AI Concepts Flashcards
Why are parameters important in large language models?
Because they can define the computing resources required for training the model
Because they improve the model’s ability to generate humanlike text
Because they can allow more complexity in the model
Because they can help to reduce biases and errors in the model
Because they improve the model’s ability to generate humanlike text
What are the variables that the model learns during its training process?
Versions
Placeholders
Books
Parameters
Parameters
Which are Salesforce LLMs?
A
SalesGen, CodeSales, and CodeB5
B
ForceGen, ForceSales, and ForceTF
C
CodeGen, CodeT5+, and CodeTF
D
SalesGen, ForceSales, and CodeB5
C
CodeGen, CodeT5+, and CodeTF
True or false: To access an LLM in your Salesforce org, you must use either a Salesforce LLM or a domain-specific model that you trained.
False
What are the three main classifications of data?
A
Numerical, categorical, and time-series
B
Structured, unstructured, and semi-structured
C
Quantitative, qualitative, and mixed
D
Tabular, image, and text
B
Structured, unstructured, and semi-structured
What are prompts in the context of generative AI?
A
A question that makes the LLM write an email.
B
A line of code that helps the LLM find relevant data.
C
Conversation starters for team bonding.
D
Instructions that help the LLM generate content.
D
Instructions that help the LLM generate content.
What is a goal in a prompt?
A
What you hope to achieve with the model’s output
B
The type of content you want the model to create
C
A quantitative metric that measures prompt strength
D
A physical goal post that you throw prompts over
A
What you hope to achieve with the model’s output
How can you add business data to your prompt templates in Salesforce?
A
Merge fields
B
Flows
C
Trailhead badges
D
A and B
A and B
Which is the main benefit of using prompt templates?
A
They increase the volume of output from the LLM.
B
They ensure that the LLM’s response is hallucination-free.
C
They’re designed to handle complex logic.
D
They’re reusable, allowing you to scale.
D
They’re reusable, allowing you to scale.
What is required to create a field generation prompt template using Prompt Builder?
A
Template Name
B
Recipient Object
C
Object
D
A and B
E
A and C
Template Name & Object
What type of flow do you use with a field generation prompt template?
A
Generated Field Flow
B
Template-Triggered Prompt Flow
C
Field Prompt Template Flow
D
Flow Prompt Template Capability
B
Template-Triggered Prompt Flow
When reviewing a prompt response, which consideration ensures accuracy and avoids including unintended information?
A
Bias
B
Action/Goal Completion
C
Repetition
D
Factual Accuracy
D
Factual Accuracy
What are the two Prompt Builder features that allow users to preview prompt responses?
A
Response and Preview
B
Resolution and Response
C
Preview and Revise
D
Specifics and Resolution
B
Resolution and Response
The two Prompt Builder features that allow users to preview prompt responses are Resolution and Response.
The Preview section in Prompt Builder is divided into two parts:
- Resolution: This shows the “resolved” prompt, which is the prompt after merge fields have been replaced with selected record data.
- Response: This displays the generated text from the large language model (LLM) based on the resolved prompt[1].
These features allow users to see how their prompt template will be resolved with actual data and preview the AI-generated response before finalizing the template[1].
What does zero data retention mean?
A
The person who receives the response manually deletes the prompt and all its data.
B
The response remains masked.
C
The prompt remains masked.
D
The prompt, its responses, and all related data are forgotten by the LLM.
D
The prompt, its responses, and all related data are forgotten by the LLM.
How is a response scanned for toxic language?
A
The end user reviews the response.
B
The response is sent to a panel of reviewers.
C
The machine learning models are used to identify toxic content.
D
A third-party LLM checks and stores the response.
C
The machine learning models are used to identify toxic content.
What allows Agentforce to call different topics and actions as a conversation shifts?
A
The Trust Layer
B
The Atlas Reasoning Engine
C
The channels used in the conversation
D
The guardrails that exist
B
The Atlas Reasoning Engine
Agentforce SDR Agent is grounded in what three components?
A
A company’s sales data, sales reps comments, and Leads
B
A company’s sales reps feedback, Leads, and Opportunity records
C
A company’s product, Sales, and Lead records
D
A company’s sales, product, and customer data
D
A company’s sales, product, and customer data
