Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

AI > Data Cloud > Flashcards

Data Cloud Flashcards

1
Q

What are two agentforce guardrails?

A
  1. Natural-language instructions telling the agent what it can and can’t do.
  2. Built-in security features in the Einstein Trust Layer
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

When is it best practice to connect orgs using Data Cloud One?

A

When you want to centralize control across orgs and minimize data silos

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What type of connection lets Salesforce orgs power platform features with Data Cloud data?

A

Companion Connection

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

3 types of connections that allow SF orgs to use data cloud data to power platform features

A
  1. Standard SF CRM Connections
  2. Data Cloud One companion connections
  3. Data Sources
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Performance is evaluated on what type of set?

A

Test Set

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is Data Cleaning?

A

Remove irrelevant data, correcting errors, and possibly anonymizing sensitive information.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Data Collection is what?

A

Accumulate relevant data for the specific domain or task. This might involve gathering user interactions or using domain-specific data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Try to list 5 of these known Harm Distribution Bias taxonomies

A

race
sex
religion
nation of origin, citizenship, immigrant status
disability
age
financial means
sexual orientation or gender identity
information and communication
transportation and storage
Arts
Entertainment and recreation
law enforcement
wholesale and retail trade
public administration
human health and social work activities
administrative and support service activities
Education
Defense
Real Estate
Service
Manufacturing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is a Harm Taxonomy?

A

1) an entity that experienced
2) a harm event or harm issue that
3) can be directly linked to a consequence of the behavior of
4) an AI system.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What are the 3 forms of data that an org gathers?

A
  1. Structured
  2. Semi-structured
    3.Unstructured
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Types of Unstructured data can be…

A

Chat Transcripts
Audio files
Video files
Emails
Legal Documents
Large texts ie books or articles

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Data Cloud references unstructured data in what formats?

A

HTML
TXT
PDF

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are some connections Data Cloud already supports?

A

Amazon S3
Azure Blob Storage
Google Cloud Storage

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

How do you reference unstructured data through a connection?

A

Create a connection between your external blob store and Data Cloud
Create an unstructured data lake object (UDLO) and map it to an unstructured data model object (UDMO).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is a UDLO?

A

Unstructured Data lake object

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is a UDMO?

A

Unstructured Data Model Object

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What type of chunking strategies does Data Cloud support?

A
  1. HTML - based passage extraction chunking strategy
    2.Token Based extraction strategy
18
Q

Chunking:
Semantic-based passage extraction use what meaning?

A

The semantic meaning inherent in HTML tags to chunk a document into passages.

19
Q

How is semantic based extraction done using HTML elements?

A

Chunks a document into passages.
HTML elements such as headings (<h1>, <h2>), lists (<ul>, <ol>), or bold text (<strong>) acting as a subheading are considered logical boundaries for passages.</strong></ol></ul></h2></h1>

20
Q

Chunking: Window-based extraction strategies use what elements?

A

Block level elements

21
Q

Chunking:
Examples of block level elements for window extraction strategies

A

<div> and <p> tags
raw text separated by line breaks to chunk documents into passages.
If a paragraph doesn’t contain any HTML, the extraction is done at the sentence level.</p></div>

22
Q

Examples of HTML elements when chunking of a document into passages

A

headings (<h1>, <h2>),
lists (<ul>, <ol>), or
bold text (<strong>) acting as a subheading are considered logical boundaries for passages.</strong></ol></ul></h2></h1>

23
Q

With token-based extraction, chunked content is divided how?

A

Divided into tokens so that it can be vectorized

24
Q

What is a BLOB?

A

Binary Large Object that stores binary data.

25
Q

When you chunk UDMOs or DMOs, you break them down into manageable, semantically meaningful chunks. These units of text are stored in Data Cloud in chunk data model objects. These are called?

A

CDMO’s

26
Q

CDMO’s are created from?

A

Data model objects or
Unstructured data model objects

27
Q
A
28
Q

Vectorized (in regards to chunking & token based extraction) is the process of…?

A

Turning data into numerical vectors that are machine readable.

29
Q

Machine readable vectors can be the following:

A

1.Sentences
2.Words
3. Letters
4. Punctuation

30
Q

Vector Embeddings are?

A

Numerical representations of text that store relationships between words or phrases.

31
Q

What do Vector Embeddings do?

A

Captures the semantic meaning of the content, so chunks of content that are semantically similar have similar vector embeddings.

32
Q

How does capturing the semantic meaning of content through vector embeddings help machines?

A

It helps machines to process and comprehend language effectively.

Salesforce Help.https://help.salesforce.com/s/articleView?language=en_US&id=sf.c360_a_search_index_grounding.htm&type=5&_ga=2.204830608.1056163890.1727635727-1818110520.1727635700

33
Q

Search Index Configurations changes to which stages as it processes data from the source DMO/UDMO?

A

Submitted to In progress

34
Q

Where can you find the ready status?

A

Data model under status

35
Q

What is Atlas Reasoning Engine?

A

Brain behind Agentforce.

36
Q

How does Atlas Reasoning Engine Work?

A

Atlas generates a plan based on wht the role is trying to do, then ealuates and refines its plan (if required it can loop to pull in additional data).
When taking an action it will look at what business process (eg flows) should be used. FInally it engages wiht the customer or eemployee basedon their channel preference

37
Q

What are the 4 components of needed to connect a websites data to Data Cloud?

A

Data Capture Rules
Event Definitions
Javascript Beacon
Data Stream

38
Q

What is another name for the JavaScript Beacon?

A

CDN or CDN Script

39
Q

CDN script stands for?

A

Content Delivery Network

40
Q

The CDN Script looks like this:

A
41
Q

Which of the following occurs after an event definition and data capture have been implemented?

A) A developer selects Website as the Connector type.
B) Data from Salesforce CRM gets ingested into Data Cloud.
C) A marketing specialist creates a new website.
D) The JavaScript beacon is embedded as a script tag in the website.

A

D) The JavaScript beacon is embedded as a script tag in the website.

42
Q

What are the three necessary components to connect website data to Data Cloud?

A) Event definition, data capture, and JavaScript beacon
B) Data beacon, event capture, and data definition
C) Quantum encryption module, neural network interface, and hyperloop data transfer protocol
D) API key, SSL certificate, and a web analytics tool

A

A) Event definition, data capture, and JavaScript beacon

AI (4 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions