Salesforce AI Specialist 2
Salesforce AI Specialist 2
1 of 60.
An Al Specialist is tasked with configuring a generative model to create personalized sales emails using customer data stored in Salesforce. The Al Specialist has already fine-
tuned a large language model (LLM) on the OpenAl platform. Security and data privacy are critical concerns for the client.
How should the Al Specialist integrate the custom LLM into Salesforce?
A.Q Enable model endpoint on OpenAl and make callouts to the model to generate emails.
8.() Create an application of the custom LLM and embed it in Sales Cloud via iFrame.
C.@) Add the fine-tuned LLM in Einstein Studio Mode! Builder.
2 of 60. Universal Containers is evaluating Einstein Generative Al features to improve the productivity of the service center operation.
““
3 of 60. Universal Containers implements Custom Agent Actions to enhance its customer service operations. The development team needs to understand the core components
of a Custom Agent Action to ensure proper configuration and functionality.
What should the development team review in the Custom Agent Action configuration to identify one of the core components of a Custom Agent Action?
A@) Instructions
8.0 Action Triggers
C.O Output Types
4 of 60. Universal Containers (UC) wants 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.
\ A@) Turn on Service Replies, Service Al Grounding, and Grounding with Knowledge.
8. Tum on Service Al Grounding and Grounding with Knowledge.
€. Turn on Service Al Grounding, Grounding with Case, and Service Replies.
S of 60. An Al 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
* Tone and voice examples
A.Q Utilize a standard email template and manually insert the required data fields.
ao Call a prompt initiated flow to fetch and ground the required data
€. Create a flex template that takes the records in question as inputs.
6 of 60. An Al Specialist has created an Agent 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 Al Specialist do to identify the root cause of the problem?
A.Q In Agent Builder within the Dynamic Panel, confirm selected action and observe the values in Input and Output sections.
8Q) In Agent Builder, verify the utterance entered by the user and review session event logs for debug information.
€. In Agent Builder within the Dynamic Panel, turn on dynamic debugging to show the inputs and outputs.
7 of 60. Universal Containers tests out a new Einstein Generative Al 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?
8 of 60. Universal Containers (UC) wants to offer personalized service experiences and reduce agent handling time with Al-generated email responses, grounded in Knowledge
base.
. 9 of 60. What is the correct process to leverage Prompt Builder in a Salesforce org?
1 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.
| 8.() 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
C.(Q 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.
TN TN (O B
10 of 60. A data scientist needs to view and manage models in Einstein Studio. The data scientist also needs to create prompt templates in Prompt Builder.
-“
11 of 60. When configuring a prompt template, an Al Specialist previews the results of the prompt template they've written. They see two distinct text outputs: Resolution and
Response.
\ A@) 1t shows the response from the LLM based on the sample record
8.0 It shows which sensitive data is masked before it is sent to the LLM.
€. It shows the full text that is sent to the Trust Layer.
12 of 60. What should an Al Specialist consider when using related list merge fields in a prompt template associated 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
| 8.0 Prompt generation will yield no response when there is no related list associated with an Account in runtime
C.Q If person accounts have been enabled, merge fields will not be available for the Account object
Scanned h CamScanner
¢_kryterion
Test Aids~ Support Exit Exam
. partner
13 of 60. An Al Specialist is tasked with analyzing Agent interactions looking into user inputs, requests, and queries to identify patterns and trends.
14 of 60. An Al 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 Al Specialist gather the necessary data for the prompt template?
A. () Select the Account Opportunity object as a resource when creating the prompt template.
8 (@) Create a flow to retrieve the opportunity information.
€. Select the latest Opportunities related list as a merge field
15 of 60. 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.
I () (e e
16 of 60. 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 for the order fulfillment process.
How should an Al Specialist apply the power of conversational Al to this use case?
17 of 60. In Model Playground, which hyperparameters of an existing Salesforce-enabled foundational model can an Al Specialist change?
18 of 60. 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 prompts?
“m
19 of 60. 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 Al features.
Which Einstein Generative Al feature should an Al Specialist recommend to help the rep get the details they might have missed during a conversation?
TN IS [T Erme
20 of 60. Before activating a custom Agent action, an Al Specialist would like to understand multiple real-world user utterances to ensure the action is being selected
appropriately.
w o
21 of 60. Universal Containers plans to enhance the customer support team's productivity using Al.
