Single agent vs multi-agent systems in Agentic AI - Interactive Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define a single agent that takes an action.

Agentic AI

class Agent:
    def act(self, state):
        return [1]

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

ANone

Bstate

C'move_forward'

Dself

Attempts:

3 left

💡 Hint

Common Mistakes

Returning the state instead of an action.

Returning None or self which are not valid actions.

The agent's act method should return an action, here the string 'move_forward'.

2fill in blank

medium

Complete the code to initialize a multi-agent system with two agents.

Agentic AI

class MultiAgentSystem:
    def __init__(self):
        self.agents = [[1], Agent()]

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

AAgent()

BAgent

Cagents

Dself

Attempts:

3 left

💡 Hint

Common Mistakes

Using the class name without parentheses.

Using undefined variables.

We need to create instances of Agent using Agent() to add to the list.

3fill in blank

hard

Fix the error in the method that collects actions from all agents.

Agentic AI

def get_actions(self, state):
    return [agent.[1](state) for agent in self.agents]

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

Amove

Brun

Caction

Dact

Attempts:

3 left

💡 Hint

Common Mistakes

Using method names that do not exist like 'move' or 'run'.

The method to get an agent's action is called act.

4fill in blank

hard

Fill both blanks to create a dictionary of agent actions keyed by agent id.

Agentic AI

def actions_dict(self, state):
    return {agent.[1]: agent.[2](state) for agent in self.agents}

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

Aid

Bact

Cname

Dstate

Attempts:

3 left

💡 Hint

Common Mistakes

Using name instead of id.

Using state instead of calling act.

Use agent.id as the key and agent.act(state) as the value.

5fill in blank

hard

Fill all three blanks to implement a step where all agents act and results are collected.

Agentic AI

def step(self, state):
    results = {agent.[1]: agent.[2](state) for agent in self.agents}
    return results if results else [3]

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

Aid

Bact

C{}

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Returning None instead of an empty dictionary.

Using wrong attribute or method names.

Use agent.id as keys, agent.act(state) as values, and return an empty dictionary if no results.