Supervisor agent pattern in Agentic AI

Introduction

The supervisor agent pattern helps manage multiple AI agents by overseeing their tasks and making sure they work well together.

When you have several AI agents working on parts of a big problem and need to coordinate them.

When you want to check the quality of results from different agents before finalizing an answer.

When tasks are complex and require breaking down into smaller steps handled by different agents.

When you want to improve reliability by having a supervisor catch mistakes or conflicts.

When you want to combine strengths of different AI agents for better overall performance.

Syntax

Agentic AI

class SupervisorAgent:
    def __init__(self, agents):
        self.agents = agents

    def supervise(self, task):
        results = [agent.perform(task) for agent in self.agents]
        final_result = self.evaluate(results)
        return final_result

    def evaluate(self, results):
        # Combine or select best result
        pass

The supervisor agent holds references to other agents it manages.

It collects results from agents and decides the best or combined output.

Examples

A simple agent that returns a string result for a task.

Agentic AI

class Agent:
    def perform(self, task):
        return f"Result from {task}"

Supervisor collects results and picks one based on a simple rule.

Agentic AI

class SupervisorAgent:
    def __init__(self, agents):
        self.agents = agents

    def supervise(self, task):
        results = [agent.perform(task) for agent in self.agents]
        return max(results)  # picks the lexicographically largest result

Sample Model

This program shows two agents doing the same task. The supervisor collects their results and picks the longest one as the final answer.

Agentic AI

class Agent:
    def __init__(self, name):
        self.name = name

    def perform(self, task):
        return f"{self.name} completed {task}"

class SupervisorAgent:
    def __init__(self, agents):
        self.agents = agents

    def supervise(self, task):
        results = [agent.perform(task) for agent in self.agents]
        print("Agent results:")
        for r in results:
            print(r)
        final = self.evaluate(results)
        return final

    def evaluate(self, results):
        # For demo, pick the longest result string
        return max(results, key=len)

# Create agents
agent1 = Agent("AgentA")
agent2 = Agent("AgentB")

# Create supervisor
supervisor = SupervisorAgent([agent1, agent2])

# Run supervision
final_output = supervisor.supervise("task1")
print("Final chosen result:", final_output)

Important Notes

The supervisor agent pattern helps organize teamwork among AI agents.

Evaluation logic can be simple or complex depending on the problem.

This pattern improves reliability by checking multiple agent outputs.

Summary

Supervisor agent manages and coordinates multiple AI agents.

It collects and evaluates results to decide the best output.

Useful for complex tasks needing teamwork and quality control.

Practice

1. What is the main role of a Supervisor agent in the supervisor agent pattern?

easy

A. To collect raw data from sensors

B. To train a single AI model

C. To replace all other agents with one

D. To manage and coordinate multiple AI agents

Solution

1. Step 1: Understand the supervisor agent's purpose

   The supervisor agent is designed to oversee and coordinate multiple AI agents working together.

2. Step 2: Differentiate from other roles

   Unlike training or data collection, the supervisor agent focuses on managing teamwork and quality control.

3. Final Answer:

   To manage and coordinate multiple AI agents -> Option D

4. Quick Check:

   Supervisor agent = manager of multiple agents [OK]

Hint: Supervisor agent = team manager of AI agents [OK]

Common Mistakes:

• Confusing supervisor with data collector
• Thinking supervisor trains models directly
• Assuming supervisor replaces all agents

2. Which of the following is the correct way to describe the supervisor agent's function in code?

easy

A. supervisor.replace_agents()

B. supervisor.train_single_model(data)

C. supervisor.collect_results(agents)

D. supervisor.ignore_agent_outputs()

Solution

1. Step 1: Identify supervisor's interaction with agents

   The supervisor collects and evaluates results from multiple agents, so a method like collect_results fits.

2. Step 2: Eliminate incorrect options

   Training a single model, replacing agents, or ignoring outputs do not match the supervisor's coordination role.

3. Final Answer:

   supervisor.collect_results(agents) -> Option C

4. Quick Check:

   Supervisor collects results = collect_results() [OK]

Hint: Supervisor collects and evaluates agent outputs [OK]

Common Mistakes:

• Choosing training method instead of collection
• Thinking supervisor replaces agents
• Ignoring outputs contradicts supervisor role

3. Given this code snippet for a supervisor agent pattern, what will be the printed output?

class Agent:
    def __init__(self, name, score):
        self.name = name
        self.score = score

class Supervisor:
    def __init__(self, agents):
        self.agents = agents
    def best_agent(self):
        return max(self.agents, key=lambda a: a.score).name

agents = [Agent('A1', 85), Agent('A2', 90), Agent('A3', 88)]
supervisor = Supervisor(agents)
print(supervisor.best_agent())

medium

A. A1

B. A2

C. A3

D. None

Solution

1. Step 1: Understand the agent scores

   Agents have scores: A1=85, A2=90, A3=88.

2. Step 2: Identify the agent with the highest score

   The best_agent method returns the name of the agent with the max score, which is A2 with 90.

3. Final Answer:

   A2 -> Option B

4. Quick Check:

   Max score agent = A2 [OK]

Hint: Max score agent name is printed [OK]

Common Mistakes:

• Choosing agent with second highest score
• Confusing agent names
• Assuming None if not found

4. Identify the bug in this supervisor agent code snippet:

class Supervisor:
    def __init__(self, agents):
        self.agents = agents
    def best_score(self):
        return max(self.agents, key=lambda a: a.score)

agents = [{'name': 'A1', 'score': 80}, {'name': 'A2', 'score': 95}]
supervisor = Supervisor(agents)
print(supervisor.best_score())

medium

A. Agents should be objects, not dictionaries

B. max() function is used incorrectly

C. Missing return statement in best_score

D. Supervisor class missing __init__ method

Solution

1. Step 1: Check agent data type and usage

   The best_score method expects agents with attribute score, but agents are dictionaries, not objects.

2. Step 2: Understand attribute vs key access

   Using a.score on a dictionary causes an error; dictionaries need a['score'].

3. Final Answer:

   Agents should be objects, not dictionaries -> Option A

4. Quick Check:

   Attribute access on dict causes error [OK]

Hint: Use objects or adjust attribute access for dicts [OK]

Common Mistakes:

• Thinking max() usage is wrong
• Missing return statement (it exists)
• Ignoring data type mismatch

5. You want to design a supervisor agent that combines outputs from three different AI agents solving a complex task. Which approach best fits the supervisor agent pattern?

hard

A. Collect outputs, evaluate quality, and select the best result

B. Run only the fastest agent and ignore others

C. Train all agents on the same data independently

D. Replace all agents with a single large model

Solution

1. Step 1: Understand supervisor agent's coordination role

   The supervisor should gather outputs from all agents and decide which is best based on quality.

2. Step 2: Evaluate other options

   Ignoring agents, training independently without coordination, or replacing agents contradict the supervisor pattern.

3. Final Answer:

   Collect outputs, evaluate quality, and select the best result -> Option A

4. Quick Check:

   Supervisor = collect + evaluate + select best [OK]

Hint: Supervisor picks best output from all agents [OK]

Common Mistakes:

• Ignoring some agents' outputs
• Confusing training with supervising
• Replacing agents instead of coordinating