A.Q Estimating support ticket volume based on historical data and seasonal trends
n° Creating a draft of a support bulletin post for new product patches
€. Creating an Al-generated customer support agent performance score
TN TN (0 B
I+
A.Q A tool for developers to use in Visual Studio Code that creates prompts for Apex programming, assisting developers in writing code more efficiently.
8. A tool within Salesforce offering real-time Al-powered suggestions and guidance to users, improving productivity and decision-making.
co A tool that enables companies to create reusable prompts for large language models (LLMs), bringing generative Al responses to their flow of work
23 of 60. Universal Containers (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.
24 of 60. How does the Einstein Trust Layer ensure that sensitive data is protected while generating useful and meaningful responses?
25 of 60. 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 Al model should UC use to achieve this?
A o Predictive model
m BRI
26 of 60.
Universal Containers is considering leveraging the Einstein Trust Layer in conjunction with Einstein Generative Al Audit Data.
What should the Al Specialist check before creating the Field Generation prompt to ensure it is possible for the field to be enabled for generative AI?
A o That the field chosen must be a rich text field with 255 characters or more
0
Time Remaining: 01:26:22@
28 of 60. When a customer chat is initiated, which functionality in Salesforce provides generative Al replies or draft emails based on recommended Knowledge articles?
29 of 60. Universal Containers' current Al data masking rules do not align with organizational privacy and security policies and requirements.
30 of 60. 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 Al solution should the new support reps use to understand the details of a case without reading through each case comment?
31 of 60. What is best practice when refining Agentforce custom action instructions?
TN RN [ e
32 of 60. Universal Containers (UC) has 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?
A.(Q Submit a prompt review case to Salesforce and conduct thorough testing in the playground to refine outputs until they meet user expectations.
n’ Create concise, cle nd consistent prompt templates with effective grounding, contextual role-playing, clear instructions, and iterative feedback.
€. Enable prompt test mode, allocate different prompt var 10ns to a subset of users for evaluation, and standardize the most effective model based on performance feedback.
TN RN [ B
A, Enable data scientists to train predictive Al models with historical CRM data using built-in machine learning capabilities.
8. Enable Salesforce admin users to create and train custom large language models (LLMs) using CRM data.
co Bring together a convers: ional interface for interacting with Al for all Salesforce users, such as developers and ecommerce retailers.
34 of 60. What is an Al Specialist able to do when the "Enrich event logs with conversation data” setting in the Agentforce configuration is enabled?
A.Q View the user click path that led to each Agent action.
8. Generate details reports on all Agent conversations over any time period
c° View session data including user input and Agent responses for sessions over the past 7 days.
“ (‘WA‘
35 of 60. 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.
A @) Generate a Knowledge article based off the prompts that the agent enters to create steps to cancel flights.
8. Execute tasks based on available actions, answering questions using information from accessible Knowledge articles.
C.Q Invoke a flow which makes a call to external data to create a Knowledge article
36 of 60. An Al 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 Al Specialist use to include data from the related list of opportunities in the prompt template?
37 of 60. Which feature in the Einstein Trust Layer helps to minimize the risks of jailbreaking and prompt injection attacks?
A° Prompt Defense
8. O Secure Data Retrieval and Grounding
38 of 60. Universal Containers (UC) uses Salesforce Service Cloud to support its customers and agents handling cases. UC is considering implementing Agentforce and
extending Service Cloud to mobile users.
A@) When the goal is to streamline customer support processes and improve response times
8. When the main objective is to enhance data security and compliance measures
€. When the focus is on optimizing marketing campaigns and strategies
39 of 60. What is the role of the large language model (LLM) in understanding intent and executing an Agent Action?
A.Q) Determine a user's topic access and sort actions by priority to be executed
8(@) !dentify the best matching topic and actions and correct order of execution
€. Q Find similar requested topics and provide the actions that need to be executed
40 of 60. An administrator wants to check the response of the Flex prompt template they've built, but the preview button is greyed out.
41 of 60. An Al Specialist wants to use the related lists from an account in a custom prompt template.
What should the Al Specialist consider when configuring the prompt template?
42 of 60. Universal Containers wants to utilize Agentforce for Sales to help sales reps reach their sales quotas by providing Al-generated plans containing guidance and steps
for closing deals.
