Model Builder 8% Flashcards
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?
A. Product recommendation prediction
B. Customer churn prediction
C. Contract Renewal Date prediction
B. Customer churn prediction
https://help.salesforce.com/s/articleView?id=sf.c360_a_ai_ec_use_cases.htm&type=5
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. Security and data privacy are critical concerns for the client.
How should the AI Specialist integrate the custom LLM into Salesforce?
A. Add the fine-tuned LLM in Einstein Studio Model Builder.
B. Enable model endpoint on OpenAl and make callouts to the model to generate emails.
C. Create an application of the custom LLM and embed it in Sales Cloud via iFrame.
A. Add the fine-tuned LLM in Einstein Studio Model Builder.
https://help.salesforce.com/s/articleView?language=en_US&id=sf.c360_a_ai_foundation_models.htm&type=5
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?
A. It shows the full text that is sent to the Trust Layer.
B. It shows the response from the LLM based on the sample record.
C. It shows which sensitive data is masked before it is sent to the LLM.
A. It shows the full text that is sent to the Trust Layer.
In Model Playground, which hyper parameters of an existing Salesforce-enabled foundational model can an AI Specialist change?
A. Temperature, Top-k sampling, Presence Penalty
B. Temperature, Frequency Penalty, Presence Penalty
C. Temperature, Frequency Penalty, Output Tokens
B. Temperature, Frequency Penalty, Presence Penalty
https://help.salesforce.com/s/articleView?id=sf.c360_a_ai_foundation_models_configure.htm&type=5
Universal Containers wants to use an external large language model (LLM) in Prompt Builder.
What should an AI Specialist recommend?
A. Use Apex to connect to an external LLM and ground the prompt.
B. Use BYO-LLM functionality in Einstein Studio
C. Use Flow and External Services to bring data from an external LLM.
B. Use BYO-LLM functionality in Einstein Studio
https://help.salesforce.com/s/articleView?id=sf.c360_a_ai_foundation_models_configure.htm&type=5
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
A. REST API
An AI specialist is editing a model conguration associated with a foundation
model in the Model Playground. Which hyperparameter can they adjust to
increase the creativity of the generated responses?
A. Frequency Penalty
B. Temperature
C. Presence Penalty
B. Temperature
Temperature is a hyperparameter adjust creativity
An AI specialist is creating a new model conguration in the Model
Playground. Which hyperparameter can they adjust to increase the number of
unique words used in the generated responses?
A. Temperature
B. Presence Penalty
C. Frequency Penalty
B. Presence Penalty
Presence Penalty is a hyperparameter used to encourage diversity
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. Predictive model and generative model
B. Generative model
C. Predictive model
C. Predictive model
