Salesforce-AI-Specialist試験問題を今すぐ試そう！最新の[2025年最新] 正解回答付き [Q33-Q54]

Salesforce-AI-Specialist試験問題を今すぐ試そう！最新の[2025年最新] 正解回答付き

練習できるSalesforce-AI-Specialistには認定ガイド問題と解答とトレーニングを提供しています

質問 # 33
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 that can be processed by the LLM varies with total user demand.
B. The number of tokens generated by the dynamic nature of the prompt template will vary by record.
C. The template type needs to be switched to Flex to accommodate the variable amount of tokens generated by the prompt grounding.

正解：B

解説：
The reason behind the token limit errors lies in the dynamic nature of the prompt template used in Field Generation. In Salesforce's AI generative models, each prompt and its corresponding output are subject to a token limit, which encompasses both the input and output of the large language model (LLM). Since the prompt template dynamically adjusts based on the specific data of each record, the number of tokens varies per record. Some records may generate longer outputs based on their data attributes, pushing the token count beyond the allowable limit for the LLM, resulting in token limit errors.
This behavior explains why users experience random failures-it is dependent on the specific data used in each case. For certain records, the combined input and output may fall within the token limit, while for others, it may exceed it. This variation is intrinsic to how dynamic templates interact with large language models.
Salesforce provides guidance in their documentation, stating that prompt template design should take into account token limits and suggests testing with varied records to avoid such random errors. It does not mention switching to Flex template type as a solution, nor does it suggest that token limits fluctuate with user demand. Token limits are a constant defined by the model itself, independent of external user load.
Reference:
Salesforce Developer Documentation on Token Limits for Generative AI Models Salesforce AI Best Practices on Prompt Design (Trailhead or Salesforce blog resources)

質問 # 34
When a customer chat is initiated, which functionality in Salesforce provides generative AI replies or draft emails based on recommended Knowledge articles?

A. Einstein Reply Recommendations
B. Einstein Service Replies
C. Einstein Grounding

正解：B

解説：
When acustomer chat is initiated,Einstein Service Repliesprovidesgenerative AI replies or draft emails based on recommendedKnowledge articles. This feature uses the information from theSalesforce Knowledge baseto generate responses that are relevant to the customer's query, improving the efficiency and accuracy of customer support interactions.
* Option Bis correct becauseEinstein Service Repliesis responsible for generating AI-driven responses based on knowledge articles.
* Option A(Einstein Reply Recommendations) is focused on recommending replies but does not generate them.
* Option C(Einstein Grounding) refers to grounding responses in data but is not directly related to drafting replies.
References:
* Einstein Service Replies Overview:https://help.salesforce.com/s/articleView?id=sf.
einstein_service_replies.htm

質問 # 35
Universal Containers wants to be able to detect with a high level 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. Access the Toxicity Detection log in Setup and export all entries where isToxicityDetected is true.
B. Create a Trust Layer audit report within Data Cloud that uses a toxicity detector type filter to display toxic responses and their respective scores.
C. Create a flow that sends an email to a specified address each time the toxicity score from the response exceeds a predefined threshold.

正解：B

解説：
To ensure that content generated by a large language model (LLM) is appropriately screened for toxic language, the AI Specialist should create aTrust Layer audit reportwithinData Cloud. By using thetoxicity detector type filter, the report can displaytoxic responsesalong with their respective toxicity scores, allowing Universal Containersto monitor and manage any toxic content generated with a high level of confidence.
* Option Cis correct because it enables visibility into toxic language detection within theTrust Layerand allows for auditing responses for toxicity.
* Option Asuggests checking a toxicity detection log, butSalesforceprovides more comprehensive options via the audit report.
* Option Binvolves creating a flow, which is unnecessary for toxicity detection monitoring.
References:
* Salesforce Trust Layer Documentation:https://help.salesforce.com/s/articleView?id=sf.
einstein_trust_layer_audit.htm

質問 # 36
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 an autolaunched flow and invoke the prompt template using the standard "Prompt Template" flow action.
B. Create a screen flow to collect sales order number and invoke the prompt template using the standard "Prompt Template" flow action.
C. Create a template-triggered prompt flow and invoke the prompt template using the standard "Prompt Template" flow action.

