Agent Orchestration Systems

Welcome back! In the previous lesson, you mastered building agentic pipelines in which specialized agents work together in a fixed sequence. Today, we're taking a significant architectural leap forward by learning how to build agent orchestration systems, where a central planner agent can dynamically decide which specialist agents to call based on the specific task at hand.

The key insight is that complex agentic systems can be wrapped as simple tools for other agents. This creates a powerful hierarchy in which agents can leverage the full capabilities of other agents as easily as they use basic functions, enabling much more flexible and intelligent problem-solving than fixed pipeline sequences.

The fundamental difference between pipelines and orchestration lies in decision-making authority. In a pipeline, you, as the developer, decide the sequence: every problem goes through analysis, then calculation, then presentation. In orchestration, the central agent makes these decisions dynamically based on the nature of each specific request. The key insight is that we can encapsulate an agent call as a tool, allowing an orchestrator agent with access to that tool to seamlessly call another specialist agent.

Here's how the agent orchestration flow works:

1. User submits a request to the orchestrator agent
2. Orchestrator analyzes the request and decides whether to handle it directly or delegate to a specialist
3. If delegation is needed, the orchestrator calls the specialist agent as a tool
4. Specialist processes the request and returns results to the orchestrator
5. Orchestrator provides the final response to the user

Consider how this changes the system's behavior. If someone asks, "What is the capital of France?", a pipeline system would still run the question through all three agents unnecessarily. An orchestrated system, however, allows the central agent to recognize that this is a straightforward knowledge question requiring no mathematical tools and respond directly. But when someone asks about solving equations, the orchestrator can intelligently delegate this to a calculator specialist. This dynamic delegation creates systems that are both more efficient and more capable.

Before we can orchestrate agents, we need to create the specialist agents that will serve as tools. Let's build a calculator assistant that specializes in mathematical problem-solving, designed to work as a standalone tool that can handle mathematical questions from start to finish.

import json
from agent import Agent
from functions import (
    sum_numbers, multiply_numbers, subtract_numbers,
    divide_numbers, power, square_root
)

# Load tool schemas
with open('schemas.json', 'r') as f:
    tool_schemas = json.load(f)

# Math tools
math_tools = {
    "sum_numbers": sum_numbers,
    "multiply_numbers": multiply_numbers,
    "subtract_numbers": subtract_numbers,
    "divide_numbers": divide_numbers,
    "power": power,
    "square_root": square_root
}

# Create a calculator assistant
calculator_assistant = Agent(
    name="calculator_assistant",
    system_prompt="Calculator assistant for equations and numeric problems.",
    tools=math_tools,
    tool_schemas=tool_schemas
)

This calculator assistant is designed as a complete mathematical problem-solver with access to all the mathematical tools. The concise system prompt establishes the agent's focus on mathematical calculations and equations while allowing it the flexibility to handle various types of mathematical problems. This balance is important for specialist agents — they need clear domain focus while maintaining enough flexibility to be useful as tools for different orchestrators.

To enable agents to use other agents as tools, we need to wrap any agent into a callable function that follows the same interface as our other tools. This helper function will streamline our workflow: we'll call it with our specialist agent to get back both a callable function and its schema, which we can then pass to our orchestrator agent, enabling it to call the specialist agent just like any other tool.

def create_agent_tool(agent, description):
    """
    Create a tool function and schema for using an agent as a tool.
    
    Args:
        agent: The agent to wrap as a tool
        description: Description of what this agent tool does
    
    Returns:
        tuple: (tool_function, tool_schema)
    """
    def agent_tool_function(message):
        # Call the agent
        _, response = agent.run([{"role": "user", "content": message}])
        
        return response
    
    # Create schema for this agent tool
    tool_schema = {
        "name": f"{agent.name}_agent",
        "description": description,
        "parameters": {
            "type": "object",
            "properties": {
                "message": {
                    "type": "string",
                    "description": "Message to send to the agent"
                }
            },
            "required": ["message"]
        }
    }
    
    return agent_tool_function, tool_schema

The key part of this function is the inner agent_tool_function. When we call agent.run(), it returns two things: the complete message history and the final text response. We use _ to ignore the message history because when one agent calls another as a tool, it only needs the final answer — not the entire conversation history with all the intermediate function calls and reasoning steps.

For example, if our orchestrator asks the calculator agent to solve an equation, it just wants the final answer, like "x = 3 and x = 2," not the detailed trace of every mathematical function that was called along the way. This keeps the tool interface clean and focused on results.

The tool schema follows the standard format with a parameters object that defines what inputs the tool expects. In this case, we only need a single message parameter that will contain the question or task to send to the specialist agent.

With our specialist agent ready and our wrapper function defined, we can now create the agent tool wrapper and build our orchestrator agent. The orchestrator will be a general-purpose assistant that can handle various types of questions, using the calculator assistant when mathematical expertise is needed.

# Create agent tool for calculator
calculator_tool_function, calculator_tool_schema = create_agent_tool(
    calculator_assistant,
    "Call the calculator assistant to solve mathematical problems and equations."
)

# Create a general assistant
helpful_assistant = Agent(
    name="helpful_assistant",
    system_prompt="You can use the calculator tool for math problems.",
    tools={calculator_tool_schema["name"]: calculator_tool_function},
    tool_schemas=[calculator_tool_schema]
)

The orchestrator agent (helpful_assistant) has a minimal system prompt that simply informs it about the availability of the calculator tool for mathematical problems. This straightforward approach allows the agent to understand its capabilities without over-constraining its behavior. Notice how we pass the calculator tool to the orchestrator just like any other tool — from the orchestrator's perspective, calling another agent is no different from calling a mathematical function.

Let's test our orchestrated system with a general knowledge question to see how the orchestrator handles tasks that don't require specialist agents.

# Create a message list with a general knowledge question
messages = [{'role': 'user', 'content': 'What is the capital of France?'}]

# Run the orchestrator agent
_, response = helpful_assistant.run(messages)

# Display the orchestrator's response to the user
print(response)

When we run this code, the orchestrator agent will receive the question and analyze whether it needs specialist assistance. Since this is a straightforward factual question about geography, the agent should recognize that it can provide the answer directly from its general knowledge without calling any tools.

Here's what happens when we execute this request:

Paris.

The orchestrator correctly identified this as a question it could handle directly using its general knowledge without calling any tools. The response was immediate and appropriate, demonstrating the system's efficiency for simple tasks that don't require specialist assistance.

Now let's test the system with a mathematical question that requires the specialist agent's expertise.

# Create a message list with a mathematical equation
messages = [{'role': 'user', 'content': 'What is the solution to the equation x^2 - 5x + 6 = 0?'}]

# Run the orchestrator agent
_, response = helpful_assistant.run(messages)

# Display the orchestrator's response to the user
print('\n=== Final Response ===\n')
print(response)

In this example, the orchestrator will recognize that solving a quadratic equation requires mathematical expertise beyond basic knowledge. The agent should automatically decide to delegate this task to the calculator assistant tool, which will then use its mathematical functions to solve the equation step by step.

Here's the complete execution trace showing the delegation and calculation process:

🔧 Tool called: calculator_assistant_agent({'message': 'Solve the quadratic equation: x^2 - 5x + 6 = 0'})
🔧 Tool called: power({'base': -5, 'exponent': 2})
🔧 Tool called: multiply_numbers({'a': 1, 'b': 6})
🔧 Tool called: multiply_numbers({'a': 4, 'b': 1})
🔧 Tool called: multiply_numbers({'a': -1, 'b': -5})
🔧 Tool called: power({'base': -5, 'exponent': 2})
🔧 Tool called: power({'base': -5, 'exponent': 2})
🔧 Tool called: multiply_numbers({'a': 4, 'b': 6})
🔧 Tool called: power({'base': -5, 'exponent': 2})
🔧 Tool called: multiply_numbers({'a': 4, 'b': 6})
🔧 Tool called: power({'base': -5, 'exponent': 2})
🔧 Tool called: multiply_numbers({'a': 4, 'b': 6})
🔧 Tool called: power({'base': -5, 'exponent': 2})
🔧 Tool called: multiply_numbers({'a': 4, 'b': 6})

=== Final Response ===

The solutions are x = 2 and x = 3.

For the mathematical equation, the orchestrator recognized that this required mathematical expertise and delegated the task to the calculator assistant. The debug output shows the orchestrator calling the calculator_assistant_agent tool with the original question. The calculator assistant then processes the request internally, using various mathematical functions to solve the quadratic equation. Note that the internal workings of the calculator assistant (the agent tool delegation and its response) happen behind the scenes — the orchestrator simply receives the final answer and presents it to the user, demonstrating the clean separation between the orchestrator and specialist layers.

You've now learned how to build agent orchestration systems in which a central planner can dynamically delegate tasks to specialist agents. This architectural pattern offers significant advantages over fixed pipelines: it's more efficient for simple tasks, more flexible for complex problems, and allows you to build increasingly sophisticated specialist agents without complicating the overall system design.

In your upcoming practice exercises, you'll build your own orchestrated agent systems with multiple specialists for different domains. This foundation will enable you to create much more sophisticated and flexible agentic systems that can adapt their approach based on the specific requirements of each task.