43 of 60. Universal Containers' service team wants to customize the standard case summary response from Agentforce.
A.Q Customize the standard Record Summary template for the Case object.
8 (@) Create a custom Record Summary prompt template for the Case object.
€. Summanze the Case with a standard Agent action
44 of 60. An Al 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 Al-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 Al Specialist include these instructions on a new line in the prompt template?
N ISR (T B
45 of 60. 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?
46 of 60. An Al Specialist configured Data Masking within the Einstein Trust Layer.
How should the Al Specialist begin validating that the correct fields are being masked?
A o Request the Einstein Generative Al 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.
47 of 60. Universal Containers (UC) wants to enable its sales team with automatic post-call visibility into mention of competitors, products, and other custom phras:
Which feature should the Al Specialist set up to enable UC's sales team?
A @ Call Insights
8. Call Summaries
€.Q Call Explorer
48 of 60. Universal Containers (UC) wants to assess Salesforce's generative Al 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 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 the Al Specialist highlight to UC that addresses these requirements?
49 of 60. 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
50 of 60. Universal Containers (UC) is experimenting with using public Generative Al models and is 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 a Salesforce Al Specialist recommend to address these concerns?
mm
51 of 60. The marketing team at Universal Containers is looking for a way to personalize emails based on customer behavior, preferences, and purchase history.
52 of 60. An Al Specialist turned on Einstein Generative Al in Setup. Now, the Al Specialist would like to create custom prompt templates in Prompt Builder. However, they
cannot access Prompt Builder in the Setup menu.
A.QQ The Prompt Template User permission set was not assigned correctly.
8.(Q The large language model (LLM) was not configured correctly in Data Cloud
cc The Prompt Template Manager permission set was not assigned correctly.
m - feview x!
54 of 60. Universal Containers (UC) wants to use Flow to bring data from unified Data Cloud objects to prompt templates.
55 of 60. The Al 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 Al Specialist take upon modifying the masked fields?
A.@ Test and confirm that the responses generated from prompts that utiize the data and masked data do not adversely affect the quality of the generated response
8.() Turn off the Einstein Trust Layer and turn it on again.
€. Tum on Einstein Feedback so that end users can report if there are any negative side effects on Al features.
56 of 60. An Al Specialist built a Field Generation prompt template that worked for many records, but users are reporting random failures with token limit errors.
A.QQ The template type needs to be switched to Flex to accommodate the variable amount of tokens generated by the prompt grounding
8.() The number of tokens that can be processed by the LM varies with total user demand,
c° The number of tokens generated by the dynamic nature of the prompt template will vary by record
57 of 60. Universal Containers (UC) wants to enable its sales team to use Al to suggest recommended products from its catalog.
58 of 60. An Al Specialist wants to include data from the response of external service invocation (REST API callout) into the prompt template.
N N (T e
59 of 60. 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 throughout the week reviewing past communications and details about their customers before performing their outreach.
Which standard Agent action helps sales reps draft personalized emails to prospects by generating text based on previous successful communications?
60 of 60. Universal Containers wants 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 an Al Specialist take in the Trust Layer to confirm toxicity is being appropriately managed?
A.( Create a flow that sends an email to a specified address each time the toxicity score from the response exceeds a predefined threshold.
8 (@) Create a Trust Layer audit report within Data Cloud that uses a toxicity detector type filter to display toxic responses and their respective scores.
€. Access the Toxicity Detection log in Setup and export all entries where isToxicityDetected is true.
TN RN (e e
Assessment Summary
Number of Items Answered: 60
Number of Items Unanswered: o
Number of Items Marked for Review: ]
Answers
1LC 2.8 3A .A
5.8 6.8 7.€C 8.A
92.A 10.8 1A 12. A
13.8 14.8 15.C 16. A
172.8 18. A 19.C 20.C
2.8 22.C 23.C 24. A
25.C 26.8 27.€C 28.8
29, C 30, C 3.8 32.8
33.C 34.C 35.A 36. A
37.A 38, A 39.8 40.C
4LA 42.8 43.8 44.C
45.8 46. 8 a7. A 48.A
49. A 50. A SL.A 52.C
23.C 24.8 55. A 56.C
S2.A 58.8 9. C 60. 8