Defining success criteria for agents in Agentic AI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define a success criterion function that returns True if the agent's score is above 80.

Agentic AI

def success_criterion(score):
    return score [1] 80

Drag options to blanks, or click blank then click option'

A<

B>

C==

D<=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' will mark low scores as success.

Using '==' is too strict and only accepts exactly 80.

The success criterion checks if the score is greater than 80, so the correct operator is '>'.

2fill in blank

medium

Complete the code to define a function that returns True if the agent's task completion time is less than the allowed time.

Agentic AI

def success_criterion(completion_time, allowed_time):
    return completion_time [1] allowed_time

Drag options to blanks, or click blank then click option'

A<

B>

C>=

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using '>' would mean finishing after the allowed time is success.

Using '==' is too strict and only accepts exact matches.

The agent succeeds if it finishes before the allowed time, so completion_time must be less than allowed_time.

3fill in blank

hard

Fix the error in the success check that should return True if the agent's accuracy is at least 90%.

Agentic AI

def success_criterion(accuracy):
    return accuracy [1] 0.9

Drag options to blanks, or click blank then click option'

A>=

B<

C<=

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' or '<=' would mark low accuracy as success.

Using '==' only accepts exactly 0.9 accuracy.

The success criterion requires accuracy to be at least 90%, so '>=' is the correct operator.

4fill in blank

hard

Fill both blanks to create a success criterion that returns True if the agent's reward is greater than 50 and the error is less than 0.1.

Agentic AI

def success_criterion(reward, error):
    return reward [1] 50 and error [2] 0.1

Drag options to blanks, or click blank then click option'

A>

B<

C>=

D<=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '>=' or '<=' changes the strictness of the condition.

Mixing up the operators reverses the logic.

The agent succeeds if reward is greater than 50 and error is less than 0.1, so the operators are '>' and '<'.

5fill in blank

hard

Fill all three blanks to define a success criterion that returns True if the agent's score is at least 75, time is less than 120, and errors are at most 5.

Agentic AI

def success_criterion(score, time, errors):
    return score [1] 75 and time [2] 120 and errors [3] 5

Drag options to blanks, or click blank then click option'

A>=

B<

C<=

D>

Attempts:

3 left

💡 Hint

Common Mistakes

Using '>' instead of '>=' excludes exact 75 score.

Using '>' or '>=' for time or errors reverses the logic.

The agent succeeds if score >= 75, time < 120, and errors <= 5, so the operators are '>=', '<', and '<=' respectively.