Why production agents need different architecture in Agentic AI - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define a production agent's main loop.

Agentic AI

while agent.is_active():
    action = agent.[1](input_data)
    agent.execute(action)

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

Adecide_action

Btrain_model

Cload_data

Dsave_state

Attempts:

3 left

💡 Hint

Common Mistakes

Using methods related to training or saving instead of deciding actions.

The method 'decide_action' is used by the agent to choose what to do next based on input data.

2fill in blank

medium

Complete the code to initialize a production agent with a specific architecture.

Agentic AI

agent = ProductionAgent(architecture=[1])

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

A'simple_nn'

B'reactive_architecture'

C'random_forest'

D'linear_regression'

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing architectures meant for static data or batch processing.

Production agents often use reactive architectures to respond quickly to changing environments.

3fill in blank

hard

Fix the error in the code that updates the agent's state in production.

Agentic AI

def update_state(self, input):
    self.state = self.state [1] input
    return self.state

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

A*=

B=

C-=

D+=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '=' replaces the state instead of updating it.

Using '+=' updates the current state by adding new input, which is typical in state updates.

4fill in blank

hard

Fill in the blank to create a dictionary comprehension that filters agent logs for errors.

Agentic AI

error_logs = {log_id: log for log_id, log in logs.items() if [1] in log}

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

A'error'

Bcontains

Cstartswith

D'warning'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'startswith' or filtering for 'warning' instead of 'error'.

We check if each log contains the string 'error' to filter error logs.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps agent IDs to their status if active.

Agentic AI

active_agents = {agent[1]: agent[2] for agent in agents if agent.status [3] 'active'}

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

A.id

B.status

C==

D!=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '!=' instead of '==' or wrong property names.

We map agent.id to agent.status only if the status equals 'active'.