正解：B

解説：
To implement a solution where users enter a sales order number and the system generates a summary, the AI Specialist should create a screen flow to collect the sales order number and invoke the prompt template. The standard "Prompt Template" flow action can then be used to trigger the custom prompt, providing a summary of the sales order header and details.
Option B, creating a template-triggered prompt flow, is not necessary for this scenario because the requirement is to directly collect input through a screen flow.
Option C, using an autolaunched flow, would be inappropriate here because the solution requires user interaction (entering a sales order number), which is best suited to a screen flow.
Salesforce AI Specialist Reference:
For further guidance on creating prompt templates with flows: https://help.salesforce.com/s/articleView?id=sf.prompt_template_flow_integration.htm

質問 # 37
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. SOQL
B. Apex trigger
C. Flows

正解：C

解説：
When creating acustom actionin Einstein Copilot, one of the available options is to useFlows. Flows are a powerful automation tool in Salesforce, allowing the AI Specialist to define custom logic and actions within the Copilot system. This makes it easy to extend Copilot's functionality without needing custom code.
WhileApex triggersandSOQLare important Salesforce tools,Flowsare the recommended method for creating custom actions within Einstein Copilot because they are declarative and highly adaptable.
For further guidance, refer toSalesforce Flow documentationandEinstein Copilot customization resources.

質問 # 38
Universal Containers Is Interested In Improving the sales operation efficiency by analyzing their data using Al-powered predictions in Einstein Studio.
Which use case works for this scenario?

A. Predict customer sentiment toward a promotion message.
B. Predict customer lifetime value of an account.
C. Predict most popular products from new product catalog.

正解：B

解説：
For improvingsales operations efficiency,Einstein Studiois ideal for creating AI-powered models that can predict outcomes based on data. One of the most valuable use cases is predictingcustomer lifetime value, which helps sales teams focus on high-value accounts and make more informed decisions.Customer lifetime value (CLV)predictions can optimize strategies around customer retention, cross-selling, and long-term engagement.
* Option Bis the correct choice as predicting customer lifetime value is a well-established use case for AI in sales.
* Option A(customer sentiment) is typically handled through NLP models, whileOption C(product popularity) is more of a marketing analysis use case.
References:
* Salesforce Einstein Studio Use Case Overview:https://help.salesforce.com/s/articleView?id=sf.
einstein_studio_overview

質問 # 39
In Model Playground, which hyperparameters of an existing
Salesforce-enabled foundational model can an AI Specialist change?

A. Temperature, Frequency Penalty, Output Tokens
B. Temperature, Top-k sampling, Presence Penalty
C. Temperature, Frequency Penalty, Presence Penalty

正解：C

解説：
InModel Playground, an AI specialist working with a Salesforce-enabled foundational model has control over specific hyperparameters that can directly affect the behavior of the generative model:
* Temperature: Controls the randomness of predictions. A higher temperature leads to more diverse outputs, while a lower temperature makes the model's responses more focused and deterministic.
* Frequency Penalty: Reduces the likelihood of the model repeating the same phrases or outputs frequently.
* Presence Penalty: Encourages the model to introduce new topics in its responses, rather than sticking with familiar, previously mentioned content.
These hyperparameters are adjustable to fine-tune the model's responses, ensuring that it meets the desired behavior and use case requirements. Salesforce documentation confirms that these three are the key tunable hyperparameters in the Model Playground.
For more details, refer toSalesforce AI Model Playgroundguidance from Salesforce's official documentation on foundational model adjustments.

質問 # 40
Universal Containers' service team wants to customize the standard case summary response from Einstein Copilot.
What should the AI Specialist do to achieve this?

A. Summarize the Case with a standard copilot action.
B. Create a custom Record Summary prompt template for the Case object.
C. Customize the standard Record Summary template for the Case object,

正解：B

解説：
To customize thecase summary responsefromEinstein Copilot, the AI Specialist should create acustom Record Summary prompt templatefor theCase object. This allows Universal Containers to tailor the way case data is summarized, ensuring the output aligns with specific business requirements or user preferences.
* Option A(customizing the standard Record Summary template) does not provide the flexibility required for deep customization.
* Option B(standard Copilot action) won't allow customization; it will only use default settings.
Refer toSalesforce Prompt Builder documentationfor guidance on creating custom templates for record summaries.

質問 # 41
The marketing team at Universal Containers is looking for a way personalize emails based on customer behavior, preferences, and purchase history.
Why should the team use Einstein Copilot as the solution?

A. To send automated emails to all customers
B. To generate relevant content when engaging with each customer
C. To analyze past campaign performance

正解：B

解説：
Einstein Copilotis designed to assist in generating personalized, AI-driven content based on customer data such as behavior, preferences, and purchase history. For the marketing team atUniversal Containers, this is the perfect solution to create dynamic and relevant email content. By leveragingEinstein Copilot, they can ensure that each customer receives tailored communications, improving engagement and conversion rates.
* Option Ais correct asEinstein Copilothelps generate real-time, personalized content based on comprehensive data about the customer.
* Option Brefers more to Einstein Analytics or Marketing Cloud Intelligence, andOption Cdeals with automation, which isn't the primary focus ofEinstein Copilot.
References:
* Salesforce Einstein Copilot Overview:https://help.salesforce.com/s/articleView?
id=einstein_copilot_overview.htm

質問 # 42
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?

A. Storing this data requires Data Cloud to be provisioned.
B. Storing this data requires a custom object for data to be configured.
C. Storing this data requires Salesforce big objects.

正解：A

質問 # 43
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?

A. Generative model
B. Predictive model
C. Predictive model and generative model

正解：B

解説：
Universal Containersshould use aPredictive modelto decide which of the three emails to send based on the customer'slifetime value scoreandmarket segment. Predictive models analyze data to forecast outcomes, and in this case, it would predict the most appropriate email to send based on customer attributes. Additionally, predictive models can provideexplainabilityto show why a certain email was chosen, which is crucial for UC' s requirement to explain the decision-making process.
* Generative modelsare typically used for content creation, not decision-making, and thus wouldn't be suitable for this requirement.
* Predictive modelsoffer the ability to explain why a particular decision was made, which aligns with UC's needs.
Refer toSalesforce's Predictive AI model documentationfor more insights on how predictive models are used for segmentation and decision making.

質問 # 44
Universal Containers' 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

正解：A

解説：
To accessexternally-hosted models, such as a large language model (LLM) hosted on AWS, theModel Builderin Salesforce is the appropriate tool.Model Builderallows teams to integrate and deploy external AI models into the Salesforce platform, making it possible to leverage models hosted outside of Salesforce infrastructure while still benefiting from the platform's native AI capabilities.
* Option B, App Builder, is primarily used to build and configure applications in Salesforce, not to integrate AI models.
* Option C, Copilot Builder, focuses on building assistant-like tools rather than integrating external AI models.
Model Builder enables seamless integration with external systems and models, allowing Salesforce users to use external LLMs for generating AI-driven insights and automation.
Salesforce AI Specialist References:For more details, check the Model Builder guide here:https://help.
salesforce.com/s/articleView?id=sf.model_builder_external_models.htm

質問 # 45
How does the Einstein Trust Layer ensure that sensitive data is protected while generating useful and meaningful responses?

