d) Einstein Knowledge Management
115. Which Einstein for Sales feature helps identify the best times to contact leads based on historical
engagement data?
116. In a scenario where customer service agents need to recommend relevant knowledge base articles,
which Einstein for Service feature would be helpful?
117. Northern Trail Outfitters (NTO) wants 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 an Al
Specialist take to make this option available to NTO?
a) Data masking
b) Dynamic grounding with secure data retrieval
Marina Carabelos Sánchez
Latest Update 22-01-2025
119. Universal Containers wants to enable its sales team to get insights into product and competitor names
mentioned during calls. How should UC meet this requirement?
a) Enable Einstein Conversation Insights, assign permission sets, define recording managers, and customize
insights with up to 50 competitor names.
b) Enable Einstein Conversation Insights, connect a recording provider, assign permission sets, and
customize insights with up to 25 products.
c) Enable Einstein Conversation Insights, enable sales recording, assign permission sets, and customize
insights with up to 50 products.
120. Universal Containers wants to reduce overall agent handling time by minimizing the time spent typing
routine answers for common questions in chat and reducing post-chat analysis by suggesting values for
case fields. Which combination of Einstein for Service features enables this effort?
121. Universal Containers is 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?
122. Universal Containers wants 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 an AI
Specialist implement to meet this requirement?
a) Create a screen flow to collect the sales order number and invoke the prompt template using the
standard "Prompt Template" flow action.
b) Create a template-triggered prompt flow and invoke the prompt template using the standard "Prompt
Template" flow action.
c) Create an autolaunched flow and invoke the prompt template using the standard "Prompt Template"
flow action.
123. Universal Containers has 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?
a) The user does not have the Prompt Template User permission set assigned.
b) The prompt template associated with the summary field is not activated for that user.
c) The user does not have the Generative AI User permission set assigned.
124. Universal Containers (UC) is 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?
Marina Carabelos Sánchez
Latest Update 22-01-2025
125. How should an organization use the Einstein Trust Layer to audit, track, and view masked data?
a) Utilize the audit trail that captures and stores all LLM submitted prompts in Data Cloud.
b) In Setup, use Prompt Builder to send a prompt to the LLM requesting for the masked data.
c) Access the audit trail in Setup and export all user-generated prompts.
126. An AI Specialist implements 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. The AI Specialist
needs to configure the system to use the most accurate and up-to-date information for email
generation. Which grounding technique should the AI Specialist use?
127. Universal Containers (UC) has 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?
a) Service AI Grounding
b) Work Summaries
c) Service Replies
128. Universal Containers wants 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?
129. Universal Containers is planning a marketing email about products that most closely match a
customer's expressed interests. What should an AI Specialist recommend to generate this email?
a) Standard email marketing template using Apex or flows for matching interest in products
b) Custom sales email template which is grounded with interest and product information
c) Standard email draft with Einstein and choose standard email template
130. An AI Specialist is creating a custom action in Einstein Copilot. Which option is available for the AI
Specialist to choose for the custom copilot action?
a) Apex trigger
b) SOQL
c) Flows
131. 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. Which AI
capability should the team use?
Marina Carabelos Sánchez
Latest Update 22-01-2025
a) Einstein Copilot
b) Prompt Builder
c) Model Builder
132. An AI Specialist is tasked with configuring a generative model to create personalized sales emails using
customer data stored in Salesforce. The AI Specialist has already fine-tuned a large language model
(LLM) on the OpenAI platform. How should the AI Specialist integrate the custom LLM into Salesforce?
(REVISAR SI ESTÁ REPETIDA)
a) Create an application of the custom LLM and embed it in Sales Cloud via iFrame.
b) Add the fine-tuned LLM in Einstein Studio Model Builder.
c) Enable model endpoint on OpenAI and make callouts to the model to generate emails.
133. Universal Containers (UC) wants 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?
134. Universal Containers is 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?
135. Based on the user utterance, "Show me all the customers in New York," which standard Einstein Copilot
action will the planner service use?
a) Query Records
b) Select Records
c) Fetch Records
136. Universal Containers is using Einstein Copilot for Sales to find similar opportunities to help close deals
faster. What is one criterion that Einstein Copilot for Sales uses to match similar opportunities?
137. An AI Specialist wants to include data from the response of external service invocation (REST API
callout) into the prompt template. How should the AI Specialist meet this requirement? (seen more or
less before)
138. What should an AI Specialist consider when using related list merge fields in a prompt template
associated with an Account object in Prompt Builder?
Marina Carabelos Sánchez
Latest Update 22-01-2025
a) The Activities related list on the Account object is not supported because it is a polymorphic field.
b) If person accounts have been enabled, merge fields will not be available for the Account object.
c) Prompt generation will yield no response when there is no related list associated with an Account in
runtime.
a) Not Safe
b) Moderately safe
c) Safe
140. Universal Containers (UC) is implementing Service AI Grounding to enhance its customers 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 AI Grounding?
141. Universal Containers wants to use an external large language model (LLM) in Prompt Builder. What
should and AI Specialist recommend?
a) Use Flow and External Services to bring data from an external LLM
b) Use BYO-LLM functionality in Einstein Studio
c) Use Apex to connect to an external LLM and ground the prompt
142. Universal Containers plans to implement prompt templates that utilize foundation models. What
should the AI Specialist consider when building prompt templates in Prompt Builder?
a) Train LLM with data using different writing styles including word choice, intensifiers, emojis and
punctuation
b) Ask it to role-play as a character in the prompt template to provide more context to the LLM
c) Include multiple-choice questions within the prompt to test the LLM’s understanding of the context
143. Universal Containers has an active standard email prompt template that does not fully deliver on the
business requirements. Which steps should an AI Specialist take to use the content of the standard
prompt email template in question and customize it to fully meet the business requirements?
144. An AI Specialist at Universal Containers (UC) is 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 the AI Specialist use and which consideration should they review?
Marina Carabelos Sánchez
Latest Update 22-01-2025
145. An AI Specialist is tasked to optimize a business process flow by assigning actions to agents within the
Salesforce Agentforce Platform.
What is the correct method for the AI Specialist to assign actions to an Agent?
A. Assign the action to a Topic First in Agent Builder
B. Assign the action to a Topic first on the Agent Actions detail page.
C. Assign the action to a Topic first on Action Builder.