Responsible AI Tools & Practices Word Search
MediumFind each term hidden in the grid. Selecting a word reveals its definition and a link to study it in depth.
P
X
A
Q
Q
F
Z
D
I
H
M
C
J
Y
G
D
G
N
L
W
M
J
E
A
L
P
V
Z
I
X
Q
C
Y
A
L
Q
O
U
N
L
Y
K
J
I
B
E
K
C
F
F
O
Y
N
I
H
T
B
F
P
K
X
B
J
R
I
T
H
Q
I
B
H
Z
X
D
Q
P
R
G
R
P
R
O
Y
O
T
E
M
L
H
B
L
K
N
N
C
H
A
X
E
Q
O
B
U
D
W
A
E
D
I
P
H
P
L
I
D
O
R
T
R
E
I
P
H
I
C
V
M
I
C
C
L
C
W
A
U
N
O
I
K
K
U
V
Q
O
H
I
D
V
C
W
D
G
U
A
R
D
R
A
I
L
S
T
K
L
T
C
T
K
O
G
U
F
A
Z
V
R
Q
Y
E
P
B
D
P
P
O
O
L
N
A
M
U
H
D
D
W
O
F
W
U
U
H
G
H
G
Q
Z
O
E
O
D
D
J
W
W
D
A
Q
B
F
I
Z
C
A
M
K
Drag across letters, or tap the first and last letter. On a keyboard, use arrows + Enter.
Advertisement
Terms in this set
- Explainability The ability to explain why a model produced a particular output or decision.
- Guardrails Guardrails for Amazon Bedrock — configurable safety filters for FM inputs and outputs.
- Clarify Amazon SageMaker Clarify — detects bias in data and models and explains predictions.
- Model Monitor Amazon SageMaker Model Monitor — detects data and model quality drift in production.
- Model Card A document recording a model's intended use, performance, and limitations.
- Toxicity Harmful, offensive, or abusive content in model output.
- Human-in-the-Loop Inserting human review into an AI workflow for oversight on important decisions.