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

正解：A

解説：
The Einstein Trust Layer ensures that sensitive data is protected while generating useful and meaningful responses by masking sensitive data before it is sent to the Large Language Model (LLM) and then de-masking it during the response journey.
How It Works:
Data Masking in the Request Journey:
Sensitive Data Identification: Before sending the prompt to the LLM, the Einstein Trust Layer scans the input for sensitive data, such as personally identifiable information (PII), confidential business information, or any other data deemed sensitive.
Masking Sensitive Data: Identified sensitive data is replaced with placeholders or masks. This ensures that the LLM does not receive any raw sensitive information, thereby protecting it from potential exposure.
Processing by the LLM:
Masked Input: The LLM processes the masked prompt and generates a response based on the masked data.
No Exposure of Sensitive Data: Since the LLM never receives the actual sensitive data, there is no risk of it inadvertently including that data in its output.
De-masking in the Response Journey:
Re-insertion of Sensitive Data: After the LLM generates a response, the Einstein Trust Layer replaces the placeholders in the response with the original sensitive data.
Providing Meaningful Responses: This de-masking process ensures that the final response is both meaningful and complete, including the necessary sensitive information where appropriate.
Maintaining Data Security: At no point is the sensitive data exposed to the LLM or any unintended recipients, maintaining data security and compliance.
Why Option A is Correct:
De-masking During Response Journey: The de-masking process occurs after the LLM has generated its response, ensuring that sensitive data is only reintroduced into the output at the final stage, securely and appropriately.
Balancing Security and Utility: This approach allows the system to generate useful and meaningful responses that include necessary sensitive information without compromising data security.
Why Options B and C are Incorrect:
Option B (Masked data will be de-masked during request journey):
Incorrect Process: De-masking during the request journey would expose sensitive data before it reaches the LLM, defeating the purpose of masking and compromising data security.
Option C (Responses that do not meet the relevance threshold will be automatically rejected):
Irrelevant to Data Protection: While the Einstein Trust Layer does enforce relevance thresholds to filter out inappropriate or irrelevant responses, this mechanism does not directly relate to the protection of sensitive data. It addresses response quality rather than data security.
Reference:
Salesforce AI Specialist Documentation - Einstein Trust Layer Overview:
Explains how the Trust Layer masks sensitive data in prompts and re-inserts it after LLM processing to protect data privacy.
Salesforce Help - Data Masking and De-masking Process:
Details the masking of sensitive data before sending to the LLM and the de-masking process during the response journey.
Salesforce AI Specialist Exam Guide - Security and Compliance in AI:
Outlines the importance of data protection mechanisms like the Einstein Trust Layer in AI implementations.
Conclusion:
The Einstein Trust Layer ensures sensitive data is protected by masking it before sending any prompts to the LLM and then de-masking it during the response journey. This process allows Salesforce to generate useful and meaningful responses that include necessary sensitive information without exposing that data during the AI processing, thereby maintaining data security and compliance.

質問 # 46
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. Field Generation
B. Sales Email
C. Record Summary

正解：A

解説：
The correct answer isField Generationbecause this template type is designed to dynamically populate form fields with content generated by a large language model (LLM). In this scenario, leadership wants a dynamic form field that contains a summary or description generated by AI to aid customer interactions. Additionally, they want to keep a human in the loop, meaning the generated content will likely be reviewed or edited by a person before it's finalized, which aligns with theField Generationprompt template.
* Field Generation: This prompt type allows you to generate content for specific fields in Salesforce, leveraging large language models to create dynamic and contextual information. It ensures that AI content is available within the record where needed, but it allows human oversight or review, supporting the "human-in-the-loop" strategy.
* Sales Email: This prompt type is mainly used for generating email content for outreach or responses, which doesn't align directly with populating fields in a form.
* Record Summary: While this option might seem close, it is typically used to summarize entire records for high-level insights rather than filling specific fields with dynamic content based on AI generation.
Salesforce AI Specialist References:
* You can explore more about these prompt templates and AI capabilities through Salesforce documentation and official resources on Prompt Builder:https://help.salesforce.com/s/articleView?id=sf.
prompt_builder_templates_overview.htm

質問 # 47
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 Manager permission set was not assigned correctly.
B. The Prompt Template User permission set was not assigned correctly.
C. The large language model (LLM) was not configured correctly in Data Cloud.

正解：A

解説：
In order to access and create custom prompt templates inPrompt Builder, the AI Specialist must have the Prompt Template Managerpermission set assigned. Without this permission, they will not be able to access Prompt Builderin the Setup menu, even thoughEinstein Generative AIis enabled.
* Option Bis correct because thePrompt Template Managerpermission set is required to usePrompt Builder.
* Option A(Prompt Template User permission set) is incorrect because this permission allows users to use prompts, but not create or manage them.
* Option C(LLM configuration in Data Cloud) is unrelated to the ability to accessPrompt Builder.
References:
* Salesforce Prompt Builder Permissions:https://help.salesforce.com/s/articleView?id=sf.
prompt_builder_permissions.htm

質問 # 48
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?

A. Field Generation, and that Dynamic Forms is enabled
B. Field Generation, and that Dynamic Fields is enabled
C. Flex, and that Dynamic Fields is enabled

正解：B

解説：
When creating acustom prompt templateto populate a field with generated output, the most appropriate template type isField Generation. This template is specifically designed for generating field-specific outputs using generative AI.
Additionally, the AI Specialist must ensure thatDynamic Fieldsare enabled.Dynamic Fieldsallow the system to use real-time data inputs from related records or fields when generating content, ensuring that the AI output is contextually accurate and relevant. This is crucial when populating specific fields with AI-generated content, as it ensures the data source remains dynamic and up-to-date.
TheEinstein Trust Layerwill track and audit the interactions to ensure the organization can monitor AI adoption and make necessary enhancements based on AI usage patterns.
For further reading, refer to Salesforce's guidelines onField Generation templatesand theEinstein Trust Layer.

質問 # 49
Universal Containers (UC) wants to use Flow to bring data from unified Data Cloud objects to prompt templates.
Which type of flow should UC use?

A. Template-triggered prompt flow
B. Unified-object linking flow
C. Data Cloud-triggered flow

正解：C

解説：
In this scenario,Universal Containerswants to bring data fromunified Data Cloud objectsinto prompt templates, and the best way to do that is through aData Cloud-triggered flow. This type of flow is specifically designed to trigger actions based on data changes within Salesforce Data Cloud objects.
Data Cloud-triggered flows can listen for changes in the unified data model and automatically bring relevant data into the system, making it available for prompt templates. This ensures that the data is both real-time and up-to-date when used in generative AI contexts.
For more detailed guidance, refer to Salesforce documentation onData Cloud-triggered flowsandData Cloud integrationswith generative AI solutions.

質問 # 50
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. Request the Einstein Generative AI Audit Data from the Security section of the Setup menu.
B. Enable the collection and storage of Einstein Generative AI Audit Data on the Einstein Feedback setup page.
C. Use a Flow-based resource in Prompt Builder to debug the fields' merge values using Flow Debugger.

正解：A

解説：
To begin validating that the correct fields are being masked in Einstein Trust Layer, the AI Specialist should request the Einstein Generative AI Audit Data from the Security section of the Salesforce Setup menu. This audit data allows the AI Specialist to see how data is being processed, including which fields are being masked, providing transparency and validation that the configuration is working as expected.
Option B is correct because it allows for the retrieval of audit data that can be used to validate data masking.
Option A (Flow Debugger) and Option C (Einstein Feedback) do not relate to validating field masking in the context of the Einstein Trust Layer.
Reference:
Salesforce Einstein Trust Layer Documentation: https://help.salesforce.com/s/articleView?id=sf.einstein_trust_layer_audit.htm

質問 # 51
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 for the prompt template?

A. Create a flow to retrieve the opportunity information.
B. Select the Account Opportunity object as a resource when creating the prompt template.
C. Select the latest Opportunities related list as a merge field.

正解：A

解説：
To gather the necessary data for populating the Latest Opportunities Summary custom field on the Account object with information from the three most recently opened opportunities, the AI Specialist should create a flow. A flow can be configured to query and retrieve the required opportunity records based on criteria such as their open date. Once the flow has gathered the necessary data, it can be used in a prompt template or other automation processes to populate the custom field on the Account record.
Option A is correct because creating a flow allows for dynamic data retrieval and control over the logic for selecting the most recent opportunities.
Option B and Option C do not provide sufficient control or data retrieval capabilities needed for this scenario.
Reference:
Salesforce Flow Documentation: https://help.salesforce.com/s/articleView?id=sf.flow.htm

質問 # 52
What is best practice when refining Einstein Copilot custom action instructions?

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

正解：B

解説：
When refiningEinstein Copilot custom action instructions, it is considered best practice toprovide examples of user messagesthat are expected to trigger the action. This helps ensure that the custom action understands a variety of user inputs and can effectively respond to the intent behind the messages.
* Option B(consistent phrases) can improve clarity but does not directly refine the triggering logic.
* Option C(specifying a persona) is not as crucial as giving examples that illustrate how users will interact with the custom action.
For more details, refer toSalesforce's Einstein Copilot documentationon building and refining custom actions.

質問 # 53
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 that can be processed by the LLM varies with total user demand.
B. The number of tokens generated by the dynamic nature of the prompt template will vary by record.
C. The template type needs to be switched to Flex to accommodate the variable amount of tokens generated by the prompt grounding.

正解：B

解説：
The reason behind the token limit errors lies in the dynamic nature of the prompt template used in Field Generation. In Salesforce's AI generative models, each prompt and its corresponding output are subject to a token limit, which encompasses both the input and output of the large language model (LLM). Since the prompt template dynamically adjusts based on the specific data of each record, the number of tokens varies per record. Some records may generate longer outputs based on their data attributes, pushing the token count beyond the allowable limit for the LLM, resulting in token limit errors.
This behavior explains why users experience random failures-it is dependent on the specific data used in each case. For certain records, the combined input and output may fall within the token limit, while for others, it may exceed it. This variation is intrinsic to how dynamic templates interact with large language models.
Salesforce provides guidance in their documentation, stating that prompt template design should take into account token limits and suggests testing with varied records to avoid such random errors. It does not mention switching to Flex template type as a solution, nor does it suggest that token limits fluctuate with user demand.
Token limits are a constant defined by the model itself, independent of external user load.
References:
* Salesforce Developer Documentation onToken Limits for Generative AI Models
* Salesforce AI Best Practices on Prompt Design (Trailhead or Salesforce blog resources)

質問 # 54
......

Salesforce Salesforce-AI-Specialist 認定試験の出題範囲：

トピック	出題範囲
トピック 1	Einstein Trust Layer: このセクションでは、セキュリティプロトコルの実装とデータプライバシーの保護を担当する Salesforce AI スペシャリストのスキルを評価します。Einstein Trust Layer のセキュリティ、プライバシー、および基本機能に重点が置かれています。
トピック 2	プロンプトビルダー: このセクションでは、Salesforce の AI ツールを扱う AI スペシャリストの専門知識を評価します。プロンプトビルダー機能に重点を置き、候補者はビジネスニーズに基づいてその使用方法を理解する必要があります。
トピック 3	モデルビルダー: 試験のこの部分では、Salesforce 環境内で AI モデルを操作する Salesforce AI スペシャリストの専門知識に重点が置かれています。受験者は、モデルビルダーを使用するタイミングと、ビジネスニーズを満たすために標準、カスタム、または Bring Your Own Large Language Model (BYOLLM) 生成モデルを構成する方法に関する知識を証明する必要があります。
トピック 4	Agentforce ツール: このトピックでは、AI スペシャリストが適切な場合にエージェントを使用して知識を獲得します。さらに、このトピックでは、エージェントの動作と Agentforce の推論エンジンについて説明します。最後に、このトピックでは、エージェントの採用の管理と監視に焦点を当てます。
トピック 5	CRM アプリケーションにおける生成 AI: 試験のこの部分では、CRM システム内の生成 AI に関する AI スペシャリストの知識を評価します。Einstein for Sales および Einstein for Service における生成 AI 機能の使用について取り上げます。